20240202在Ubuntu20.04.6下使用whisper.cpp的显卡模式

20240202在Ubuntu20.04.6下使用whisper.cpp的显卡模式
2024/2/2 19:43

【结论：在Ubuntu20.04.6下，确认large模式识别7分钟中文视频，需要356447.78 ms，也就是356.5秒，需要大概5分钟！效率太差！】
前提条件，可以通过技术手段上外网！^_
首先你要有一张NVIDIA的显卡，比如我用的PDD拼多多的二手GTX1080显卡。【并且极其可能是矿卡！】800￥
2、请正确安装好NVIDIA最新的545版本的驱动程序和CUDA、cuDNN。
2、安装Torch
3、配置whisper

https://github.com/ggerganov/whisper.cpp
https://www.toutiao.com/article/7276732434920653312/?app=news_article×tamp=1706802934&use_new_style=1&req_id=2024020123553463D3509B1706BC79D479&group_id=7276732434920653312&tt_from=mobile_qq&utm_source=mobile_qq&utm_medium=toutiao_android&utm_campaign=client_share&share_token=7bcb7488-a03d-4291-96fb-d0835ac76cca&source=m_redirect
https://www.toutiao.com/article/7276732434920653312/
OpenAI的whisper的c/c++ 版本体验

首先下载代码,注：我的OS环境是Ubuntu20.04.6。
git clone https://github.com/ggerganov/whisper.cpp

下载成功后进入项目目录：
cd whisper.cpp

执行如下脚本命令下载模型，这里选择的base 版本，我们先来测试英语识别：
bash ./models/download-ggml-model.sh base.en
但是尝试了几次都无法下载成功，报错消息如下：

网上search 了一下，找到可提供下载的链接：
https://github.com/ggerganov/whisper.cpp/tree/master/models
https://huggingface.co/ggerganov/whisper.cpp/tree/main
我选择下载全部35个文件！

下载成功后将模型文件copy 到项目中的models目录：
cp ~/Downloads/ggml-base.en.gin /home/havelet/ai/whisper.cpp/models

接下来执行如下编译命令：
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ make clean
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ WHISPER_CLBLAST=1 make -j16

执行结果如下：
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ WHISPER_CUBLAS=1 make
I whisper.cpp build info: 
I UNAME_S:  Linux
I UNAME_P:  x86_64
I UNAME_M:  x86_64
I CFLAGS:   -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include
I LDFLAGS:   -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib
I CC:       cc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
I CXX:      g++ (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0

nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -Wno-pedantic -c ggml-cuda.cu -o ggml-cuda.o
cc  -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include   -c ggml.c -o ggml.o
cc  -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include   -c ggml-alloc.c -o ggml-alloc.o
cc  -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include   -c ggml-backend.c -o ggml-backend.o
cc  -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include   -c ggml-quants.c -o ggml-quants.o
g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -c whisper.cpp -o whisper.o
g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include examples/main/main.cpp examples/common.cpp examples/common-ggml.cpp ggml-cuda.o ggml.o ggml-alloc.o ggml-backend.o ggml-quants.o whisper.o -o main  -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib
./main -h

usage: ./main [options] file0.wav file1.wav ...

options:
  -h,        --help              [default] show this help message and exit
  -t N,      --threads N         [4      ] number of threads to use during computation
  -p N,      --processors N      [1      ] number of processors to use during computation
  -ot N,     --offset-t N        [0      ] time offset in milliseconds
  -on N,     --offset-n N        [0      ] segment index offset
  -d  N,     --duration N        [0      ] duration of audio to process in milliseconds
  -mc N,     --max-context N     [-1     ] maximum number of text context tokens to store
  -ml N,     --max-len N         [0      ] maximum segment length in characters
  -sow,      --split-on-word     [false  ] split on word rather than on token
  -bo N,     --best-of N         [5      ] number of best candidates to keep
  -bs N,     --beam-size N       [5      ] beam size for beam search
  -wt N,     --word-thold N      [0.01   ] word timestamp probability threshold
  -et N,     --entropy-thold N   [2.40   ] entropy threshold for decoder fail
  -lpt N,    --logprob-thold N   [-1.00  ] log probability threshold for decoder fail
  -debug,    --debug-mode        [false  ] enable debug mode (eg. dump log_mel)
  -tr,       --translate         [false  ] translate from source language to english
  -di,       --diarize           [false  ] stereo audio diarization
  -tdrz,     --tinydiarize       [false  ] enable tinydiarize (requires a tdrz model)
  -nf,       --no-fallback       [false  ] do not use temperature fallback while decoding
  -otxt,     --output-txt        [false  ] output result in a text file
  -ovtt,     --output-vtt        [false  ] output result in a vtt file
  -osrt,     --output-srt        [false  ] output result in a srt file
  -olrc,     --output-lrc        [false  ] output result in a lrc file
  -owts,     --output-words      [false  ] output script for generating karaoke video
  -fp,       --font-path         [/System/Library/Fonts/Supplemental/Courier New Bold.ttf] path to a monospace font for karaoke video
  -ocsv,     --output-csv        [false  ] output result in a CSV file
  -oj,       --output-json       [false  ] output result in a JSON file
  -ojf,      --output-json-full  [false  ] include more information in the JSON file
  -of FNAME, --output-file FNAME [       ] output file path (without file extension)
  -np,       --no-prints         [false  ] do not print anything other than the results
  -ps,       --print-special     [false  ] print special tokens
  -pc,       --print-colors      [false  ] print colors
  -pp,       --print-progress    [false  ] print progress
  -nt,       --no-timestamps     [false  ] do not print timestamps
  -l LANG,   --language LANG     [en     ] spoken language ('auto' for auto-detect)
  -dl,       --detect-language   [false  ] exit after automatically detecting language
             --prompt PROMPT     [       ] initial prompt
  -m FNAME,  --model FNAME       [models/ggml-base.en.bin] model path
  -f FNAME,  --file FNAME        [       ] input WAV file path
  -oved D,   --ov-e-device DNAME [CPU    ] the OpenVINO device used for encode inference
  -ls,       --log-score         [false  ] log best decoder scores of tokens
  -ng,       --no-gpu            [false  ] disable GPU

g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include examples/bench/bench.cpp ggml-cuda.o ggml.o ggml-alloc.o ggml-backend.o ggml-quants.o whisper.o -o bench  -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib
g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include examples/quantize/quantize.cpp examples/common.cpp examples/common-ggml.cpp ggml-cuda.o ggml.o ggml-alloc.o ggml-backend.o ggml-quants.o whisper.o -o quantize  -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib
g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include examples/server/server.cpp examples/common.cpp examples/common-ggml.cpp ggml-cuda.o ggml.o ggml-alloc.o ggml-backend.o ggml-quants.o whisper.o -o server  -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ll

编译成功后，则可以执行测试程序，首先执行自带测试音频：【英文】
./main -f samples/jfk.wav
执行结果如下，我们可看到识别结果正确：

rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ./main -l zh -osrt -m models/g
generate-coreml-interface.sh  generate-coreml-model.sh      ggml-base.en.bin              ggml-large-v3.bin             ggml-medium.bin               ggml_to_pt.py                 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ./main -l zh -osrt -m models/ggml
ggml-base.en.bin   ggml-large-v3.bin  ggml-medium.bin    ggml_to_pt.py      
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ./main -l zh -osrt -m models/ggml-large-v3.bin chs.wav
whisper_init_from_file_with_params_no_state: loading model from 'models/ggml-large-v3.bin'
whisper_model_load: loading model
whisper_model_load: n_vocab       = 51866
whisper_model_load: n_audio_ctx   = 1500
whisper_model_load: n_audio_state = 1280
whisper_model_load: n_audio_head  = 20
whisper_model_load: n_audio_layer = 32
whisper_model_load: n_text_ctx    = 448
whisper_model_load: n_text_state  = 1280
whisper_model_load: n_text_head   = 20
whisper_model_load: n_text_layer  = 32
whisper_model_load: n_mels        = 128
whisper_model_load: ftype         = 1
whisper_model_load: qntvr         = 0
whisper_model_load: type          = 5 (large v3)
whisper_model_load: adding 1609 extra tokens
whisper_model_load: n_langs       = 100
ggml_init_cublas: GGML_CUDA_FORCE_MMQ:   no
ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
ggml_init_cublas: found 1 CUDA devices:
  Device 0: NVIDIA GeForce GTX 1080, compute capability 6.1, VMM: yes
whisper_backend_init: using CUDA backend
whisper_model_load:    CUDA0 total size =  3094.86 MB (3 buffers)
whisper_model_load: model size    = 3094.36 MB
whisper_backend_init: using CUDA backend
whisper_init_state: kv self size  =  220.20 MB
whisper_init_state: kv cross size =  245.76 MB
whisper_init_state: compute buffer (conv)   =   35.50 MB
whisper_init_state: compute buffer (encode) =  233.50 MB
whisper_init_state: compute buffer (cross)  =   10.15 MB
whisper_init_state: compute buffer (decode) =  108.99 MB

system_info: n_threads = 4 / 36 | AVX = 1 | AVX2 = 1 | AVX512 = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | METAL = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | CUDA = 1 | COREML = 0 | OPENVINO = 0 | 

main: processing 'chs.wav' (6748501 samples, 421.8 sec), 4 threads, 1 processors, 5 beams + best of 5, lang = zh, task = transcribe, timestamps = 1 ...

[00:00:00.040 --> 00:00:01.460]  前段时间有个巨石横火
[00:00:01.460 --> 00:00:02.860]  某某是男人最好的衣媒
[00:00:02.860 --> 00:00:04.800]  这里的某某可以替换为减肥
[00:00:04.800 --> 00:00:07.620]  长发 西装 考研 书唱 永结无间等等等等
[00:00:07.620 --> 00:00:09.320]  我听到最新的一个说法是
[00:00:09.320 --> 00:00:11.940]  微分碎盖加口罩加半框眼镜加冲锋衣
[00:00:11.940 --> 00:00:13.440]  等于男人最好的衣媒
[00:00:13.440 --> 00:00:14.420]  大概也就前几年
[00:00:14.420 --> 00:00:17.560]  冲锋衣还和格子衬衫并列为程序员穿搭精华
[00:00:17.560 --> 00:00:19.940]  紫红色冲锋衣还被誉为广场舞达妈标配
[00:00:19.940 --> 00:00:22.700]  骆驼牌还是我爹这个年纪的人才会愿意买的牌子
[00:00:22.700 --> 00:00:24.380]  不知道风向为啥变得这么快
[00:00:24.380 --> 00:00:26.680]  为啥这东西突然变成男生逆袭神器
[00:00:26.680 --> 00:00:27.660]  时尚潮流单品
[00:00:27.660 --> 00:00:29.580]  后来我翻了一下小红书就懂了
[00:00:29.580 --> 00:00:30.460]  时尚这个时期
[00:00:30.460 --> 00:00:31.620]  重点不在于衣服
[00:00:31.620 --> 00:00:32.160]  在于人
[00:00:32.160 --> 00:00:34.500]  现在小红书上面和冲锋衣相关的笔记
[00:00:34.500 --> 00:00:36.220]  照片里的男生都是这样的
[00:00:36.220 --> 00:00:36.880]  这样的
[00:00:36.880 --> 00:00:38.140]  还有这样的
[00:00:38.140 --> 00:00:39.460]  你们哪里是看穿搭的
[00:00:39.460 --> 00:00:40.540]  你们明明是看脸
[00:00:40.540 --> 00:00:41.780]  就这个造型这个年龄
[00:00:41.780 --> 00:00:43.920]  你换上老头衫也能穿出氛围感好吗
[00:00:43.920 --> 00:00:46.560]  我又想起了当年郭德纲老师穿计繁西的残剧
[00:00:46.560 --> 00:00:48.560]  这个世界对我们这些长得不好看的人
[00:00:48.560 --> 00:00:49.480]  还真是苛刻呢
[00:00:49.480 --> 00:00:52.100]  所以说我总结了一下冲锋衣传达的要领
[00:00:52.100 --> 00:00:54.200]  大概就是一张白净且人畜无汉的脸
[00:00:54.200 --> 00:00:55.120]  充足的发量
[00:00:55.120 --> 00:00:55.980]  纤细的体型
[00:00:55.980 --> 00:00:58.160]  当然身上的冲锋衣还得是骆驼的
[00:00:58.160 --> 00:00:59.320]  去年在户外用品界
[00:00:59.320 --> 00:01:01.100]  最顶流的既不是鸟像书
[00:01:01.100 --> 00:01:02.560]  也不是有校服之称的北面
[00:01:02.560 --> 00:01:04.120]  或者老台顶流哥伦比亚
[00:01:04.120 --> 00:01:04.800]  而是骆驼
[00:01:04.800 --> 00:01:06.980]  双十一骆驼在天猫户外服饰品类
[00:01:06.980 --> 00:01:08.860]  拿下销售额和销量双料冠军
[00:01:08.860 --> 00:01:09.980]  销量达到百万级
[00:01:09.980 --> 00:01:10.620]  在抖音
[00:01:10.620 --> 00:01:13.200]  骆驼销售同比增幅高达百分之296
[00:01:13.200 --> 00:01:15.920]  旗下主打的三合一高性价比冲锋衣成为爆品
[00:01:15.920 --> 00:01:17.260]  哪怕不看双十一
[00:01:17.260 --> 00:01:18.020]  随手一搜
[00:01:18.020 --> 00:01:21.040]  骆驼在冲锋衣的七日销售榜上都是图榜的存在
[00:01:21.040 --> 00:01:22.480]  这是线上的销售表现
[00:01:22.480 --> 00:01:24.200]  至于线下还是网友总结的好
[00:01:24.200 --> 00:01:26.740]  如今在南方街头的骆驼比沙漠里的都多
[00:01:26.740 --> 00:01:27.540]  爬个华山
[00:01:27.540 --> 00:01:28.320]  满山的骆驼
[00:01:28.320 --> 00:01:29.840]  随便逛个街撞山了
[00:01:29.840 --> 00:01:31.060]  至于骆驼为啥这么火
[00:01:31.060 --> 00:01:31.800]  便宜啊
[00:01:31.800 --> 00:01:33.400]  拿卖的最好的丁真同款
[00:01:33.400 --> 00:01:35.500]  幻影黑三合一冲锋衣举个例子
[00:01:35.500 --> 00:01:36.000]  线下买
[00:01:36.000 --> 00:01:37.440]  标牌价格2198
[00:01:37.440 --> 00:01:38.940]  但是跑到网上看一下
[00:01:38.940 --> 00:01:40.460]  标价就变成了699
[00:01:40.460 --> 00:01:41.220]  至于折扣
[00:01:41.220 --> 00:01:42.360]  日常也都是有的
[00:01:42.360 --> 00:01:43.440]  400出头就能买到
[00:01:43.440 --> 00:01:44.960]  甚至有时候能低到300价
[00:01:44.960 --> 00:01:46.140]  要是你还嫌贵
[00:01:46.140 --> 00:01:48.200]  路头还有200块出头的单层冲锋衣
[00:01:48.200 --> 00:01:49.080]  就这个价格
[00:01:49.080 --> 00:01:51.520]  搁上海恐怕还不够两次CityWalk的报名费
[00:01:51.520 --> 00:01:52.560]  看了这个价格
[00:01:52.560 --> 00:01:53.560]  再对比一下北面
[00:01:53.560 --> 00:01:54.640]  1000块钱起步
[00:01:54.640 --> 00:01:56.000]  你就能理解为啥北面
[00:01:56.000 --> 00:01:58.120]  这么快就被大学生踢出了校服序列了
[00:01:58.120 --> 00:02:00.380]  我不知道现在大学生每个月生活费多少
[00:02:00.380 --> 00:02:02.160]  反正按照我上学时候的生活费
[00:02:02.160 --> 00:02:03.200]  一个月不吃不喝
[00:02:03.200 --> 00:02:05.080]  也就买得起俩袖子加一个帽子
[00:02:05.080 --> 00:02:06.420]  难怪当年全是假北面
[00:02:06.420 --> 00:02:07.400]  现在都是真路头
[00:02:07.400 --> 00:02:08.640]  至少人家是正品啊
[00:02:08.640 --> 00:02:10.080]  我翻了一下社交媒体
[00:02:10.080 --> 00:02:12.060]  发现对路头的吐槽和买了路头的
[00:02:12.060 --> 00:02:13.340]  基本上是1比1的比例
[00:02:13.340 --> 00:02:15.040]  吐槽最多的就是衣服会掉色
[00:02:15.040 --> 00:02:15.960]  还会串色
[00:02:15.960 --> 00:02:17.100]  比如图增洗个几次
[00:02:17.100 --> 00:02:18.240]  穿个两天就掉光了
[00:02:18.240 --> 00:02:19.600]  比如不同仓库发的货
[00:02:19.600 --> 00:02:20.600]  质量参差不齐
[00:02:20.600 --> 00:02:22.300]  买衣服还得看户口拼出身
[00:02:22.300 --> 00:02:23.660]  至于什么做工比较差
[00:02:23.660 --> 00:02:24.300]  内胆多
[00:02:24.300 --> 00:02:24.880]  走线糙
[00:02:24.880 --> 00:02:26.380]  不防水之类的就更多了
[00:02:26.380 --> 00:02:27.360]  但是这些吐槽
[00:02:27.360 --> 00:02:29.160]  并不意味着会影响路头的销量
[00:02:29.160 --> 00:02:30.820]  甚至还会有不少自来水表示
[00:02:30.820 --> 00:02:32.680]  就这价格要啥自行车啊
[00:02:32.680 --> 00:02:34.080]  所谓性价比性价比
[00:02:34.080 --> 00:02:35.340]  脱离价位谈性能
[00:02:35.340 --> 00:02:36.980]  这就不符合消费者的需求嘛
[00:02:36.980 --> 00:02:38.480]  无数次价格战告诉我们
[00:02:38.480 --> 00:02:39.500]  只要肯降价
[00:02:39.500 --> 00:02:40.960]  就没有卖不出去的产品
[00:02:40.960 --> 00:02:41.820]  一件冲锋衣
[00:02:41.820 --> 00:02:43.500]  1000多你觉得平平无奇
[00:02:43.500 --> 00:02:44.900]  500多你觉得差点意思
[00:02:44.900 --> 00:02:46.480]  200块你就要秒下单了
[00:02:46.480 --> 00:02:48.520]  到99恐怕就要拼点手速了
[00:02:48.520 --> 00:02:49.560]  像冲锋衣这个品类
[00:02:49.560 --> 00:02:50.720]  本来价格跨度就大
[00:02:50.720 --> 00:02:52.660]  北面最便宜的Gortex冲锋衣
[00:02:52.660 --> 00:02:53.740]  价格3000起步
[00:02:53.740 --> 00:02:56.360]  大概是同品牌最便宜冲锋衣的三倍价格
[00:02:56.360 --> 00:02:57.060]  至于十足鸟
[00:02:57.060 --> 00:02:59.020]  搭载了Gortex的硬壳起步价
[00:02:59.020 --> 00:02:59.780]  就要到4500
[00:02:59.780 --> 00:03:01.080]  而且同样是Gortex
[00:03:01.080 --> 00:03:02.860]  内部也有不同的系列和档次
[00:03:02.860 --> 00:03:03.520]  做成衣服
[00:03:03.520 --> 00:03:05.780]  中间的差价恐怕就够买两件骆驼了
[00:03:05.780 --> 00:03:06.620]  至于智能控温
[00:03:06.620 --> 00:03:07.320]  防水拉链
[00:03:07.320 --> 00:03:07.900]  全压胶
[00:03:07.900 --> 00:03:09.760]  更加不可能出现在骆驼这里了
[00:03:09.760 --> 00:03:11.780]  至少不会是三四百的骆驼身上会有的
[00:03:11.780 --> 00:03:12.660]  有的价外的衣服
[00:03:12.660 --> 00:03:14.040]  买的就是一个放弃幻想
[00:03:14.040 --> 00:03:15.660]  吃到肚子里的科技鱼很活
[00:03:15.660 --> 00:03:16.840]  是能给你省钱的
[00:03:16.840 --> 00:03:18.320]  穿在身上的科技鱼很活
[00:03:18.320 --> 00:03:20.040]  装装件件都是要加钱的
[00:03:20.040 --> 00:03:21.440]  所以正如罗曼罗兰所说
[00:03:21.440 --> 00:03:23.040]  这世界上只有一种英雄主义
[00:03:23.040 --> 00:03:24.860]  就是在认清了骆驼的本质以后
[00:03:24.860 --> 00:03:26.060]  依然选择买骆驼
[00:03:26.060 --> 00:03:26.900]  关于骆驼的火爆
[00:03:26.900 --> 00:03:28.180]  我有一些小小的看法
[00:03:28.180 --> 00:03:28.960]  骆驼这个东西
[00:03:28.960 --> 00:03:30.220]  它其实就是个潮牌
[00:03:30.220 --> 00:03:31.940]  看看它的营销方式就知道了
[00:03:31.940 --> 00:03:32.920]  现在打开小红书
[00:03:32.920 --> 00:03:35.120]  日常可以看到骆驼穿搭是这样的
[00:03:35.120 --> 00:03:36.900]  加一点氛围感是这样的
[00:03:36.900 --> 00:03:37.400]  对比一下
[00:03:37.400 --> 00:03:39.240]  其他品牌的风格是这样的
[00:03:39.240 --> 00:03:40.020]  这样的
[00:03:40.020 --> 00:03:41.280]  其实对比一下就知道了
[00:03:41.280 --> 00:03:42.600]  其他品牌突出一个时程
[00:03:42.600 --> 00:03:44.240]  能防风就一定要讲防风
[00:03:44.240 --> 00:03:45.960]  能扛冻就一定要讲扛冻
[00:03:45.960 --> 00:03:47.340]  但骆驼在营销的时候
[00:03:47.340 --> 00:03:49.080]  主打的就是一个城市户外风
[00:03:49.080 --> 00:03:50.440]  虽然造型是春风衣
[00:03:50.440 --> 00:03:52.180]  但场景往往是在城市里
[00:03:52.180 --> 00:03:54.220]  哪怕在野外也要突出一个风和日丽
[00:03:54.220 --> 00:03:54.940]  阳光敏媚
[00:03:54.940 --> 00:03:56.500]  至少不会在明显的严寒
[00:03:56.500 --> 00:03:58.020]  高海拔或是恶劣气候下
[00:03:58.020 --> 00:04:00.160]  如果用一个词形容骆驼的营销风格
[00:04:00.160 --> 00:04:00.920]  那就是清洗
[00:04:00.920 --> 00:04:03.060]  或者说他很理解自己的消费者是谁
[00:04:03.060 --> 00:04:03.920]  需要什么产品
[00:04:03.920 --> 00:04:05.260]  从使用场景来说
[00:04:05.260 --> 00:04:06.600]  骆驼的消费者买春风衣
[00:04:06.600 --> 00:04:08.640]  不是真的有什么大风大雨要去应对
[00:04:08.640 --> 00:04:10.880]  春风衣的作用是下雨没带伞的时候
[00:04:10.880 --> 00:04:12.160]  临时顶个几分钟
[00:04:12.160 --> 00:04:13.700]  让你能图书馆跑回宿舍
[00:04:13.700 --> 00:04:14.940]  或者是冬天骑电动车
[00:04:14.940 --> 00:04:16.220]  被风吹得不行的时候
[00:04:16.220 --> 00:04:17.200]  稍微扛一下风
[00:04:17.200 --> 00:04:18.340]  不至于体感太冷
[00:04:18.340 --> 00:04:19.700]  当然他们也会出门
[00:04:19.700 --> 00:04:21.780]  但大部分时候也都是去别的城市
[00:04:21.780 --> 00:04:23.860]  或者在城市周边搞搞简单的徒步
[00:04:23.860 --> 00:04:24.920]  这种情况下
[00:04:24.920 --> 00:04:25.920]  穿个骆驼也就够了
[00:04:25.920 --> 00:04:27.220]  从购买动机来说
[00:04:27.220 --> 00:04:29.260]  骆驼就更没有必要上那些硬核科技了
[00:04:29.260 --> 00:04:30.920]  消费者买骆驼买的是个什么呢
[00:04:30.920 --> 00:04:32.240]  不是春风衣的功能性
[00:04:32.240 --> 00:04:33.380]  而是春风衣的造型
[00:04:33.380 --> 00:04:34.340]  宽松的版型
[00:04:34.340 --> 00:04:36.380]  能精准遮住微微隆起的小肚子
[00:04:36.380 --> 00:04:37.440]  棱角分明的质感
[00:04:37.440 --> 00:04:39.420]  能隐藏一切不完美的整体线条
[00:04:39.420 --> 00:04:41.260]  显瘦的副作用就是显年轻
[00:04:41.260 --> 00:04:42.600]  再配上一条牛仔裤
[00:04:42.600 --> 00:04:43.680]  配上一双大黄靴
[00:04:43.680 --> 00:04:45.100]  大学生的气质就出来了
[00:04:45.100 --> 00:04:47.700]  要是自拍的时候再配上大学宿舍洗漱台
[00:04:47.700 --> 00:04:49.380]  那永远擦不干净的镜子
[00:04:49.380 --> 00:04:50.840]  瞬间青春无敌了
[00:04:50.840 --> 00:04:51.700]  说的更直白一点
[00:04:51.700 --> 00:04:53.060]  人家买的是个锦铃神器
[00:04:53.060 --> 00:04:53.820]  所以说
[00:04:53.820 --> 00:04:55.860]  吐槽穿骆驼都是假户外爱好者的人
[00:04:55.860 --> 00:04:57.460]  其实并没有理解骆驼的定位
[00:04:57.460 --> 00:04:59.780]  骆驼其实是给了想要入门山系穿搭
[00:04:59.780 --> 00:05:01.740]  想要追逐流行的人一个最平价
[00:05:01.740 --> 00:05:02.980]  决策成本最低的选择
[00:05:02.980 --> 00:05:04.880]  至于那些真正的硬核户外爱好者
[00:05:04.880 --> 00:05:05.800]  骆驼既没有能力
[00:05:05.800 --> 00:05:07.080]  也没有打算触打他们
[00:05:07.080 --> 00:05:07.980]  反过来说
[00:05:07.980 --> 00:05:09.460]  那些自驾穿越边疆国道
[00:05:09.460 --> 00:05:11.680]  或者去阿尔卑斯山区登山探险的人
[00:05:11.680 --> 00:05:13.540]  也不太可能在户外服饰上省钱
[00:05:13.540 --> 00:05:14.900]  毕竟光是交通住宿
[00:05:14.900 --> 00:05:15.600]  请假出行
[00:05:15.600 --> 00:05:16.560]  成本就不低了
[00:05:16.560 --> 00:05:17.320]  对他们来说
[00:05:17.320 --> 00:05:19.140]  户外装备很多时候是保命用的
[00:05:19.140 --> 00:05:21.180]  也就不存在跟风凹造型的必要了
[00:05:21.180 --> 00:05:22.300]  最后我再说个题外话
[00:05:22.300 --> 00:05:23.320]  年轻人追捧骆驼
[00:05:23.320 --> 00:05:24.240]  一个隐藏的原因
[00:05:24.240 --> 00:05:25.940]  其实是羽绒服越来越贵了
[00:05:25.940 --> 00:05:26.620]  有媒体统计
[00:05:26.620 --> 00:05:28.440]  现在国产羽绒服的平均售价
[00:05:28.440 --> 00:05:29.880]  已经高达881元
[00:05:29.880 --> 00:05:31.140]  波斯灯均价最高
[00:05:31.140 --> 00:05:31.900]  接近2000元
[00:05:31.900 --> 00:05:32.880]  而且过去几年
[00:05:32.880 --> 00:05:34.800]  国产羽绒服品牌都在转向高端化
[00:05:34.800 --> 00:05:37.060]  羽绒服市场分为8000元以上的奢侈级
[00:05:37.060 --> 00:05:38.440]  2000元以下的大众级
[00:05:38.440 --> 00:05:39.740]  而在中间的高端级
[00:05:39.740 --> 00:05:41.220]  国产品牌一直没有存在感
[00:05:41.220 --> 00:05:42.140]  所以过去几年
[00:05:42.140 --> 00:05:43.520]  波斯灯天空人这些品牌
[00:05:43.520 --> 00:05:45.260]  都把2000元到8000元这个市场
[00:05:45.260 --> 00:05:46.560]  当成未来的发展趋势
[00:05:46.560 --> 00:05:47.980]  东芯证券研报显示
[00:05:47.980 --> 00:05:49.600]  从2018到2021年
[00:05:49.600 --> 00:05:52.080]  波斯灯均价4年涨幅达到60%以上
[00:05:52.080 --> 00:05:53.080]  过去5个财年
[00:05:53.080 --> 00:05:54.300]  这个品牌的营销开支
[00:05:54.300 --> 00:05:56.020]  从20多亿涨到了60多亿
[00:05:56.020 --> 00:05:57.240]  羽绒服价格往上走
[00:05:57.240 --> 00:05:59.160]  年轻消费者就开始抛弃羽绒服
[00:05:59.160 --> 00:06:00.300]  购买平价春风衣
[00:06:00.300 --> 00:06:02.240]  里面再穿个普通价位的摇篱绒
[00:06:02.240 --> 00:06:03.280]  或者羽绒小夹克
[00:06:03.280 --> 00:06:05.100]  也不比大几千的羽绒服差多少
[00:06:05.100 --> 00:06:05.740]  说到底
[00:06:05.740 --> 00:06:07.120]  现在消费社会发达了
[00:06:07.120 --> 00:06:08.300]  没有什么需求是一定要
[00:06:08.300 --> 00:06:09.740]  某种特定的解决方案
[00:06:09.740 --> 00:06:11.500]  特定价位的商品才能实现的
[00:06:11.500 --> 00:06:12.080]  要保暖
[00:06:12.080 --> 00:06:13.140]  羽绒服固然很好
[00:06:13.140 --> 00:06:15.320]  但春风衣加一些内搭也很暖和
[00:06:15.320 --> 00:06:15.820]  要时尚
[00:06:15.820 --> 00:06:17.860]  大几千块钱的设计师品牌非常不错
[00:06:17.860 --> 00:06:19.360]  但350的拼多多服饰
[00:06:19.360 --> 00:06:20.520]  搭得好也能出产
[00:06:20.520 --> 00:06:21.620]  要去野外徒步
[00:06:21.620 --> 00:06:22.940]  花五六千买鸟也可以
[00:06:22.940 --> 00:06:25.100]  但迪卡侬也足以应付大多数状况
[00:06:25.100 --> 00:06:25.720]  所以说
[00:06:25.720 --> 00:06:27.420]  花高价买春风衣当然也OK
[00:06:27.420 --> 00:06:28.540]  三四百买件骆驼
[00:06:28.540 --> 00:06:29.880]  也是可以介绍的选择
[00:06:29.880 --> 00:06:31.900]  何况骆驼也多多少少有一些功能性
[00:06:31.900 --> 00:06:32.840]  毕竟它再怎么样
[00:06:32.840 --> 00:06:33.920]  还是个春风衣
[00:06:33.920 --> 00:06:34.800]  理解了这个事情
[00:06:34.800 --> 00:06:35.740]  就很容易分辨
[00:06:35.740 --> 00:06:36.900]  什么是智商税的
[00:06:36.900 --> 00:06:38.740]  那些向你灌输非某个品牌不用
[00:06:38.740 --> 00:06:39.880]  告诉你某个需求
[00:06:39.880 --> 00:06:41.380]  只有某个产品才能满足
[00:06:41.380 --> 00:06:42.160]  某个品牌
[00:06:42.160 --> 00:06:44.220]  就是某个品类绝对的鄙视链顶端
[00:06:44.220 --> 00:06:45.900]  这类营销的智商税含量
[00:06:45.900 --> 00:06:46.860]  必然是很高的
[00:06:46.860 --> 00:06:48.780]  它的目的是剥夺你选择的权利
[00:06:48.780 --> 00:06:51.220]  让你主动放弃比价和寻找平梯的想法
[00:06:51.220 --> 00:06:52.920]  从而避免与其他品牌竞争
[00:06:52.920 --> 00:06:54.280]  而没有竞争的市场
[00:06:54.280 --> 00:06:56.020]  才是智商税含量最高的市场
[00:06:56.020 --> 00:06:57.360]  消费商业洞见
[00:06:57.360 --> 00:06:58.420]  近在IC实验室
[00:06:58.420 --> 00:06:59.000]  我是馆长
[00:06:59.000 --> 00:06:59.840]  我们下期再见
[00:06:59.840 --> 00:07:01.840]  谢谢大家!

output_srt: saving output to 'chs.wav.srt'

whisper_print_timings:     load time =  1232.24 ms
whisper_print_timings:     fallbacks =   1 p /   0 h
whisper_print_timings:      mel time =   507.42 ms
whisper_print_timings:   sample time = 14211.34 ms / 19337 runs (    0.73 ms per run)
whisper_print_timings:   encode time =  9234.67 ms /    19 runs (  486.04 ms per run)
whisper_print_timings:   decode time =    41.85 ms /     2 runs (   20.92 ms per run)
whisper_print_timings:   batchd time = 325320.62 ms / 19329 runs (   16.83 ms per run)
whisper_print_timings:   prompt time =  5857.69 ms /  3869 runs (    1.51 ms per run)
whisper_print_timings:    total time = 356447.78 ms
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ./main -l zh -osrt -m models/ggml-large-v3.bin chs.wav

参考资料：
https://blog.csdn.net/qq_43907505/article/details/135048613?spm=1001.2101.3001.6650.4&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7EYuanLiJiHua%7EPosition-4-135048613-blog-127843094.235%5Ev43%5Epc_blog_bottom_relevance_base1&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7EYuanLiJiHua%7EPosition-4-135048613-blog-127843094.235%5Ev43%5Epc_blog_bottom_relevance_base1&utm_relevant_index=9
https://blog.csdn.net/qq_43907505/article/details/135048613
开源语音识别faster-whisper部署教程

日语源视频：【通过hotbox获取】
https://www.bilibili.com/video/BV1fG4y1b74e/?vd_source=4a6b675fa22dfa306da59f67b1f22616
「原神」神里绫华日语配音，谁能拒绝一只蝴蝶忍呢？

中文源视频：【通过猫抓获取】
https://www.ixigua.com/7320445308314485283
2024-01-05 11:06国产冲锋衣杀疯了！百元骆驼如何营销卖爆？-IC实验室

rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ffmpeg
ffmpeg version 4.2.7-0ubuntu0.1 Copyright (c) 2000-2022 the FFmpeg developers
usage: ffmpeg [options] [[infile options] -i infile]... {[outfile options] outfile}...
Use -h to get full help or, even better, run 'man ffmpeg'
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ffmpeg -i chi.mp4 -ar 16000 -ac 1 -c:a pcm_s16le chi.wav
ffmpeg version 4.2.7-0ubuntu0.1 Copyright (c) 2000-2022 the FFmpeg developers
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ffmpeg -i chs.mp4 -ar 16000 -ac 1 -c:a pcm_s16le chs.wav

LOG如下：

rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ make clean
I whisper.cpp build info: 
I UNAME_S:  Linux
I UNAME_P:  x86_64
I UNAME_M:  x86_64
I CFLAGS:   -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3
I LDFLAGS:  
I CC:       cc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
I CXX:      g++ (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0

rm -f *.o main stream command talk talk-llama bench quantize server lsp libwhisper.a libwhisper.so
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ll
total 19196
drwxrwxr-x 17 rootroot rootroot     4096 2月   2 17:46 ./
drwxr-xr-x 30 rootroot rootroot     4096 2月   2 16:49 ../
drwxrwxr-x  7 rootroot rootroot     4096 2月   2 16:49 bindings/
-rwx------  1 rootroot rootroot  3465644 1月  12 01:28 chs.mp4*
-rw-rw-r--  1 rootroot rootroot 13497126 2月   2 17:26 chs.wav
-rw-rw-r--  1 rootroot rootroot    11821 2月   2 17:41 chs.wav使用CPU.srt
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 cmake/
-rw-rw-r--  1 rootroot rootroot    19150 2月   2 16:49 CMakeLists.txt
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 coreml/
drwx------  2 rootroot rootroot     4096 2月   2 17:45 CPU/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 .devops/
drwxrwxr-x 24 rootroot rootroot     4096 2月   2 16:49 examples/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 extra/
-rw-rw-r--  1 rootroot rootroot    31647 2月   2 16:49 ggml-alloc.c
-rw-rw-r--  1 rootroot rootroot     4055 2月   2 16:49 ggml-alloc.h
-rw-rw-r--  1 rootroot rootroot    67212 2月   2 16:49 ggml-backend.c
-rw-rw-r--  1 rootroot rootroot    11720 2月   2 16:49 ggml-backend.h
-rw-rw-r--  1 rootroot rootroot     5874 2月   2 16:49 ggml-backend-impl.h
-rw-rw-r--  1 rootroot rootroot   676115 2月   2 16:49 ggml.c
-rw-rw-r--  1 rootroot rootroot   440093 2月   2 16:49 ggml-cuda.cu
-rw-rw-r--  1 rootroot rootroot     2104 2月   2 16:49 ggml-cuda.h
-rw-rw-r--  1 rootroot rootroot    85094 2月   2 16:49 ggml.h
-rw-rw-r--  1 rootroot rootroot     7567 2月   2 16:49 ggml-impl.h
-rw-rw-r--  1 rootroot rootroot     2358 2月   2 16:49 ggml-metal.h
-rw-rw-r--  1 rootroot rootroot   150160 2月   2 16:49 ggml-metal.m
-rw-rw-r--  1 rootroot rootroot   225659 2月   2 16:49 ggml-metal.metal
-rw-rw-r--  1 rootroot rootroot    85693 2月   2 16:49 ggml-opencl.cpp
-rw-rw-r--  1 rootroot rootroot     1386 2月   2 16:49 ggml-opencl.h
-rw-rw-r--  1 rootroot rootroot   401791 2月   2 16:49 ggml-quants.c
-rw-rw-r--  1 rootroot rootroot    13705 2月   2 16:49 ggml-quants.h
drwxrwxr-x  8 rootroot rootroot     4096 2月   2 16:49 .git/
drwxrwxr-x  3 rootroot rootroot     4096 2月   2 16:49 .github/
-rw-rw-r--  1 rootroot rootroot      803 2月   2 16:49 .gitignore
-rw-rw-r--  1 rootroot rootroot       96 2月   2 16:49 .gitmodules
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 grammars/
-rw-rw-r--  1 rootroot rootroot     1072 2月   2 16:49 LICENSE
-rw-rw-r--  1 rootroot rootroot    14883 2月   2 16:49 Makefile
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 17:24 models/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 openvino/
-rw-rw-r--  1 rootroot rootroot     1776 2月   2 16:49 Package.swift
-rw-rw-r--  1 rootroot rootroot    39115 2月   2 16:49 README.md
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 samples/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 spm-headers/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 tests/
-rw-rw-r--  1 rootroot rootroot   232975 2月   2 16:49 whisper.cpp
-rw-rw-r--  1 rootroot rootroot    30248 2月   2 16:49 whisper.h
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ll main
ls: cannot access 'main': No such file or directory
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ WHISPER_CLBLAST=1 make -j16
I whisper.cpp build info: 
I UNAME_S:  Linux
I UNAME_P:  x86_64
I UNAME_M:  x86_64
I CFLAGS:   -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CLBLAST
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CLBLAST
I LDFLAGS:   -lclblast -lOpenCL
I CC:       cc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
I CXX:      g++ (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0

g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CLBLAST -c ggml-opencl.cpp -o ggml-opencl.o
cc  -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CLBLAST   -c ggml.c -o ggml.o
cc  -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CLBLAST   -c ggml-alloc.c -o ggml-alloc.o
cc  -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CLBLAST   -c ggml-backend.c -o ggml-backend.o
cc  -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CLBLAST   -c ggml-quants.c -o ggml-quants.o
g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CLBLAST -c whisper.cpp -o whisper.o
ggml-opencl.cpp:15:10: fatal error: clblast.h: No such file or directory
   15 | #include
      |          ^~~~~~~~~~~
compilation terminated.
make: *** [Makefile:255: ggml-opencl.o] Error 1
make: *** Waiting for unfinished jobs....

rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ sidp aptg-et install openblas

Command 'sidp' not found, did you mean:

  command 'ssdp' from snap ssdp (0.0.1)
  command 'sipp' from deb sip-tester (1:3.6.0-1build1)
  command 'sip' from deb sip-dev (4.19.21+dfsg-1build1)
  command 'sfdp' from deb graphviz (2.42.2-3build2)

See 'snap info ' for additional versions.

rootroot@rootroot-X99-Turbo:~/whisper.cpp$ sidp apt-get install openblas

Command 'sidp' not found, did you mean:

  command 'ssdp' from snap ssdp (0.0.1)
  command 'sfdp' from deb graphviz (2.42.2-3build2)
  command 'sip' from deb sip-dev (4.19.21+dfsg-1build1)
  command 'sipp' from deb sip-tester (1:3.6.0-1build1)

See 'snap info ' for additional versions.

rootroot@rootroot-X99-Turbo:~/whisper.cpp$ sudo apt-get install openblas
[sudo] password for rootroot: 
Reading package lists... Done
Building dependency tree       
Reading state information... Done
E: Unable to locate package openblas
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ sudo apt install openblas
Reading package lists... Done
Building dependency tree       
Reading state information... Done
E: Unable to locate package openblas
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ sudo apt-get install libopenblas-dev
Reading package lists... Done
Building dependency tree       
Reading state information... Done
The following additional packages will be installed:
  libopenblas-pthread-dev libopenblas0 libopenblas0-pthread
The following NEW packages will be installed:
  libopenblas-dev libopenblas-pthread-dev libopenblas0 libopenblas0-pthread
0 upgraded, 4 newly installed, 0 to remove and 11 not upgraded.
Need to get 13.7 MB of archives.
After this operation, 153 MB of additional disk space will be used.
Do you want to continue? [Y/n] y
Get:1 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal-updates/universe amd64 libopenblas0-pthread amd64 0.3.8+ds-1ubuntu0.20.04.1 [9,127 kB]
Get:2 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal-updates/universe amd64 libopenblas0 amd64 0.3.8+ds-1ubuntu0.20.04.1 [5,892 B]
Get:3 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal-updates/universe amd64 libopenblas-pthread-dev amd64 0.3.8+ds-1ubuntu0.20.04.1 [4,526 kB]
Get:4 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal-updates/universe amd64 libopenblas-dev amd64 0.3.8+ds-1ubuntu0.20.04.1 [16.4 kB]
Fetched 13.7 MB in 2s (8,470 kB/s)         
Selecting previously unselected package libopenblas0-pthread:amd64.
(Reading database ... 207405 files and directories currently installed.)
Preparing to unpack .../libopenblas0-pthread_0.3.8+ds-1ubuntu0.20.04.1_amd64.deb ...
Unpacking libopenblas0-pthread:amd64 (0.3.8+ds-1ubuntu0.20.04.1) ...
Selecting previously unselected package libopenblas0:amd64.
Preparing to unpack .../libopenblas0_0.3.8+ds-1ubuntu0.20.04.1_amd64.deb ...
Unpacking libopenblas0:amd64 (0.3.8+ds-1ubuntu0.20.04.1) ...
Selecting previously unselected package libopenblas-pthread-dev:amd64.
Preparing to unpack .../libopenblas-pthread-dev_0.3.8+ds-1ubuntu0.20.04.1_amd64.deb ...
Unpacking libopenblas-pthread-dev:amd64 (0.3.8+ds-1ubuntu0.20.04.1) ...
Selecting previously unselected package libopenblas-dev:amd64.
Preparing to unpack .../libopenblas-dev_0.3.8+ds-1ubuntu0.20.04.1_amd64.deb ...
Unpacking libopenblas-dev:amd64 (0.3.8+ds-1ubuntu0.20.04.1) ...
Setting up libopenblas0-pthread:amd64 (0.3.8+ds-1ubuntu0.20.04.1) ...
update-alternatives: using /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3 to provide /usr/lib/x86_64-linux-gnu/libblas.so.3 (libblas.so.3-x86_64-linux-gnu) in auto mode
update-alternatives: using /usr/lib/x86_64-linux-gnu/openblas-pthread/liblapack.so.3 to provide /usr/lib/x86_64-linux-gnu/liblapack.so.3 (liblapack.so.3-x86_64-linux-gnu) in auto mode
update-alternatives: using /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblas.so.0 to provide /usr/lib/x86_64-linux-gnu/libopenblas.so.0 (libopenblas.so.0-x86_64-linux-gnu) in auto mode
Setting up libopenblas0:amd64 (0.3.8+ds-1ubuntu0.20.04.1) ...
Setting up libopenblas-pthread-dev:amd64 (0.3.8+ds-1ubuntu0.20.04.1) ...
update-alternatives: using /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so to provide /usr/lib/x86_64-linux-gnu/libblas.so (libblas.so-x86_64-linux-gnu) in auto mode
update-alternatives: using /usr/lib/x86_64-linux-gnu/openblas-pthread/liblapack.so to provide /usr/lib/x86_64-linux-gnu/liblapack.so (liblapack.so-x86_64-linux-gnu) in auto mode
update-alternatives: using /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblas.so to provide /usr/lib/x86_64-linux-gnu/libopenblas.so (libopenblas.so-x86_64-linux-gnu) in auto mode
Setting up libopenblas-dev:amd64 (0.3.8+ds-1ubuntu0.20.04.1) ...
Processing triggers for libc-bin (2.31-0ubuntu9.14) ...
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ WHISPER_CUBLAS=1 make -j16
expr: syntax error: unexpected argument ‘11.6’
I whisper.cpp build info: 
I UNAME_S:  Linux
I UNAME_P:  x86_64
I UNAME_M:  x86_64
I CFLAGS:   -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include
I LDFLAGS:   -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib
I CC:       cc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
I CXX:      g++ (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0

nvcc --forward-unknown-to-host-compiler -arch=all -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -Wno-pedantic -c ggml-cuda.cu -o ggml-cuda.o
make: nvcc: Command not found
make: *** [Makefile:225: ggml-cuda.o] Error 127
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ nvcc -v

Command 'nvcc' not found, but can be installed with:

sudo apt install nvidia-cuda-toolkit

rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ sudo apt install nvidia-cuda-toolkit
Reading package lists... Done
Building dependency tree       
Reading state information... Done
The following additional packages will be installed:
  g++-8 javascript-common libaccinj64-10.1 libcublas10 libcublaslt10 libcudart10.1 libcufft10 libcufftw10 libcuinj64-10.1 libcupti-dev libcupti-doc libcupti10.1 libcurand10 libcusolver10 libcusolvermg10 libcusparse10 libjs-jquery libnppc10 libnppial10 libnppicc10
  libnppicom10 libnppidei10 libnppif10 libnppig10 libnppim10 libnppist10 libnppisu10 libnppitc10 libnpps10 libnvblas10 libnvgraph10 libnvidia-compute-545 libnvidia-ml-dev libnvjpeg10 libnvrtc10.1 libnvtoolsext1 libnvvm3 libstdc++-8-dev libthrust-dev libvdpau-dev
  node-html5shiv nvidia-cuda-dev nvidia-cuda-doc nvidia-cuda-gdb nvidia-opencl-dev nvidia-profiler nvidia-visual-profiler ocl-icd-opencl-dev opencl-c-headers
Suggested packages:
  g++-8-multilib gcc-8-doc apache2 | lighttpd | httpd libstdc++-8-doc libvdpau-doc nodejs nvidia-driver | nvidia-tesla-440-driver | nvidia-tesla-418-driver libpoclu-dev
Recommended packages:
  libnvcuvid1 nsight-compute nsight-systems
The following NEW packages will be installed:
  g++-8 javascript-common libaccinj64-10.1 libcublas10 libcublaslt10 libcudart10.1 libcufft10 libcufftw10 libcuinj64-10.1 libcupti-dev libcupti-doc libcupti10.1 libcurand10 libcusolver10 libcusolvermg10 libcusparse10 libjs-jquery libnppc10 libnppial10 libnppicc10
  libnppicom10 libnppidei10 libnppif10 libnppig10 libnppim10 libnppist10 libnppisu10 libnppitc10 libnpps10 libnvblas10 libnvgraph10 libnvidia-compute-545 libnvidia-ml-dev libnvjpeg10 libnvrtc10.1 libnvtoolsext1 libnvvm3 libstdc++-8-dev libthrust-dev libvdpau-dev
  node-html5shiv nvidia-cuda-dev nvidia-cuda-doc nvidia-cuda-gdb nvidia-cuda-toolkit nvidia-opencl-dev nvidia-profiler nvidia-visual-profiler ocl-icd-opencl-dev opencl-c-headers
0 upgraded, 50 newly installed, 0 to remove and 11 not upgraded.
Need to get 1,111 MB/1,160 MB of archives.
After this operation, 3,056 MB of additional disk space will be used.
Do you want to continue? [Y/n] y
Get:1 file:/var/cuda-repo-ubuntu2004-12-3-local  libnvidia-compute-545 545.23.08-0ubuntu1 [48.8 MB]
Err:1 file:/var/cuda-repo-ubuntu2004-12-3-local  libnvidia-compute-545 545.23.08-0ubuntu1
  File not found - /var/cuda-repo-ubuntu2004-12-3-local/./libnvidia-compute-545_545.23.08-0ubuntu1_amd64.deb (2: No such file or directory)
Get:2 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/universe amd64 libstdc++-8-dev amd64 8.4.0-3ubuntu2 [1,537 kB]
Get:3 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/universe amd64 g++-8 amd64 8.4.0-3ubuntu2 [10.1 MB]
Get:4 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/main amd64 javascript-common all 11 [6,066 B]
Get:5 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libaccinj64-10.1 amd64 10.1.243-3 [1,893 kB]
Get:6 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libcublaslt10 amd64 10.1.243-3 [9,249 kB]
Get:7 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libcublas10 amd64 10.1.243-3 [29.7 MB]
Get:8 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libcudart10.1 amd64 10.1.243-3 [125 kB]
Get:9 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libcufft10 amd64 10.1.243-3 [85.3 MB]
Get:10 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libcufftw10 amd64 10.1.243-3 [124 kB]
Get:11 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libcuinj64-10.1 amd64 10.1.243-3 [2,030 kB]
Get:12 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libcupti10.1 amd64 10.1.243-3 [4,311 kB]
Get:13 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libcurand10 amd64 10.1.243-3 [39.0 MB]
Get:14 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libcusolver10 amd64 10.1.243-3 [44.5 MB]
Get:15 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libcusolvermg10 amd64 10.1.243-3 [28.1 MB]                                                                                                                                                           
Get:16 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libcusparse10 amd64 10.1.243-3 [56.8 MB]                                                                                                                                                             
Get:17 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/main amd64 libjs-jquery all 3.3.1~dfsg-3 [329 kB]                                                                                                                                                                     
Get:18 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnppc10 amd64 10.1.243-3 [123 kB]                                                                                                                                                                  
Get:19 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnppial10 amd64 10.1.243-3 [3,667 kB]                                                                                                                                                              
Get:20 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnppicc10 amd64 10.1.243-3 [1,621 kB]                                                                                                                                                              
Get:21 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnppicom10 amd64 10.1.243-3 [539 kB]                                                                                                                                                               
Get:22 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnppidei10 amd64 10.1.243-3 [2,001 kB]                                                                                                                                                             
Get:23 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnppif10 amd64 10.1.243-3 [22.0 MB]                                                                                                                                                                
Get:24 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnppig10 amd64 10.1.243-3 [12.0 MB]                                                                                                                                                                
Get:25 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnppim10 amd64 10.1.243-3 [2,694 kB]                                                                                                                                                               
Get:26 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnppist10 amd64 10.1.243-3 [7,313 kB]                                                                                                                                                              
Get:27 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnppisu10 amd64 10.1.243-3 [116 kB]                                                                                                                                                                
Get:28 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnppitc10 amd64 10.1.243-3 [802 kB]                                                                                                                                                                
Get:29 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnpps10 amd64 10.1.243-3 [2,970 kB]                                                                                                                                                                
Get:30 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnvblas10 amd64 10.1.243-3 [129 kB]                                                                                                                                                                
Get:31 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnvgraph10 amd64 10.1.243-3 [44.5 MB]                                                                                                                                                              
Get:32 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnvidia-ml-dev amd64 10.1.243-3 [58.1 kB]                                                                                                                                                          
Get:33 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnvjpeg10 amd64 10.1.243-3 [1,227 kB]                                                                                                                                                              
Get:34 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnvrtc10.1 amd64 10.1.243-3 [6,307 kB]                                                                                                                                                             
Get:35 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/main amd64 libvdpau-dev amd64 1.3-1ubuntu2 [37.3 kB]                                                                                                                                                                  
Get:36 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/universe amd64 node-html5shiv all 3.7.3+dfsg-3 [12.9 kB]                                                                                                                                                              
Get:37 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libcupti-dev amd64 10.1.243-3 [4,779 kB]                                                                                                                                                             
Get:38 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libcupti-doc all 10.1.243-3 [2,117 kB]                                                                                                                                                               
Get:39 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnvtoolsext1 amd64 10.1.243-3 [25.1 kB]                                                                                                                                                            
Get:40 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libnvvm3 amd64 10.1.243-3 [4,436 kB]                                                                                                                                                                 
Get:41 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 libthrust-dev all 1.9.5-1 [526 kB]                                                                                                                                                                   
Get:42 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 nvidia-cuda-dev amd64 10.1.243-3 [420 MB]                                                                                                                                                            
Get:43 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 nvidia-cuda-doc all 10.1.243-3 [102 MB]                                                                                                                                                              
Get:44 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 nvidia-cuda-gdb amd64 10.1.243-3 [2,722 kB]                                                                                                                                                          
Get:45 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 nvidia-profiler amd64 10.1.243-3 [2,673 kB]                                                                                                                                                          
Get:46 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/main amd64 opencl-c-headers all 2.2~2019.08.06-g0d5f18c-1 [29.9 kB]                                                                                                                                                   
Get:47 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/main amd64 ocl-icd-opencl-dev amd64 2.2.11-1ubuntu1 [2,512 B]                                                                                                                                                         
Get:48 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 nvidia-opencl-dev amd64 10.1.243-3 [16.5 kB]                                                                                                                                                         
Get:49 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 nvidia-cuda-toolkit amd64 10.1.243-3 [35.0 MB]                                                                                                                                                       
Get:50 http://mirrors.tuna.tsinghua.edu.cn/ubuntu focal/multiverse amd64 nvidia-visual-profiler amd64 10.1.243-3 [115 MB]                                                                                                                                                     
Fetched 1,111 MB in 29s (38.0 MB/s)                                                                                                                                                                                                                                           
E: Failed to fetch file:/var/cuda-repo-ubuntu2004-12-3-local/./libnvidia-compute-545_545.23.08-0ubuntu1_amd64.deb  File not found - /var/cuda-repo-ubuntu2004-12-3-local/./libnvidia-compute-545_545.23.08-0ubuntu1_amd64.deb (2: No such file or directory)
E: Unable to fetch some archives, maybe run apt-get update or try with --fix-missing?
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ sudo apt install nvidia-cuda-toolkit
Reading package lists... Done
Building dependency tree       
Reading state information... Done
The following additional packages will be installed:
  g++-8 javascript-common libaccinj64-10.1 libcublas10 libcublaslt10 libcudart10.1 libcufft10 libcufftw10 libcuinj64-10.1 libcupti-dev libcupti-doc libcupti10.1 libcurand10 libcusolver10 libcusolvermg10 libcusparse10 libjs-jquery libnppc10 libnppial10 libnppicc10
  libnppicom10 libnppidei10 libnppif10 libnppig10 libnppim10 libnppist10 libnppisu10 libnppitc10 libnpps10 libnvblas10 libnvgraph10 libnvidia-compute-545 libnvidia-ml-dev libnvjpeg10 libnvrtc10.1 libnvtoolsext1 libnvvm3 libstdc++-8-dev libthrust-dev libvdpau-dev
  node-html5shiv nvidia-cuda-dev nvidia-cuda-doc nvidia-cuda-gdb nvidia-opencl-dev nvidia-profiler nvidia-visual-profiler ocl-icd-opencl-dev opencl-c-headers
Suggested packages:
  g++-8-multilib gcc-8-doc apache2 | lighttpd | httpd libstdc++-8-doc libvdpau-doc nodejs nvidia-driver | nvidia-tesla-440-driver | nvidia-tesla-418-driver libpoclu-dev
Recommended packages:
  libnvcuvid1 nsight-compute nsight-systems
The following NEW packages will be installed:
  g++-8 javascript-common libaccinj64-10.1 libcublas10 libcublaslt10 libcudart10.1 libcufft10 libcufftw10 libcuinj64-10.1 libcupti-dev libcupti-doc libcupti10.1 libcurand10 libcusolver10 libcusolvermg10 libcusparse10 libjs-jquery libnppc10 libnppial10 libnppicc10
  libnppicom10 libnppidei10 libnppif10 libnppig10 libnppim10 libnppist10 libnppisu10 libnppitc10 libnpps10 libnvblas10 libnvgraph10 libnvidia-compute-545 libnvidia-ml-dev libnvjpeg10 libnvrtc10.1 libnvtoolsext1 libnvvm3 libstdc++-8-dev libthrust-dev libvdpau-dev
  node-html5shiv nvidia-cuda-dev nvidia-cuda-doc nvidia-cuda-gdb nvidia-cuda-toolkit nvidia-opencl-dev nvidia-profiler nvidia-visual-profiler ocl-icd-opencl-dev opencl-c-headers
0 upgraded, 50 newly installed, 0 to remove and 11 not upgraded.
Need to get 0 B/1,160 MB of archives.
After this operation, 3,056 MB of additional disk space will be used.
Do you want to continue? [Y/n] y
Get:1 file:/var/cuda-repo-ubuntu2004-12-3-local  libnvidia-compute-545 545.23.08-0ubuntu1 [48.8 MB]
Err:1 file:/var/cuda-repo-ubuntu2004-12-3-local  libnvidia-compute-545 545.23.08-0ubuntu1
  File not found - /var/cuda-repo-ubuntu2004-12-3-local/./libnvidia-compute-545_545.23.08-0ubuntu1_amd64.deb (2: No such file or directory)
E: Failed to fetch file:/var/cuda-repo-ubuntu2004-12-3-local/./libnvidia-compute-545_545.23.08-0ubuntu1_amd64.deb  File not found - /var/cuda-repo-ubuntu2004-12-3-local/./libnvidia-compute-545_545.23.08-0ubuntu1_amd64.deb (2: No such file or directory)
E: Unable to fetch some archives, maybe run apt-get update or try with --fix-missing?
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ nvcc -v

Command 'nvcc' not found, but can be installed with:

sudo apt install nvidia-cuda-toolkit

rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ cd /usr/local/
rootroot@rootroot-X99-Turbo:/usr/local$ ll
total 44
drwxr-xr-x 11 root root 4096 1月  15 17:10 ./
drwxr-xr-x 14 root root 4096 3月  16  2023 ../
drwxr-xr-x  2 root root 4096 1月  15 17:10 bin/
lrwxrwxrwx  1 root root   22 1月  15 17:10 cuda -> /etc/alternatives/cuda/
lrwxrwxrwx  1 root root   25 1月  15 17:10 cuda-12 -> /etc/alternatives/cuda-12/
drwxr-xr-x 15 root root 4096 1月  15 17:10 cuda-12.3/
drwxr-xr-x  2 root root 4096 3月  16  2023 etc/
drwxr-xr-x  2 root root 4096 3月  16  2023 games/
drwxr-xr-x  2 root root 4096 3月  16  2023 include/
drwxr-xr-x  4 root root 4096 12月 16 19:57 lib/
lrwxrwxrwx  1 root root    9 12月 16 18:23 man -> share/man/
drwxr-xr-x  2 root root 4096 3月  16  2023 sbin/
drwxr-xr-x  7 root root 4096 3月  16  2023 share/
drwxr-xr-x  2 root root 4096 3月  16  2023 src/
rootroot@rootroot-X99-Turbo:/usr/local$ cd cuda
rootroot@rootroot-X99-Turbo:/usr/local/cuda$ ll
total 136
drwxr-xr-x 15 root root  4096 1月  15 17:10 ./
drwxr-xr-x 11 root root  4096 1月  15 17:10 ../
drwxr-xr-x  3 root root  4096 1月  15 17:09 bin/
drwxr-xr-x  5 root root  4096 1月  15 17:07 compute-sanitizer/
drwxr-xr-x  3 root root  4096 1月  15 17:09 doc/
-rw-r--r--  1 root root   160 10月 31 17:24 DOCS
-rw-r--r--  1 root root 61498 10月 31 17:24 EULA.txt
drwxr-xr-x  4 root root  4096 1月  16 10:39 extras/
drwxr-xr-x  4 root root  4096 1月  15 17:09 gds/
lrwxrwxrwx  1 root root    28 10月 31 17:20 include -> targets/x86_64-linux/include/
lrwxrwxrwx  1 root root    24 10月 31 17:20 lib64 -> targets/x86_64-linux/lib/
drwxr-xr-x  7 root root  4096 1月  15 17:09 libnvvp/
drwxr-xr-x  2 root root  4096 1月  15 17:09 nsightee_plugins/
drwxr-xr-x  3 root root  4096 1月  15 17:09 nvml/
drwxr-xr-x  6 root root  4096 1月  15 17:07 nvvm/
-rw-r--r--  1 root root   524 10月 31 17:24 README
drwxr-xr-x  3 root root  4096 1月  15 17:07 share/
drwxr-xr-x  2 root root  4096 1月  15 17:09 src/
drwxr-xr-x  3 root root  4096 1月  15 17:07 targets/
drwxr-xr-x  2 root root  4096 1月  15 17:07 tools/
-rw-r--r--  1 root root  3037 11月 30 02:48 version.json
rootroot@rootroot-X99-Turbo:/usr/local/cuda$ 
rootroot@rootroot-X99-Turbo:/usr/local/cuda$ cd bin/
rootroot@rootroot-X99-Turbo:/usr/local/cuda/bin$ ll
total 159484
drwxr-xr-x  3 root root     4096 1月  15 17:09 ./
drwxr-xr-x 15 root root     4096 1月  15 17:10 ../
-rwxr-xr-x  1 root root    88848 11月 23 03:32 bin2c*
lrwxrwxrwx  1 root root        4 10月 31 21:25 computeprof -> nvvp*
-rwxr-xr-x  1 root root      112 10月 31 17:41 compute-sanitizer*
drwxr-xr-x  2 root root     4096 1月  15 17:07 crt/
-rwxr-xr-x  1 root root  7336920 11月 23 03:32 cudafe++*
-rwxr-xr-x  1 root root 15812648 10月 31 18:46 cuda-gdb*
-rwxr-xr-x  1 root root   812256 10月 31 18:46 cuda-gdbserver*
-rwxr-xr-x  1 root root    75928 10月 31 17:49 cu++filt*
-rwxr-xr-x  1 root root   536064 10月 31 17:46 cuobjdump*
-rwxr-xr-x  1 root root   802968 11月 23 03:32 fatbinary*
-rwxr-xr-x  1 root root     3826 11月 30 02:48 ncu*
-rwxr-xr-x  1 root root     3616 11月 30 02:48 ncu-ui*
-rwxr-xr-x  1 root root     1580 10月 31 17:36 nsight_ee_plugins_manage.sh*
-rwxr-xr-x  1 root root      197 11月 30 02:48 nsight-sys*
-rwxr-xr-x  1 root root      743 11月 30 02:48 nsys*
-rwxr-xr-x  1 root root      833 11月 30 02:48 nsys-ui*
-rwxr-xr-x  1 root root 21784968 11月 23 03:32 nvcc*
-rwxr-xr-x  1 root root    10456 11月 23 03:32 __nvcc_device_query*
-rw-r--r--  1 root root      417 11月 23 03:32 nvcc.profile
-rwxr-xr-x  1 root root 50674712 10月 31 17:45 nvdisasm*
-rwxr-xr-x  1 root root 29746536 11月 23 03:32 nvlink*
-rwxr-xr-x  1 root root  6022464 10月 31 21:16 nvprof*
-rwxr-xr-x  1 root root   109536 10月 31 17:44 nvprune*
-rwxr-xr-x  1 root root      285 10月 31 21:25 nvvp*
-rwxr-xr-x  1 root root 29421152 11月 23 03:32 ptxas*
rootroot@rootroot-X99-Turbo:/usr/local/cuda/bin$ nvcc -v

Command 'nvcc' not found, but can be installed with:

sudo apt install nvidia-cuda-toolkit

rootroot@rootroot-X99-Turbo:/usr/local/cuda/bin$ ./nvcc -v
nvcc fatal   : No input files specified; use option --help for more information
rootroot@rootroot-X99-Turbo:/usr/local/cuda/bin$ ll nvcc
-rwxr-xr-x 1 root root 21784968 11月 23 03:32 nvcc*
rootroot@rootroot-X99-Turbo:/usr/local/cuda/bin$ ./nvcc 
bin2c                        cuda-gdb                     ncu                          nsys-ui                      nvlink                       
computeprof                  cuda-gdbserver               ncu-ui                       nvcc                         nvprof                       
compute-sanitizer            cu++filt                     nsight_ee_plugins_manage.sh  __nvcc_device_query          nvprune                      
crt/                         cuobjdump                    nsight-sys                   nvcc.profile                 nvvp                         
cudafe++                     fatbinary                    nsys                         nvdisasm                     ptxas                        
rootroot@rootroot-X99-Turbo:/usr/local/cuda/bin$ ./nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Wed_Nov_22_10:17:15_PST_2023
Cuda compilation tools, release 12.3, V12.3.107
Build cuda_12.3.r12.3/compiler.33567101_0
rootroot@rootroot-X99-Turbo:/usr/local/cuda/bin$ 
rootroot@rootroot-X99-Turbo:/usr/local/cuda/bin$ 
rootroot@rootroot-X99-Turbo:/usr/local/cuda/bin$ cd ..
rootroot@rootroot-X99-Turbo:/usr/local/cuda$ ll
total 136
drwxr-xr-x 15 root root  4096 1月  15 17:10 ./
drwxr-xr-x 11 root root  4096 1月  15 17:10 ../
drwxr-xr-x  3 root root  4096 1月  15 17:09 bin/
drwxr-xr-x  5 root root  4096 1月  15 17:07 compute-sanitizer/
drwxr-xr-x  3 root root  4096 1月  15 17:09 doc/
-rw-r--r--  1 root root   160 10月 31 17:24 DOCS
-rw-r--r--  1 root root 61498 10月 31 17:24 EULA.txt
drwxr-xr-x  4 root root  4096 1月  16 10:39 extras/
drwxr-xr-x  4 root root  4096 1月  15 17:09 gds/
lrwxrwxrwx  1 root root    28 10月 31 17:20 include -> targets/x86_64-linux/include/
lrwxrwxrwx  1 root root    24 10月 31 17:20 lib64 -> targets/x86_64-linux/lib/
drwxr-xr-x  7 root root  4096 1月  15 17:09 libnvvp/
drwxr-xr-x  2 root root  4096 1月  15 17:09 nsightee_plugins/
drwxr-xr-x  3 root root  4096 1月  15 17:09 nvml/
drwxr-xr-x  6 root root  4096 1月  15 17:07 nvvm/
-rw-r--r--  1 root root   524 10月 31 17:24 README
drwxr-xr-x  3 root root  4096 1月  15 17:07 share/
drwxr-xr-x  2 root root  4096 1月  15 17:09 src/
drwxr-xr-x  3 root root  4096 1月  15 17:07 targets/
drwxr-xr-x  2 root root  4096 1月  15 17:07 tools/
-rw-r--r--  1 root root  3037 11月 30 02:48 version.json
rootroot@rootroot-X99-Turbo:/usr/local/cuda$ cd lib64/
rootroot@rootroot-X99-Turbo:/usr/local/cuda/lib64$ ll
total 4137208
drwxr-xr-x 4 root root      4096 1月  15 17:09 ./
drwxr-xr-x 4 root root      4096 1月  15 17:07 ../
drwxr-xr-x 6 root root      4096 1月  15 17:07 cmake/
lrwxrwxrwx 1 root root        19 10月 31 21:16 libaccinj64.so -> libaccinj64.so.12.3
lrwxrwxrwx 1 root root        23 10月 31 21:16 libaccinj64.so.12.3 -> libaccinj64.so.12.3.101
-rw-r--r-- 1 root root   2412184 10月 31 21:16 libaccinj64.so.12.3.101
-rw-r--r-- 1 root root   1493144 10月 31 20:51 libcheckpoint.so
lrwxrwxrwx 1 root root        17 10月 31 17:51 libcublasLt.so -> libcublasLt.so.12
lrwxrwxrwx 1 root root        23 10月 31 17:51 libcublasLt.so.12 -> libcublasLt.so.12.3.4.1
-rw-r--r-- 1 root root 518358624 10月 31 17:51 libcublasLt.so.12.3.4.1
-rw-r--r-- 1 root root 781766258 10月 31 17:51 libcublasLt_static.a
lrwxrwxrwx 1 root root        15 10月 31 17:51 libcublas.so -> libcublas.so.12
lrwxrwxrwx 1 root root        21 10月 31 17:51 libcublas.so.12 -> libcublas.so.12.3.4.1
-rw-r--r-- 1 root root 106679344 10月 31 17:51 libcublas.so.12.3.4.1
-rw-r--r-- 1 root root 168603496 10月 31 17:51 libcublas_static.a
-rw-r--r-- 1 root root   1647010 10月 31 17:48 libcudadevrt.a
lrwxrwxrwx 1 root root        15 10月 31 17:48 libcudart.so -> libcudart.so.12
lrwxrwxrwx 1 root root        21 10月 31 17:48 libcudart.so.12 -> libcudart.so.12.3.101
-rw-r--r-- 1 root root    703808 10月 31 17:48 libcudart.so.12.3.101
-rw-r--r-- 1 root root   1417724 10月 31 17:48 libcudart_static.a
lrwxrwxrwx 1 root root        14 10月 31 17:57 libcufft.so -> libcufft.so.11
lrwxrwxrwx 1 root root        21 10月 31 17:57 libcufft.so.11 -> libcufft.so.11.0.12.1
-rw-r--r-- 1 root root 177827520 10月 31 17:57 libcufft.so.11.0.12.1
-rw-r--r-- 1 root root 199432168 10月 31 17:57 libcufft_static.a
-rw-r--r-- 1 root root 199334148 10月 31 17:57 libcufft_static_nocallback.a
lrwxrwxrwx 1 root root        15 10月 31 17:57 libcufftw.so -> libcufftw.so.11
lrwxrwxrwx 1 root root        22 10月 31 17:57 libcufftw.so.11 -> libcufftw.so.11.0.12.1
-rw-r--r-- 1 root root    966600 10月 31 17:57 libcufftw.so.11.0.12.1
-rw-r--r-- 1 root root     79566 10月 31 17:57 libcufftw_static.a
lrwxrwxrwx 1 root root        19 10月 26 07:36 libcufile_rdma.so -> libcufile_rdma.so.1
lrwxrwxrwx 1 root root        23 10月 26 07:36 libcufile_rdma.so.1 -> libcufile_rdma.so.1.8.1
-rw-r--r-- 1 root root     43320 10月 26 07:36 libcufile_rdma.so.1.8.1
-rw-r--r-- 1 root root     65206 10月 26 07:36 libcufile_rdma_static.a
lrwxrwxrwx 1 root root        14 10月 26 07:36 libcufile.so -> libcufile.so.0
lrwxrwxrwx 1 root root        18 10月 26 07:36 libcufile.so.0 -> libcufile.so.1.8.1
-rw-r--r-- 1 root root   2993680 10月 26 07:36 libcufile.so.1.8.1
-rw-r--r-- 1 root root  24282190 10月 26 07:36 libcufile_static.a
-rw-r--r-- 1 root root    948952 10月 31 17:49 libcufilt.a
lrwxrwxrwx 1 root root        18 10月 31 21:16 libcuinj64.so -> libcuinj64.so.12.3
lrwxrwxrwx 1 root root        22 10月 31 21:16 libcuinj64.so.12.3 -> libcuinj64.so.12.3.101
-rw-r--r-- 1 root root   2832640 10月 31 21:16 libcuinj64.so.12.3.101
-rw-r--r-- 1 root root     30922 10月 31 17:48 libculibos.a
lrwxrwxrwx 1 root root        14 10月 31 20:51 libcupti.so -> libcupti.so.12
lrwxrwxrwx 1 root root        20 10月 31 20:51 libcupti.so.12 -> libcupti.so.2023.3.1
-rw-r--r-- 1 root root   7683440 10月 31 20:51 libcupti.so.2023.3.1
-rw-r--r-- 1 root root  19214978 10月 31 20:51 libcupti_static.a
lrwxrwxrwx 1 root root        15 11月 23 03:55 libcurand.so -> libcurand.so.10
lrwxrwxrwx 1 root root        23 11月 23 03:55 libcurand.so.10 -> libcurand.so.10.3.4.107
-rw-r--r-- 1 root root  96259504 11月 23 03:55 libcurand.so.10.3.4.107
-rw-r--r-- 1 root root  96328614 11月 23 03:55 libcurand_static.a
-rw-r--r-- 1 root root  16788330 10月 31 18:36 libcusolver_lapack_static.a
-rw-r--r-- 1 root root   1005514 10月 31 18:36 libcusolver_metis_static.a
lrwxrwxrwx 1 root root        19 10月 31 18:36 libcusolverMg.so -> libcusolverMg.so.11
lrwxrwxrwx 1 root root        27 10月 31 18:36 libcusolverMg.so.11 -> libcusolverMg.so.11.5.4.101
-rw-r--r-- 1 root root  83040368 10月 31 18:36 libcusolverMg.so.11.5.4.101
lrwxrwxrwx 1 root root        17 10月 31 18:36 libcusolver.so -> libcusolver.so.11
lrwxrwxrwx 1 root root        25 10月 31 18:36 libcusolver.so.11 -> libcusolver.so.11.5.4.101
-rw-r--r-- 1 root root 115640600 10月 31 18:36 libcusolver.so.11.5.4.101
-rw-r--r-- 1 root root 133576956 10月 31 18:36 libcusolver_static.a
lrwxrwxrwx 1 root root        17 10月 31 18:09 libcusparse.so -> libcusparse.so.12
lrwxrwxrwx 1 root root        25 10月 31 18:09 libcusparse.so.12 -> libcusparse.so.12.2.0.103
-rw-r--r-- 1 root root 267184960 10月 31 18:09 libcusparse.so.12.2.0.103
-rw-r--r-- 1 root root 299914796 10月 31 18:09 libcusparse_static.a
-rw-r--r-- 1 root root   1005514 10月 31 18:36 libmetis_static.a
lrwxrwxrwx 1 root root        13 10月 31 18:19 libnppc.so -> libnppc.so.12
lrwxrwxrwx 1 root root        19 10月 31 18:19 libnppc.so.12 -> libnppc.so.12.2.3.2
-rw-r--r-- 1 root root   1642992 10月 31 18:19 libnppc.so.12.2.3.2
-rw-r--r-- 1 root root     30686 10月 31 18:19 libnppc_static.a
lrwxrwxrwx 1 root root        15 10月 31 18:19 libnppial.so -> libnppial.so.12
lrwxrwxrwx 1 root root        21 10月 31 18:19 libnppial.so.12 -> libnppial.so.12.2.3.2
-rw-r--r-- 1 root root  17568560 10月 31 18:19 libnppial.so.12.2.3.2
-rw-r--r-- 1 root root  19071940 10月 31 18:19 libnppial_static.a
lrwxrwxrwx 1 root root        15 10月 31 18:19 libnppicc.so -> libnppicc.so.12
lrwxrwxrwx 1 root root        21 10月 31 18:19 libnppicc.so.12 -> libnppicc.so.12.2.3.2
-rw-r--r-- 1 root root   7500616 10月 31 18:19 libnppicc.so.12.2.3.2
-rw-r--r-- 1 root root   7041694 10月 31 18:19 libnppicc_static.a
lrwxrwxrwx 1 root root        16 10月 31 18:19 libnppidei.so -> libnppidei.so.12
lrwxrwxrwx 1 root root        22 10月 31 18:19 libnppidei.so.12 -> libnppidei.so.12.2.3.2
-rw-r--r-- 1 root root  11134104 10月 31 18:19 libnppidei.so.12.2.3.2
-rw-r--r-- 1 root root  11875304 10月 31 18:19 libnppidei_static.a
lrwxrwxrwx 1 root root        14 10月 31 18:19 libnppif.so -> libnppif.so.12
lrwxrwxrwx 1 root root        20 10月 31 18:19 libnppif.so.12 -> libnppif.so.12.2.3.2
-rw-r--r-- 1 root root 101066824 10月 31 18:19 libnppif.so.12.2.3.2
-rw-r--r-- 1 root root 103942380 10月 31 18:19 libnppif_static.a
lrwxrwxrwx 1 root root        14 10月 31 18:19 libnppig.so -> libnppig.so.12
lrwxrwxrwx 1 root root        20 10月 31 18:19 libnppig.so.12 -> libnppig.so.12.2.3.2
-rw-r--r-- 1 root root  41137040 10月 31 18:19 libnppig.so.12.2.3.2
-rw-r--r-- 1 root root  41987560 10月 31 18:19 libnppig_static.a
lrwxrwxrwx 1 root root        14 10月 31 18:19 libnppim.so -> libnppim.so.12
lrwxrwxrwx 1 root root        20 10月 31 18:19 libnppim.so.12 -> libnppim.so.12.2.3.2
-rw-r--r-- 1 root root  10322760 10月 31 18:19 libnppim.so.12.2.3.2
-rw-r--r-- 1 root root   9259562 10月 31 18:19 libnppim_static.a
lrwxrwxrwx 1 root root        15 10月 31 18:19 libnppist.so -> libnppist.so.12
lrwxrwxrwx 1 root root        21 10月 31 18:19 libnppist.so.12 -> libnppist.so.12.2.3.2
-rw-r--r-- 1 root root  38171728 10月 31 18:19 libnppist.so.12.2.3.2
-rw-r--r-- 1 root root  39228112 10月 31 18:19 libnppist_static.a
lrwxrwxrwx 1 root root        15 10月 31 18:19 libnppisu.so -> libnppisu.so.12
lrwxrwxrwx 1 root root        21 10月 31 18:19 libnppisu.so.12 -> libnppisu.so.12.2.3.2
-rw-r--r-- 1 root root    716168 10月 31 18:19 libnppisu.so.12.2.3.2
-rw-r--r-- 1 root root     11266 10月 31 18:19 libnppisu_static.a
lrwxrwxrwx 1 root root        15 10月 31 18:19 libnppitc.so -> libnppitc.so.12
lrwxrwxrwx 1 root root        21 10月 31 18:19 libnppitc.so.12 -> libnppitc.so.12.2.3.2
-rw-r--r-- 1 root root   5530224 10月 31 18:19 libnppitc.so.12.2.3.2
-rw-r--r-- 1 root root   4503836 10月 31 18:19 libnppitc_static.a
lrwxrwxrwx 1 root root        13 10月 31 18:19 libnpps.so -> libnpps.so.12
lrwxrwxrwx 1 root root        19 10月 31 18:19 libnpps.so.12 -> libnpps.so.12.2.3.2
-rw-r--r-- 1 root root  18105592 10月 31 18:19 libnpps.so.12.2.3.2
-rw-r--r-- 1 root root  17960158 10月 31 18:19 libnpps_static.a
lrwxrwxrwx 1 root root        15 10月 31 17:51 libnvblas.so -> libnvblas.so.12
lrwxrwxrwx 1 root root        21 10月 31 17:51 libnvblas.so.12 -> libnvblas.so.12.3.4.1
-rw-r--r-- 1 root root    728856 10月 31 17:51 libnvblas.so.12.3.4.1
lrwxrwxrwx 1 root root        18 10月 31 18:11 libnvJitLink.so -> libnvJitLink.so.12
lrwxrwxrwx 1 root root        24 10月 31 18:11 libnvJitLink.so.12 -> libnvJitLink.so.12.3.101
-rw-r--r-- 1 root root  52190720 10月 31 18:11 libnvJitLink.so.12.3.101
-rw-r--r-- 1 root root  63530708 10月 31 18:11 libnvJitLink_static.a
lrwxrwxrwx 1 root root        15 10月 31 17:49 libnvjpeg.so -> libnvjpeg.so.12
lrwxrwxrwx 1 root root        22 10月 31 17:49 libnvjpeg.so.12 -> libnvjpeg.so.12.3.0.81
-rw-r--r-- 1 root root   6705968 10月 31 17:49 libnvjpeg.so.12.3.0.81
-rw-r--r-- 1 root root   6828780 10月 31 17:49 libnvjpeg_static.a
-rw-r--r-- 1 root root  28538488 10月 31 20:51 libnvperf_host.so
-rw-r--r-- 1 root root  36274804 10月 31 20:51 libnvperf_host_static.a
-rw-r--r-- 1 root root   6018384 10月 31 20:51 libnvperf_target.so
-rw-r--r-- 1 root root  47925582 11月 23 03:32 libnvptxcompiler_static.a
lrwxrwxrwx 1 root root        25 11月 23 03:49 libnvrtc-builtins.so -> libnvrtc-builtins.so.12.3
lrwxrwxrwx 1 root root        29 11月 23 03:49 libnvrtc-builtins.so.12.3 -> libnvrtc-builtins.so.12.3.107
-rw-r--r-- 1 root root   6662024 11月 23 03:49 libnvrtc-builtins.so.12.3.107
-rw-r--r-- 1 root root   6681284 11月 23 03:49 libnvrtc-builtins_static.a
lrwxrwxrwx 1 root root        14 11月 23 03:49 libnvrtc.so -> libnvrtc.so.12
lrwxrwxrwx 1 root root        20 11月 23 03:49 libnvrtc.so.12 -> libnvrtc.so.12.3.107
-rw-r--r-- 1 root root  60792048 11月 23 03:49 libnvrtc.so.12.3.107
-rw-r--r-- 1 root root  75105270 11月 23 03:49 libnvrtc_static.a
lrwxrwxrwx 1 root root        18 10月 31 17:52 libnvToolsExt.so -> libnvToolsExt.so.1
lrwxrwxrwx 1 root root        22 10月 31 17:52 libnvToolsExt.so.1 -> libnvToolsExt.so.1.0.0
-rw-r--r-- 1 root root     40136 10月 31 17:52 libnvToolsExt.so.1.0.0
lrwxrwxrwx 1 root root        14 10月 31 17:37 libOpenCL.so -> libOpenCL.so.1
lrwxrwxrwx 1 root root        16 10月 31 17:37 libOpenCL.so.1 -> libOpenCL.so.1.0
lrwxrwxrwx 1 root root        18 10月 31 17:37 libOpenCL.so.1.0 -> libOpenCL.so.1.0.0
-rw-r--r-- 1 root root     30856 10月 31 17:37 libOpenCL.so.1.0.0
-rw-r--r-- 1 root root    912728 10月 31 20:51 libpcsamplingutil.so
drwxr-xr-x 2 root root      4096 1月  15 17:09 stubs/
rootroot@rootroot-X99-Turbo:/usr/local/cuda/lib64$ cd -
/usr/local/cuda
rootroot@rootroot-X99-Turbo:/usr/local/cuda$ cd ~/whisper.cpp/
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ll
total 20728
drwxrwxr-x 17 rootroot rootroot     4096 2月   2 17:46 ./
drwxr-xr-x 30 rootroot rootroot     4096 2月   2 16:49 ../
drwxrwxr-x  7 rootroot rootroot     4096 2月   2 16:49 bindings/
-rwx------  1 rootroot rootroot  3465644 1月  12 01:28 chs.mp4*
-rw-rw-r--  1 rootroot rootroot 13497126 2月   2 17:26 chs.wav
-rw-rw-r--  1 rootroot rootroot    11821 2月   2 17:41 chs.wav使用CPU.srt
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 cmake/
-rw-rw-r--  1 rootroot rootroot    19150 2月   2 16:49 CMakeLists.txt
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 coreml/
drwx------  2 rootroot rootroot     4096 2月   2 17:45 CPU/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 .devops/
drwxrwxr-x 24 rootroot rootroot     4096 2月   2 16:49 examples/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 extra/
-rw-rw-r--  1 rootroot rootroot    31647 2月   2 16:49 ggml-alloc.c
-rw-rw-r--  1 rootroot rootroot     4055 2月   2 16:49 ggml-alloc.h
-rw-rw-r--  1 rootroot rootroot    20504 2月   2 17:46 ggml-alloc.o
-rw-rw-r--  1 rootroot rootroot    67212 2月   2 16:49 ggml-backend.c
-rw-rw-r--  1 rootroot rootroot    11720 2月   2 16:49 ggml-backend.h
-rw-rw-r--  1 rootroot rootroot     5874 2月   2 16:49 ggml-backend-impl.h
-rw-rw-r--  1 rootroot rootroot    58464 2月   2 17:46 ggml-backend.o
-rw-rw-r--  1 rootroot rootroot   676115 2月   2 16:49 ggml.c
-rw-rw-r--  1 rootroot rootroot   440093 2月   2 16:49 ggml-cuda.cu
-rw-rw-r--  1 rootroot rootroot     2104 2月   2 16:49 ggml-cuda.h
-rw-rw-r--  1 rootroot rootroot    85094 2月   2 16:49 ggml.h
-rw-rw-r--  1 rootroot rootroot     7567 2月   2 16:49 ggml-impl.h
-rw-rw-r--  1 rootroot rootroot     2358 2月   2 16:49 ggml-metal.h
-rw-rw-r--  1 rootroot rootroot   150160 2月   2 16:49 ggml-metal.m
-rw-rw-r--  1 rootroot rootroot   225659 2月   2 16:49 ggml-metal.metal
-rw-rw-r--  1 rootroot rootroot   550040 2月   2 17:46 ggml.o
-rw-rw-r--  1 rootroot rootroot    85693 2月   2 16:49 ggml-opencl.cpp
-rw-rw-r--  1 rootroot rootroot     1386 2月   2 16:49 ggml-opencl.h
-rw-rw-r--  1 rootroot rootroot   401791 2月   2 16:49 ggml-quants.c
-rw-rw-r--  1 rootroot rootroot    13705 2月   2 16:49 ggml-quants.h
-rw-rw-r--  1 rootroot rootroot   198024 2月   2 17:46 ggml-quants.o
drwxrwxr-x  8 rootroot rootroot     4096 2月   2 16:49 .git/
drwxrwxr-x  3 rootroot rootroot     4096 2月   2 16:49 .github/
-rw-rw-r--  1 rootroot rootroot      803 2月   2 16:49 .gitignore
-rw-rw-r--  1 rootroot rootroot       96 2月   2 16:49 .gitmodules
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 grammars/
-rw-rw-r--  1 rootroot rootroot     1072 2月   2 16:49 LICENSE
-rw-rw-r--  1 rootroot rootroot    14883 2月   2 16:49 Makefile
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 17:24 models/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 openvino/
-rw-rw-r--  1 rootroot rootroot     1776 2月   2 16:49 Package.swift
-rw-rw-r--  1 rootroot rootroot    39115 2月   2 16:49 README.md
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 samples/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 spm-headers/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 tests/
-rw-rw-r--  1 rootroot rootroot   232975 2月   2 16:49 whisper.cpp
-rw-rw-r--  1 rootroot rootroot    30248 2月   2 16:49 whisper.h
-rw-rw-r--  1 rootroot rootroot   728384 2月   2 17:46 whisper.o
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ cd ..
rootroot@rootroot-X99-Turbo:~$ 
rootroot@rootroot-X99-Turbo:~$ cp .bashrc bak1.bashrc
rootroot@rootroot-X99-Turbo:~$ cd -
/home/rootroot/whisper.cpp
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ll
total 20728
drwxrwxr-x 17 rootroot rootroot     4096 2月   2 17:46 ./
drwxr-xr-x 30 rootroot rootroot     4096 2月   2 17:55 ../
drwxrwxr-x  7 rootroot rootroot     4096 2月   2 16:49 bindings/
-rwx------  1 rootroot rootroot  3465644 1月  12 01:28 chs.mp4*
-rw-rw-r--  1 rootroot rootroot 13497126 2月   2 17:26 chs.wav
-rw-rw-r--  1 rootroot rootroot    11821 2月   2 17:41 chs.wav使用CPU.srt
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 cmake/
-rw-rw-r--  1 rootroot rootroot    19150 2月   2 16:49 CMakeLists.txt
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 coreml/
drwx------  2 rootroot rootroot     4096 2月   2 17:45 CPU/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 .devops/
drwxrwxr-x 24 rootroot rootroot     4096 2月   2 16:49 examples/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 extra/
-rw-rw-r--  1 rootroot rootroot    31647 2月   2 16:49 ggml-alloc.c
-rw-rw-r--  1 rootroot rootroot     4055 2月   2 16:49 ggml-alloc.h
-rw-rw-r--  1 rootroot rootroot    20504 2月   2 17:46 ggml-alloc.o
-rw-rw-r--  1 rootroot rootroot    67212 2月   2 16:49 ggml-backend.c
-rw-rw-r--  1 rootroot rootroot    11720 2月   2 16:49 ggml-backend.h
-rw-rw-r--  1 rootroot rootroot     5874 2月   2 16:49 ggml-backend-impl.h
-rw-rw-r--  1 rootroot rootroot    58464 2月   2 17:46 ggml-backend.o
-rw-rw-r--  1 rootroot rootroot   676115 2月   2 16:49 ggml.c
-rw-rw-r--  1 rootroot rootroot   440093 2月   2 16:49 ggml-cuda.cu
-rw-rw-r--  1 rootroot rootroot     2104 2月   2 16:49 ggml-cuda.h
-rw-rw-r--  1 rootroot rootroot    85094 2月   2 16:49 ggml.h
-rw-rw-r--  1 rootroot rootroot     7567 2月   2 16:49 ggml-impl.h
-rw-rw-r--  1 rootroot rootroot     2358 2月   2 16:49 ggml-metal.h
-rw-rw-r--  1 rootroot rootroot   150160 2月   2 16:49 ggml-metal.m
-rw-rw-r--  1 rootroot rootroot   225659 2月   2 16:49 ggml-metal.metal
-rw-rw-r--  1 rootroot rootroot   550040 2月   2 17:46 ggml.o
-rw-rw-r--  1 rootroot rootroot    85693 2月   2 16:49 ggml-opencl.cpp
-rw-rw-r--  1 rootroot rootroot     1386 2月   2 16:49 ggml-opencl.h
-rw-rw-r--  1 rootroot rootroot   401791 2月   2 16:49 ggml-quants.c
-rw-rw-r--  1 rootroot rootroot    13705 2月   2 16:49 ggml-quants.h
-rw-rw-r--  1 rootroot rootroot   198024 2月   2 17:46 ggml-quants.o
drwxrwxr-x  8 rootroot rootroot     4096 2月   2 16:49 .git/
drwxrwxr-x  3 rootroot rootroot     4096 2月   2 16:49 .github/
-rw-rw-r--  1 rootroot rootroot      803 2月   2 16:49 .gitignore
-rw-rw-r--  1 rootroot rootroot       96 2月   2 16:49 .gitmodules
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 grammars/
-rw-rw-r--  1 rootroot rootroot     1072 2月   2 16:49 LICENSE
-rw-rw-r--  1 rootroot rootroot    14883 2月   2 16:49 Makefile
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 17:24 models/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 openvino/
-rw-rw-r--  1 rootroot rootroot     1776 2月   2 16:49 Package.swift
-rw-rw-r--  1 rootroot rootroot    39115 2月   2 16:49 README.md
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 samples/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 spm-headers/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 tests/
-rw-rw-r--  1 rootroot rootroot   232975 2月   2 16:49 whisper.cpp
-rw-rw-r--  1 rootroot rootroot    30248 2月   2 16:49 whisper.h
-rw-rw-r--  1 rootroot rootroot   728384 2月   2 17:46 whisper.o
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ source ~/.bashrc
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ echo $P
$PATH        $PIPESTATUS  $PPID        $PS1         $PS2         $PS4         $PWD         
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ echo $PATH 
/usr/local/cuda/bin:/home/rootroot/.local/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Wed_Nov_22_10:17:15_PST_2023
Cuda compilation tools, release 12.3, V12.3.107
Build cuda_12.3.r12.3/compiler.33567101_0
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ echo $LD_LIBRARY_PATH
/usr/local/cuda/lib64:
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ WHISPER_CUBLAS=1 make -j16
I whisper.cpp build info: 
I UNAME_S:  Linux
I UNAME_P:  x86_64
I UNAME_M:  x86_64
I CFLAGS:   -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include
I LDFLAGS:   -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib
I CC:       cc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
I CXX:      g++ (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0

nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -Wno-pedantic -c ggml-cuda.cu -o ggml-cuda.o
g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include examples/main/main.cpp examples/common.cpp examples/common-ggml.cpp ggml-cuda.o ggml.o ggml-alloc.o ggml-backend.o ggml-quants.o whisper.o -o main  -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib
g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include examples/bench/bench.cpp ggml-cuda.o ggml.o ggml-alloc.o ggml-backend.o ggml-quants.o whisper.o -o bench  -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib
g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include examples/quantize/quantize.cpp examples/common.cpp examples/common-ggml.cpp ggml-cuda.o ggml.o ggml-alloc.o ggml-backend.o ggml-quants.o whisper.o -o quantize  -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib
g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include examples/server/server.cpp examples/common.cpp examples/common-ggml.cpp ggml-cuda.o ggml.o ggml-alloc.o ggml-backend.o ggml-quants.o whisper.o -o server  -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib 
/usr/bin/ld: ggml.o: in function `ggml_compute_forward_mul_mat':
ggml.c:(.text+0x178a3): undefined reference to `ggml_cl_can_mul_mat'
/usr/bin/ld: ggml.c:(.text+0x17e01): undefined reference to `ggml_cl_mul_mat'
/usr/bin/ld: ggml.o: in function `ggml_init':
ggml.c:(.text+0x23942): undefined reference to `ggml_cl_init'
/usr/bin/ld: ggml.o: in function `ggml_graph_plan':
ggml.c:(.text+0x38346): undefined reference to `ggml_cl_can_mul_mat'
/usr/bin/ld: ggml.c:(.text+0x386a4): undefined reference to `ggml_cl_mul_mat_get_wsize'
/usr/bin/ld: ggml.o: in function `ggml_compute_forward_add':
ggml.c:(.text+0x1afdc): undefined reference to `ggml_cl_add'
/usr/bin/ld: ggml.o: in function `ggml_compute_forward_mul':
ggml.c:(.text+0x1d60c): undefined reference to `ggml_cl_mul'
collect2: error: ld returned 1 exit status
make: *** [Makefile:367: bench] Error 1
make: *** Waiting for unfinished jobs....
/usr/bin/ld: ggml.o: in function `ggml_compute_forward_mul_mat':
ggml.c:(.text+0x178a3): undefined reference to `ggml_cl_can_mul_mat'
/usr/bin/ld: ggml.c:(.text+0x17e01): undefined reference to `ggml_cl_mul_mat'
/usr/bin/ld: ggml.o: in function `ggml_init':
ggml.c:(.text+0x23942): undefined reference to `ggml_cl_init'
/usr/bin/ld: ggml.o: in function `ggml_graph_plan':
ggml.c:(.text+0x38346): undefined reference to `ggml_cl_can_mul_mat'
/usr/bin/ld: ggml.c:(.text+0x386a4): undefined reference to `ggml_cl_mul_mat_get_wsize'
/usr/bin/ld: ggml.o: in function `ggml_compute_forward_add':
ggml.c:(.text+0x1afdc): undefined reference to `ggml_cl_add'
/usr/bin/ld: ggml.o: in function `ggml_compute_forward_mul':
ggml.c:(.text+0x1d60c): undefined reference to `ggml_cl_mul'
collect2: error: ld returned 1 exit status
make: *** [Makefile:370: quantize] Error 1
/usr/bin/ld: ggml.o: in function `ggml_compute_forward_mul_mat':
ggml.c:(.text+0x178a3): undefined reference to `ggml_cl_can_mul_mat'
/usr/bin/ld: ggml.c:(.text+0x17e01): undefined reference to `ggml_cl_mul_mat'
/usr/bin/ld: ggml.o: in function `ggml_init':
ggml.c:(.text+0x23942): undefined reference to `ggml_cl_init'
/usr/bin/ld: ggml.o: in function `ggml_graph_plan':
ggml.c:(.text+0x38346): undefined reference to `ggml_cl_can_mul_mat'
/usr/bin/ld: ggml.c:(.text+0x386a4): undefined reference to `ggml_cl_mul_mat_get_wsize'
/usr/bin/ld: ggml.o: in function `ggml_compute_forward_add':
ggml.c:(.text+0x1afdc): undefined reference to `ggml_cl_add'
/usr/bin/ld: ggml.o: in function `ggml_compute_forward_mul':
ggml.c:(.text+0x1d60c): undefined reference to `ggml_cl_mul'
collect2: error: ld returned 1 exit status
make: *** [Makefile:363: main] Error 1
/usr/bin/ld: ggml.o: in function `ggml_compute_forward_mul_mat':
ggml.c:(.text+0x178a3): undefined reference to `ggml_cl_can_mul_mat'
/usr/bin/ld: ggml.c:(.text+0x17e01): undefined reference to `ggml_cl_mul_mat'
/usr/bin/ld: ggml.o: in function `ggml_init':
ggml.c:(.text+0x23942): undefined reference to `ggml_cl_init'
/usr/bin/ld: ggml.o: in function `ggml_graph_plan':
ggml.c:(.text+0x38346): undefined reference to `ggml_cl_can_mul_mat'
/usr/bin/ld: ggml.c:(.text+0x386a4): undefined reference to `ggml_cl_mul_mat_get_wsize'
/usr/bin/ld: ggml.o: in function `ggml_compute_forward_add':
ggml.c:(.text+0x1afdc): undefined reference to `ggml_cl_add'
/usr/bin/ld: ggml.o: in function `ggml_compute_forward_mul':
ggml.c:(.text+0x1d60c): undefined reference to `ggml_cl_mul'
collect2: error: ld returned 1 exit status
make: *** [Makefile:373: server] Error 1
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ make clean
I whisper.cpp build info: 
I UNAME_S:  Linux
I UNAME_P:  x86_64
I UNAME_M:  x86_64
I CFLAGS:   -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3
I LDFLAGS:  
I CC:       cc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
I CXX:      g++ (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0

rm -f *.o main stream command talk talk-llama bench quantize server lsp libwhisper.a libwhisper.so
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ WHISPER_CUBLAS=1 make
I whisper.cpp build info: 
I UNAME_S:  Linux
I UNAME_P:  x86_64
I UNAME_M:  x86_64
I CFLAGS:   -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include
I LDFLAGS:   -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib
I CC:       cc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
I CXX:      g++ (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0

nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -Wno-pedantic -c ggml-cuda.cu -o ggml-cuda.o
cc  -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include   -c ggml.c -o ggml.o
cc  -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include   -c ggml-alloc.c -o ggml-alloc.o
cc  -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include   -c ggml-backend.c -o ggml-backend.o
cc  -I.              -O3 -DNDEBUG -std=c11   -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include   -c ggml-quants.c -o ggml-quants.o
g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -c whisper.cpp -o whisper.o
g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include examples/main/main.cpp examples/common.cpp examples/common-ggml.cpp ggml-cuda.o ggml.o ggml-alloc.o ggml-backend.o ggml-quants.o whisper.o -o main  -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib
./main -h

usage: ./main [options] file0.wav file1.wav ...

options:
  -h,        --help              [default] show this help message and exit
  -t N,      --threads N         [4      ] number of threads to use during computation
  -p N,      --processors N      [1      ] number of processors to use during computation
  -ot N,     --offset-t N        [0      ] time offset in milliseconds
  -on N,     --offset-n N        [0      ] segment index offset
  -d  N,     --duration N        [0      ] duration of audio to process in milliseconds
  -mc N,     --max-context N     [-1     ] maximum number of text context tokens to store
  -ml N,     --max-len N         [0      ] maximum segment length in characters
  -sow,      --split-on-word     [false  ] split on word rather than on token
  -bo N,     --best-of N         [5      ] number of best candidates to keep
  -bs N,     --beam-size N       [5      ] beam size for beam search
  -wt N,     --word-thold N      [0.01   ] word timestamp probability threshold
  -et N,     --entropy-thold N   [2.40   ] entropy threshold for decoder fail
  -lpt N,    --logprob-thold N   [-1.00  ] log probability threshold for decoder fail
  -debug,    --debug-mode        [false  ] enable debug mode (eg. dump log_mel)
  -tr,       --translate         [false  ] translate from source language to english
  -di,       --diarize           [false  ] stereo audio diarization
  -tdrz,     --tinydiarize       [false  ] enable tinydiarize (requires a tdrz model)
  -nf,       --no-fallback       [false  ] do not use temperature fallback while decoding
  -otxt,     --output-txt        [false  ] output result in a text file
  -ovtt,     --output-vtt        [false  ] output result in a vtt file
  -osrt,     --output-srt        [false  ] output result in a srt file
  -olrc,     --output-lrc        [false  ] output result in a lrc file
  -owts,     --output-words      [false  ] output script for generating karaoke video
  -fp,       --font-path         [/System/Library/Fonts/Supplemental/Courier New Bold.ttf] path to a monospace font for karaoke video
  -ocsv,     --output-csv        [false  ] output result in a CSV file
  -oj,       --output-json       [false  ] output result in a JSON file
  -ojf,      --output-json-full  [false  ] include more information in the JSON file
  -of FNAME, --output-file FNAME [       ] output file path (without file extension)
  -np,       --no-prints         [false  ] do not print anything other than the results
  -ps,       --print-special     [false  ] print special tokens
  -pc,       --print-colors      [false  ] print colors
  -pp,       --print-progress    [false  ] print progress
  -nt,       --no-timestamps     [false  ] do not print timestamps
  -l LANG,   --language LANG     [en     ] spoken language ('auto' for auto-detect)
  -dl,       --detect-language   [false  ] exit after automatically detecting language
             --prompt PROMPT     [       ] initial prompt
  -m FNAME,  --model FNAME       [models/ggml-base.en.bin] model path
  -f FNAME,  --file FNAME        [       ] input WAV file path
  -oved D,   --ov-e-device DNAME [CPU    ] the OpenVINO device used for encode inference
  -ls,       --log-score         [false  ] log best decoder scores of tokens
  -ng,       --no-gpu            [false  ] disable GPU

g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include examples/bench/bench.cpp ggml-cuda.o ggml.o ggml-alloc.o ggml-backend.o ggml-quants.o whisper.o -o bench  -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib
g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include examples/quantize/quantize.cpp examples/common.cpp examples/common-ggml.cpp ggml-cuda.o ggml.o ggml-alloc.o ggml-backend.o ggml-quants.o whisper.o -o quantize  -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib
g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -pthread -mavx -mavx2 -mfma -mf16c -msse3 -mssse3 -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include examples/server/server.cpp examples/common.cpp examples/common-ggml.cpp ggml-cuda.o ggml.o ggml-alloc.o ggml-backend.o ggml-quants.o whisper.o -o server  -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ll
total 33624
drwxrwxr-x 17 rootroot rootroot     4096 2月   2 18:00 ./
drwxr-xr-x 30 rootroot rootroot     4096 2月   2 17:55 ../
-rwxrwxr-x  1 rootroot rootroot  2632736 2月   2 18:00 bench*
drwxrwxr-x  7 rootroot rootroot     4096 2月   2 16:49 bindings/
-rwx------  1 rootroot rootroot  3465644 1月  12 01:28 chs.mp4*
-rw-rw-r--  1 rootroot rootroot 13497126 2月   2 17:26 chs.wav
-rw-rw-r--  1 rootroot rootroot    11821 2月   2 17:41 chs.wav使用CPU.srt
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 cmake/
-rw-rw-r--  1 rootroot rootroot    19150 2月   2 16:49 CMakeLists.txt
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 coreml/
drwx------  2 rootroot rootroot     4096 2月   2 17:45 CPU/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 .devops/
drwxrwxr-x 24 rootroot rootroot     4096 2月   2 16:49 examples/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 extra/
-rw-rw-r--  1 rootroot rootroot    31647 2月   2 16:49 ggml-alloc.c
-rw-rw-r--  1 rootroot rootroot     4055 2月   2 16:49 ggml-alloc.h
-rw-rw-r--  1 rootroot rootroot    20504 2月   2 17:59 ggml-alloc.o
-rw-rw-r--  1 rootroot rootroot    67212 2月   2 16:49 ggml-backend.c
-rw-rw-r--  1 rootroot rootroot    11720 2月   2 16:49 ggml-backend.h
-rw-rw-r--  1 rootroot rootroot     5874 2月   2 16:49 ggml-backend-impl.h
-rw-rw-r--  1 rootroot rootroot    58712 2月   2 17:59 ggml-backend.o
-rw-rw-r--  1 rootroot rootroot   676115 2月   2 16:49 ggml.c
-rw-rw-r--  1 rootroot rootroot   440093 2月   2 16:49 ggml-cuda.cu
-rw-rw-r--  1 rootroot rootroot     2104 2月   2 16:49 ggml-cuda.h
-rw-rw-r--  1 rootroot rootroot  1741536 2月   2 17:59 ggml-cuda.o
-rw-rw-r--  1 rootroot rootroot    85094 2月   2 16:49 ggml.h
-rw-rw-r--  1 rootroot rootroot     7567 2月   2 16:49 ggml-impl.h
-rw-rw-r--  1 rootroot rootroot     2358 2月   2 16:49 ggml-metal.h
-rw-rw-r--  1 rootroot rootroot   150160 2月   2 16:49 ggml-metal.m
-rw-rw-r--  1 rootroot rootroot   225659 2月   2 16:49 ggml-metal.metal
-rw-rw-r--  1 rootroot rootroot   548304 2月   2 17:59 ggml.o
-rw-rw-r--  1 rootroot rootroot    85693 2月   2 16:49 ggml-opencl.cpp
-rw-rw-r--  1 rootroot rootroot     1386 2月   2 16:49 ggml-opencl.h
-rw-rw-r--  1 rootroot rootroot   401791 2月   2 16:49 ggml-quants.c
-rw-rw-r--  1 rootroot rootroot    13705 2月   2 16:49 ggml-quants.h
-rw-rw-r--  1 rootroot rootroot   198024 2月   2 17:59 ggml-quants.o
drwxrwxr-x  8 rootroot rootroot     4096 2月   2 16:49 .git/
drwxrwxr-x  3 rootroot rootroot     4096 2月   2 16:49 .github/
-rw-rw-r--  1 rootroot rootroot      803 2月   2 16:49 .gitignore
-rw-rw-r--  1 rootroot rootroot       96 2月   2 16:49 .gitmodules
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 grammars/
-rw-rw-r--  1 rootroot rootroot     1072 2月   2 16:49 LICENSE
-rwxrwxr-x  1 rootroot rootroot  2858480 2月   2 18:00 main*
-rw-rw-r--  1 rootroot rootroot    14883 2月   2 16:49 Makefile
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 17:24 models/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 openvino/
-rw-rw-r--  1 rootroot rootroot     1776 2月   2 16:49 Package.swift
-rwxrwxr-x  1 rootroot rootroot  2805104 2月   2 18:00 quantize*
-rw-rw-r--  1 rootroot rootroot    39115 2月   2 16:49 README.md
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 samples/
-rwxrwxr-x  1 rootroot rootroot  3161376 2月   2 18:00 server*
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 spm-headers/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 tests/
-rw-rw-r--  1 rootroot rootroot   232975 2月   2 16:49 whisper.cpp
-rw-rw-r--  1 rootroot rootroot    30248 2月   2 16:49 whisper.h
-rw-rw-r--  1 rootroot rootroot   729136 2月   2 18:00 whisper.o
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ll main 
-rwxrwxr-x 1 rootroot rootroot 2858480 2月   2 18:00 main*
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ll
total 33624
drwxrwxr-x 17 rootroot rootroot     4096 2月   2 18:00 ./
drwxr-xr-x 30 rootroot rootroot     4096 2月   2 17:55 ../
-rwxrwxr-x  1 rootroot rootroot  2632736 2月   2 18:00 bench*
drwxrwxr-x  7 rootroot rootroot     4096 2月   2 16:49 bindings/
-rwx------  1 rootroot rootroot  3465644 1月  12 01:28 chs.mp4*
-rw-rw-r--  1 rootroot rootroot 13497126 2月   2 17:26 chs.wav
-rw-rw-r--  1 rootroot rootroot    11821 2月   2 17:41 chs.wav使用CPU.srt
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 cmake/
-rw-rw-r--  1 rootroot rootroot    19150 2月   2 16:49 CMakeLists.txt
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 coreml/
drwx------  2 rootroot rootroot     4096 2月   2 17:45 CPU/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 .devops/
drwxrwxr-x 24 rootroot rootroot     4096 2月   2 16:49 examples/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 extra/
-rw-rw-r--  1 rootroot rootroot    31647 2月   2 16:49 ggml-alloc.c
-rw-rw-r--  1 rootroot rootroot     4055 2月   2 16:49 ggml-alloc.h
-rw-rw-r--  1 rootroot rootroot    20504 2月   2 17:59 ggml-alloc.o
-rw-rw-r--  1 rootroot rootroot    67212 2月   2 16:49 ggml-backend.c
-rw-rw-r--  1 rootroot rootroot    11720 2月   2 16:49 ggml-backend.h
-rw-rw-r--  1 rootroot rootroot     5874 2月   2 16:49 ggml-backend-impl.h
-rw-rw-r--  1 rootroot rootroot    58712 2月   2 17:59 ggml-backend.o
-rw-rw-r--  1 rootroot rootroot   676115 2月   2 16:49 ggml.c
-rw-rw-r--  1 rootroot rootroot   440093 2月   2 16:49 ggml-cuda.cu
-rw-rw-r--  1 rootroot rootroot     2104 2月   2 16:49 ggml-cuda.h
-rw-rw-r--  1 rootroot rootroot  1741536 2月   2 17:59 ggml-cuda.o
-rw-rw-r--  1 rootroot rootroot    85094 2月   2 16:49 ggml.h
-rw-rw-r--  1 rootroot rootroot     7567 2月   2 16:49 ggml-impl.h
-rw-rw-r--  1 rootroot rootroot     2358 2月   2 16:49 ggml-metal.h
-rw-rw-r--  1 rootroot rootroot   150160 2月   2 16:49 ggml-metal.m
-rw-rw-r--  1 rootroot rootroot   225659 2月   2 16:49 ggml-metal.metal
-rw-rw-r--  1 rootroot rootroot   548304 2月   2 17:59 ggml.o
-rw-rw-r--  1 rootroot rootroot    85693 2月   2 16:49 ggml-opencl.cpp
-rw-rw-r--  1 rootroot rootroot     1386 2月   2 16:49 ggml-opencl.h
-rw-rw-r--  1 rootroot rootroot   401791 2月   2 16:49 ggml-quants.c
-rw-rw-r--  1 rootroot rootroot    13705 2月   2 16:49 ggml-quants.h
-rw-rw-r--  1 rootroot rootroot   198024 2月   2 17:59 ggml-quants.o
drwxrwxr-x  8 rootroot rootroot     4096 2月   2 16:49 .git/
drwxrwxr-x  3 rootroot rootroot     4096 2月   2 16:49 .github/
-rw-rw-r--  1 rootroot rootroot      803 2月   2 16:49 .gitignore
-rw-rw-r--  1 rootroot rootroot       96 2月   2 16:49 .gitmodules
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 grammars/
-rw-rw-r--  1 rootroot rootroot     1072 2月   2 16:49 LICENSE
-rwxrwxr-x  1 rootroot rootroot  2858480 2月   2 18:00 main*
-rw-rw-r--  1 rootroot rootroot    14883 2月   2 16:49 Makefile
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 17:24 models/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 openvino/
-rw-rw-r--  1 rootroot rootroot     1776 2月   2 16:49 Package.swift
-rwxrwxr-x  1 rootroot rootroot  2805104 2月   2 18:00 quantize*
-rw-rw-r--  1 rootroot rootroot    39115 2月   2 16:49 README.md
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 samples/
-rwxrwxr-x  1 rootroot rootroot  3161376 2月   2 18:00 server*
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 spm-headers/
drwxrwxr-x  2 rootroot rootroot     4096 2月   2 16:49 tests/
-rw-rw-r--  1 rootroot rootroot   232975 2月   2 16:49 whisper.cpp
-rw-rw-r--  1 rootroot rootroot    30248 2月   2 16:49 whisper.h
-rw-rw-r--  1 rootroot rootroot   729136 2月   2 18:00 whisper.o
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ./main -l zh -osrt -m models/ggml-medium.bin chs.wav 
whisper_init_from_file_with_params_no_state: loading model from 'models/ggml-medium.bin'
whisper_model_load: loading model
whisper_model_load: n_vocab       = 51865
whisper_model_load: n_audio_ctx   = 1500
whisper_model_load: n_audio_state = 1024
whisper_model_load: n_audio_head  = 16
whisper_model_load: n_audio_layer = 24
whisper_model_load: n_text_ctx    = 448
whisper_model_load: n_text_state  = 1024
whisper_model_load: n_text_head   = 16
whisper_model_load: n_text_layer  = 24
whisper_model_load: n_mels        = 80
whisper_model_load: ftype         = 1
whisper_model_load: qntvr         = 0
whisper_model_load: type          = 4 (medium)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs       = 99
ggml_init_cublas: GGML_CUDA_FORCE_MMQ:   no
ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
ggml_init_cublas: found 1 CUDA devices:
  Device 0: NVIDIA GeForce GTX 1080, compute capability 6.1, VMM: yes
whisper_backend_init: using CUDA backend
whisper_model_load:    CUDA0 total size =  1533.52 MB (2 buffers)
whisper_model_load: model size    = 1533.14 MB
whisper_backend_init: using CUDA backend
whisper_init_state: kv self size  =  132.12 MB
whisper_init_state: kv cross size =  147.46 MB
whisper_init_state: compute buffer (conv)   =   28.00 MB
whisper_init_state: compute buffer (encode) =  187.14 MB
whisper_init_state: compute buffer (cross)  =    8.46 MB
whisper_init_state: compute buffer (decode) =  107.98 MB

system_info: n_threads = 4 / 36 | AVX = 1 | AVX2 = 1 | AVX512 = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | METAL = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | CUDA = 1 | COREML = 0 | OPENVINO = 0 | 

main: processing 'chs.wav' (6748501 samples, 421.8 sec), 4 threads, 1 processors, 5 beams + best of 5, lang = zh, task = transcribe, timestamps = 1 ...

[00:00:00.000 --> 00:00:01.400]  前段時間有個巨石恒火
[00:00:01.400 --> 00:00:03.000]  某某是男人最好的醫妹
[00:00:03.000 --> 00:00:04.760]  這裡的某某可以替換為減肥
[00:00:04.760 --> 00:00:07.720]  長髮 西裝 考研 速唱 永潔無間等等等等
[00:00:07.720 --> 00:00:09.280]  我聽到最新的一個說法是
[00:00:09.280 --> 00:00:11.960]  微分碎蓋加口罩加半框眼鏡加春風衣
[00:00:11.960 --> 00:00:13.320]  等於男人最好的醫妹
[00:00:13.320 --> 00:00:14.400]  大概也就前幾年
[00:00:14.400 --> 00:00:17.400]  春風衣還和格子襯衫並列為程序員穿搭精華
[00:00:17.400 --> 00:00:20.000]  紫紅色春風衣還被譽為廣場5大媽標配
[00:00:20.000 --> 00:00:21.600]  路透牌還是我爹這個年紀的人
[00:00:21.600 --> 00:00:22.800]  才會願意買的牌子
[00:00:22.800 --> 00:00:24.400]  不知道風向為啥變得這麼快
[00:00:24.400 --> 00:00:29.600]  為啥這東西突然變成男生逆襲神器 時尚潮流單品了後來我翻了一下小紅書就懂了
[00:00:29.600 --> 00:00:32.400]  時尚這個時期重點不在於衣服在於人
[00:00:32.400 --> 00:00:34.600]  現在小紅書上面和春風衣相關的筆記
[00:00:34.600 --> 00:00:36.200]  照片裡的男生都是這樣的
[00:00:36.200 --> 00:00:37.000]  這樣的
[00:00:37.000 --> 00:00:38.000]  還有這樣的
[00:00:38.000 --> 00:00:39.400]  你們哪裡是看穿搭的
[00:00:39.400 --> 00:00:40.600]  你們明明是看臉
[00:00:40.600 --> 00:00:41.800]  就這個造型這個年齡
[00:00:41.800 --> 00:00:44.000]  你換上老頭衫也能穿出氛圍感好嗎
[00:00:44.000 --> 00:00:46.600]  我又想起了當年郭德綱老師穿季凡西的殘劇
[00:00:46.600 --> 00:00:49.600]  這個世界對我們這些長得不好看的人還真是苛刻的
[00:00:49.600 --> 00:00:52.000]  所以說我總結了一下春風衣傳達的要領
[00:00:52.000 --> 00:00:54.200]  大概就是一張白鏡且人畜無憾的臉
[00:00:54.200 --> 00:00:56.000]  充足的發亮 纖細的體型
[00:00:56.000 --> 00:00:58.000]  當然身上的春風衣還得是駱駝的
[00:00:58.000 --> 00:01:00.000]  去年在戶外用品界最頂流的
[00:01:00.000 --> 00:01:01.000]  既不是鳥像樹
[00:01:01.000 --> 00:01:02.600]  也不是有校服之稱的北面
[00:01:02.600 --> 00:01:04.800]  或者老臺頂流哥倫比亞而是駱駝
[00:01:04.800 --> 00:01:07.000]  雙11 駱駝在天貓戶外服飾品類
[00:01:07.000 --> 00:01:08.800]  拿下銷售額和銷量雙料冠軍
[00:01:08.800 --> 00:01:10.000]  銷量達到百萬幾
[00:01:10.000 --> 00:01:10.600]  再抖音
[00:01:10.600 --> 00:01:13.200]  駱駝銷售同比增幅高達296%
[00:01:13.200 --> 00:01:16.000]  旗下主打的三合一高性價比春風衣成為爆品
[00:01:16.000 --> 00:01:18.000]  哪怕不看雙11 隨手一搜
[00:01:18.000 --> 00:01:21.000]  駱駝在春風衣的7日銷售榜上都是圖榜的存在
[00:01:21.000 --> 00:01:22.400]  這是線上的銷售表現
[00:01:22.400 --> 00:01:24.200]  至於線下還是網友總覺得好
[00:01:24.200 --> 00:01:26.800]  如今在南方街頭的駱駝比沙漠里的都多
[00:01:26.800 --> 00:01:28.400]  塔克華山 滿山的駱駝
[00:01:28.400 --> 00:01:29.800]  隨便逛個街撞山了
[00:01:29.800 --> 00:01:31.800]  至於駱駝為啥這麼火 便宜啊
[00:01:31.800 --> 00:01:33.400]  拿賣得最好的丁珍銅款
[00:01:33.400 --> 00:01:35.400]  幻影黑三合一春風衣舉個例子
[00:01:35.400 --> 00:01:37.600]  線下買標牌價格2198
[00:01:37.600 --> 00:01:39.000]  但是跑到網上看一下
[00:01:39.000 --> 00:01:40.600]  標價就變成了699
[00:01:40.600 --> 00:01:42.200]  至於折扣 日常也都是有的
[00:01:42.200 --> 00:01:45.000]  400出頭就能買到 甚至有時候能递到300價
[00:01:45.000 --> 00:01:48.200]  要是你還顯貴 駱駝還有200塊出頭的單層春風衣
[00:01:48.200 --> 00:01:49.000]  就這個價格
[00:01:49.000 --> 00:01:51.600]  哥上海恐怕還不夠兩次City Walk的報名費
[00:01:51.600 --> 00:01:54.600]  看來這個價格再對比一下北面1000塊錢起步
[00:01:54.600 --> 00:01:58.200]  你就能理解為啥北面這麼快就被大學生踢出了校服序列了
[00:01:58.200 --> 00:02:00.400]  我不知道現在大學生每個月生活費多少
[00:02:00.400 --> 00:02:02.200]  反正按照我上學時候的生活費
[00:02:02.200 --> 00:02:05.000]  一個月不吃不喝也就買得起倆袖子加一個帽子
[00:02:05.000 --> 00:02:07.400]  難怪當年全是假北面 現在都是真駱駝
[00:02:07.400 --> 00:02:08.600]  至少人家是正品啊
[00:02:08.600 --> 00:02:10.000]  我翻了一下社交媒體
[00:02:10.000 --> 00:02:13.400]  發現對駱駝的吐槽和買了駱駝的 基本上是1比1的比例
[00:02:13.400 --> 00:02:15.800]  吐槽最多的就是衣服會掉色 還會串色
[00:02:15.800 --> 00:02:18.200]  比如吐樽洗個幾次 穿個兩天就掉光了
[00:02:18.200 --> 00:02:20.600]  比如不同倉庫發的貨 質量參差不齊
[00:02:20.600 --> 00:02:22.400]  買衣服還得看戶口 聽出聲
[00:02:22.400 --> 00:02:26.400]  至於什麼做工比較差 內膽多 走線操 不防水之類的就更多
[00:02:26.400 --> 00:02:29.200]  但是這些吐槽 並不意味著會影響駱駝的銷量
[00:02:29.200 --> 00:02:31.000]  甚至還會有不少自來水表示
[00:02:31.000 --> 00:02:32.600]  就這價格 要啥子行車啊
[00:02:32.600 --> 00:02:35.400]  所謂性價比性價比 脫離價位談性能
[00:02:35.400 --> 00:02:38.600]  這就不符合消費者的需求嘛 無數次價格戰告訴我們
[00:02:38.600 --> 00:02:41.000]  只要肯降價 就沒有賣不出去的產品
[00:02:41.000 --> 00:02:43.600]  一件衝鋒衣1000多 你覺得平平無奇
[00:02:43.600 --> 00:02:46.400]  500多你覺得差點意思 200塊你就秒下單了
[00:02:46.400 --> 00:02:48.400]  到99 恐怕就要聘點手速了
[00:02:48.400 --> 00:02:50.800]  像衝鋒衣這個品類 本來價格跨度就大
[00:02:50.800 --> 00:02:53.800]  北面最便宜的GORTEX衝鋒衣 價格3000起步
[00:02:53.800 --> 00:02:56.200]  大概是同品牌最便宜衝鋒衣的三倍價格
[00:02:56.200 --> 00:03:00.000]  至於十足鳥搭載了GORTEX的硬殼起步價就要到4500
[00:03:00.000 --> 00:03:03.000]  而且同樣是GORTEX 內部也有不同的系列和檔次
[00:03:03.000 --> 00:03:05.800]  做成衣服 中間的差價恐怕就夠買兩件駱駝了
[00:03:05.800 --> 00:03:08.000]  至於智能控溫 防水拉鍊 全壓膠
[00:03:08.000 --> 00:03:09.800]  更加不可能出現在駱駝這裏了
[00:03:09.800 --> 00:03:11.800]  至少不會是三四百的駱駝身上會有的
[00:03:11.800 --> 00:03:14.200]  有的價外的衣服 買的就是一個放棄幻想
[00:03:14.200 --> 00:03:17.000]  吃到肚子裏的科技魚很活 是能給你省錢的
[00:03:17.000 --> 00:03:20.000]  穿在身上的科技魚很活 裝裝件件都是要加錢的
[00:03:20.000 --> 00:03:21.600]  所以正如羅曼羅蘭所說
[00:03:21.600 --> 00:03:23.200]  這世界上只有一種英雄主義
[00:03:23.200 --> 00:03:26.000]  就是在認清了駱駝的本質以後 依然選擇買駱駝
[00:03:26.000 --> 00:03:29.000]  關於駱駝的火爆 我有一些小小的看法 駱駝這東西
[00:03:29.000 --> 00:03:31.800]  它其實就是個潮牌 看看它的營銷方式就知道了
[00:03:31.800 --> 00:03:35.000]  現在打開小黃書 日常可以看到駱駝穿搭是這樣的
[00:03:35.000 --> 00:03:36.800]  加一點氛圍感是這樣的
[00:03:36.800 --> 00:03:40.000]  對比一下 其他品牌的風格是這樣的 這樣的
[00:03:40.000 --> 00:03:42.600]  其實對比一下就知道了 其他品牌突出一個時程
[00:03:42.600 --> 00:03:46.000]  能防風就一定要講防風 能扛洞就一定要講扛洞
[00:03:46.000 --> 00:03:49.200]  但駱駝在營銷的時候 主打的就是一個城市戶外風
[00:03:49.200 --> 00:03:52.200]  雖然造型是春風衣 但場景往往是在城市裏
[00:03:52.200 --> 00:03:55.000]  哪怕在野外也要突出一個風和日麗 陽光明媚
[00:03:55.000 --> 00:03:58.000]  至少不會在明顯的炎寒 高海拔或是惡劣氣候下
[00:03:58.000 --> 00:04:01.000]  如果用一個詞形容駱駝的營銷風格 那就是清洗
[00:04:01.000 --> 00:04:04.000]  或者說他很理解自己的消費者是誰 需要什麼產品
[00:04:04.000 --> 00:04:06.600]  從使用場景來說 駱駝的消費者買春風衣
[00:04:06.600 --> 00:04:08.800]  不是真的有什麼大風大雨要去應對
[00:04:08.800 --> 00:04:12.000]  春風衣的作用是下雨沒帶傘的時候 臨時頂個幾分鐘
[00:04:12.000 --> 00:04:13.600]  讓你能圖書館跑回宿舍
[00:04:13.600 --> 00:04:16.200]  或者是冬天騎電動車 被風吹得不行的時候
[00:04:16.200 --> 00:04:18.400]  稍微扛一下風 不至於體感太冷
[00:04:18.400 --> 00:04:21.800]  當然他們也會出門 但大部分時候也都是去別的城市
[00:04:21.800 --> 00:04:26.000]  或者在城市周邊搞搞簡單的徒步 這種情況下穿個駱駝已經夠了
[00:04:26.000 --> 00:04:29.400]  從購買動機來說 駱駝就更沒有必要上那些應和科技了
[00:04:29.400 --> 00:04:31.000]  消費者買駱駝買的是個什麼呢
[00:04:31.000 --> 00:04:33.400]  不是春風衣的功能性 而是春風衣的造型
[00:04:33.400 --> 00:04:36.400]  寬鬆的版型 能精準遮住微微隆起的小肚子
[00:04:36.400 --> 00:04:39.600]  棱角分明的質感 能隱藏一切不完美的身體線條
[00:04:39.600 --> 00:04:41.400]  顯瘦的副作用就是顯年輕
[00:04:41.400 --> 00:04:43.800]  再配上一條牛仔褲 配上一雙大黃靴
[00:04:43.800 --> 00:04:45.200]  大學生的氣質就出來了
[00:04:45.200 --> 00:04:47.800]  要是自拍的時候再配上大學宿舍洗素臺
[00:04:47.800 --> 00:04:51.800]  那永遠擦不乾淨的鏡子 瞬間青春無敵了 說的更直白一點
[00:04:51.800 --> 00:04:53.400]  人家買的是個剪輪神器
[00:04:53.400 --> 00:04:56.000]  所以說 吐槽穿駱駝都是假戶外愛好者的人
[00:04:56.000 --> 00:04:57.600]  其實並沒有理解駱駝的定位
[00:04:57.600 --> 00:04:59.900]  駱駝其實是給了想要入門山系穿搭
[00:04:59.900 --> 00:05:03.100]  想要追逐流行的人一個最平價 決策成本最低的選擇
[00:05:03.100 --> 00:05:04.900]  至於那些真正的應和戶外愛好者
[00:05:04.900 --> 00:05:07.300]  駱駝既沒有能力 也沒有打算觸打他們
[00:05:07.300 --> 00:05:09.600]  反過來說 那些自駕穿越邊疆國道
[00:05:09.600 --> 00:05:11.800]  或者去奧爾卑斯山區登山探險的人
[00:05:11.800 --> 00:05:16.600]  也不太可能在戶外服飾上省錢 畢竟光是交通住宿 請假出行 成本就不低了
[00:05:16.600 --> 00:05:19.100]  對他們來說 戶外裝備很多時候是保命用的
[00:05:19.100 --> 00:05:21.100]  也就不存在跟風奧造型的必要了
[00:05:21.100 --> 00:05:23.400]  最後我再說個題外話 年輕人追捧駱駝
[00:05:23.400 --> 00:05:25.900]  一個隱藏的原因 其實是羽絨服越來越貴了
[00:05:25.900 --> 00:05:30.000]  有媒體統計 現在國產羽絨服的平均售價已經高達881元
[00:05:30.000 --> 00:05:32.000]  波斯登軍價最高 接近2000元
[00:05:32.000 --> 00:05:34.900]  而且過去幾年 國產羽絨服品牌都在轉向高端化
[00:05:34.900 --> 00:05:37.100]  羽絨服市場分為8000元以上的奢侈級
[00:05:37.100 --> 00:05:41.300]  2000元以下的大重級 而在中間的高端級 國產品牌一直沒有存在感
[00:05:41.300 --> 00:05:43.600]  所以過去幾年 波斯登 天工人這些品牌
[00:05:43.600 --> 00:05:46.700]  都把2000元到8000元這個市場當成未來的發展趨勢
[00:05:46.700 --> 00:05:49.600]  東新證券研報顯示 從2018到2021年
[00:05:49.600 --> 00:05:52.200]  波斯登軍價四年漲幅達到60%以上
[00:05:52.200 --> 00:05:56.000]  過去五個菜年 這個品牌的營銷開支從20多億漲到了60多億
[00:05:56.000 --> 00:06:00.400]  羽絨服價格往上走 年輕消費者就開始拋棄羽絨服 購買平價衝鋒衣
[00:06:00.400 --> 00:06:03.400]  裡面再穿個普通價外的瑤麗絨或者羽絨小夾克
[00:06:03.400 --> 00:06:07.000]  也不比大幾千的羽絨服差多少 說到底 現在消費是會發達的
[00:06:07.000 --> 00:06:09.700]  沒有什麼需求是一定要某種特定的解決方案
[00:06:09.700 --> 00:06:11.600]  特定價位的商品才能實現的
[00:06:11.600 --> 00:06:15.200]  要保暖 羽絨服固然很好 但春風衣加一些內搭也很暖和
[00:06:15.200 --> 00:06:18.000]  要時尚 大幾千塊錢的設計師品牌非常不錯
[00:06:18.000 --> 00:06:20.700]  但350的拼多多服飾搭的好也能出彩
[00:06:20.700 --> 00:06:23.100]  要去野外徒步 花五六千買鳥也可以
[00:06:23.100 --> 00:06:25.200]  但迪卡儂也足以應付大多數狀況
[00:06:25.200 --> 00:06:27.600]  所以說 花高價買春風衣當然也OK
[00:06:27.600 --> 00:06:29.800]  三四百買件駱駝也是可以接受的選擇
[00:06:29.800 --> 00:06:33.800]  駱駝也多多少少有一些功能性 畢竟它再怎麼樣還是個春風衣
[00:06:33.800 --> 00:06:36.800]  理解了這個事情就很容易分辨什麼是智商稅的
[00:06:36.800 --> 00:06:38.900]  那些向你灌輸非某個品牌不用
[00:06:38.900 --> 00:06:41.500]  告訴你某個需求只有某個產品才能滿足
[00:06:41.500 --> 00:06:44.400]  某個品牌就是某個品類絕對的鄙視鏈頂端
[00:06:44.400 --> 00:06:46.900]  這類營銷的智商稅含量必然是很高的
[00:06:46.900 --> 00:06:48.900]  它的目的是剝奪你選擇的權利
[00:06:48.900 --> 00:06:51.300]  讓你主動放棄比價和尋找平梯的想法
[00:06:51.300 --> 00:06:53.100]  從而避免與其他品牌競爭
[00:06:53.100 --> 00:06:56.300]  而沒有競爭的市場才是智商稅含量最高的市場
[00:06:56.300 --> 00:06:59.900]  消費商業洞穴禁在IC實驗室 我是館長 我們下期再見
[00:06:59.900 --> 00:07:01.900]  謝謝收看!

output_srt: saving output to 'chs.wav.srt'

whisper_print_timings:     load time =   841.23 ms
whisper_print_timings:     fallbacks =   1 p /   0 h
whisper_print_timings:      mel time =   440.91 ms
whisper_print_timings:   sample time = 13100.71 ms / 17724 runs (    0.74 ms per run)
whisper_print_timings:   encode time =  4078.38 ms /    18 runs (  226.58 ms per run)
whisper_print_timings:   decode time =    40.70 ms /     2 runs (   20.35 ms per run)
whisper_print_timings:   batchd time = 155882.95 ms / 17702 runs (    8.81 ms per run)
whisper_print_timings:   prompt time =  3419.58 ms /  3632 runs (    0.94 ms per run)
whisper_print_timings:    total time = 177848.30 ms
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ./main -l zh -osrt -m models/g
generate-coreml-interface.sh  generate-coreml-model.sh      ggml-base.en.bin              ggml-large-v3.bin             ggml-medium.bin               ggml_to_pt.py                 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ./main -l zh -osrt -m models/ggml
ggml-base.en.bin   ggml-large-v3.bin  ggml-medium.bin    ggml_to_pt.py      
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ./main -l zh -osrt -m models/ggml-large-v3.bin chs.wav
whisper_init_from_file_with_params_no_state: loading model from 'models/ggml-large-v3.bin'
whisper_model_load: loading model
whisper_model_load: n_vocab       = 51866
whisper_model_load: n_audio_ctx   = 1500
whisper_model_load: n_audio_state = 1280
whisper_model_load: n_audio_head  = 20
whisper_model_load: n_audio_layer = 32
whisper_model_load: n_text_ctx    = 448
whisper_model_load: n_text_state  = 1280
whisper_model_load: n_text_head   = 20
whisper_model_load: n_text_layer  = 32
whisper_model_load: n_mels        = 128
whisper_model_load: ftype         = 1
whisper_model_load: qntvr         = 0
whisper_model_load: type          = 5 (large v3)
whisper_model_load: adding 1609 extra tokens
whisper_model_load: n_langs       = 100
ggml_init_cublas: GGML_CUDA_FORCE_MMQ:   no
ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
ggml_init_cublas: found 1 CUDA devices:
  Device 0: NVIDIA GeForce GTX 1080, compute capability 6.1, VMM: yes
whisper_backend_init: using CUDA backend
whisper_model_load:    CUDA0 total size =  3094.86 MB (3 buffers)
whisper_model_load: model size    = 3094.36 MB
whisper_backend_init: using CUDA backend
whisper_init_state: kv self size  =  220.20 MB
whisper_init_state: kv cross size =  245.76 MB
whisper_init_state: compute buffer (conv)   =   35.50 MB
whisper_init_state: compute buffer (encode) =  233.50 MB
whisper_init_state: compute buffer (cross)  =   10.15 MB
whisper_init_state: compute buffer (decode) =  108.99 MB

system_info: n_threads = 4 / 36 | AVX = 1 | AVX2 = 1 | AVX512 = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | METAL = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | CUDA = 1 | COREML = 0 | OPENVINO = 0 | 

main: processing 'chs.wav' (6748501 samples, 421.8 sec), 4 threads, 1 processors, 5 beams + best of 5, lang = zh, task = transcribe, timestamps = 1 ...

[00:00:00.040 --> 00:00:01.460]  前段时间有个巨石横火
[00:00:01.460 --> 00:00:02.860]  某某是男人最好的衣媒
[00:00:02.860 --> 00:00:04.800]  这里的某某可以替换为减肥
[00:00:04.800 --> 00:00:07.620]  长发 西装 考研 书唱 永结无间等等等等
[00:00:07.620 --> 00:00:09.320]  我听到最新的一个说法是
[00:00:09.320 --> 00:00:11.940]  微分碎盖加口罩加半框眼镜加冲锋衣
[00:00:11.940 --> 00:00:13.440]  等于男人最好的衣媒
[00:00:13.440 --> 00:00:14.420]  大概也就前几年
[00:00:14.420 --> 00:00:17.560]  冲锋衣还和格子衬衫并列为程序员穿搭精华
[00:00:17.560 --> 00:00:19.940]  紫红色冲锋衣还被誉为广场舞达妈标配
[00:00:19.940 --> 00:00:22.700]  骆驼牌还是我爹这个年纪的人才会愿意买的牌子
[00:00:22.700 --> 00:00:24.380]  不知道风向为啥变得这么快
[00:00:24.380 --> 00:00:26.680]  为啥这东西突然变成男生逆袭神器
[00:00:26.680 --> 00:00:27.660]  时尚潮流单品
[00:00:27.660 --> 00:00:29.580]  后来我翻了一下小红书就懂了
[00:00:29.580 --> 00:00:30.460]  时尚这个时期
[00:00:30.460 --> 00:00:31.620]  重点不在于衣服
[00:00:31.620 --> 00:00:32.160]  在于人
[00:00:32.160 --> 00:00:34.500]  现在小红书上面和冲锋衣相关的笔记
[00:00:34.500 --> 00:00:36.220]  照片里的男生都是这样的
[00:00:36.220 --> 00:00:36.880]  这样的
[00:00:36.880 --> 00:00:38.140]  还有这样的
[00:00:38.140 --> 00:00:39.460]  你们哪里是看穿搭的
[00:00:39.460 --> 00:00:40.540]  你们明明是看脸
[00:00:40.540 --> 00:00:41.780]  就这个造型这个年龄
[00:00:41.780 --> 00:00:43.920]  你换上老头衫也能穿出氛围感好吗
[00:00:43.920 --> 00:00:46.560]  我又想起了当年郭德纲老师穿计繁西的残剧
[00:00:46.560 --> 00:00:48.560]  这个世界对我们这些长得不好看的人
[00:00:48.560 --> 00:00:49.480]  还真是苛刻呢
[00:00:49.480 --> 00:00:52.100]  所以说我总结了一下冲锋衣传达的要领
[00:00:52.100 --> 00:00:54.200]  大概就是一张白净且人畜无汉的脸
[00:00:54.200 --> 00:00:55.120]  充足的发量
[00:00:55.120 --> 00:00:55.980]  纤细的体型
[00:00:55.980 --> 00:00:58.160]  当然身上的冲锋衣还得是骆驼的
[00:00:58.160 --> 00:00:59.320]  去年在户外用品界
[00:00:59.320 --> 00:01:01.100]  最顶流的既不是鸟像书
[00:01:01.100 --> 00:01:02.560]  也不是有校服之称的北面
[00:01:02.560 --> 00:01:04.120]  或者老台顶流哥伦比亚
[00:01:04.120 --> 00:01:04.800]  而是骆驼
[00:01:04.800 --> 00:01:06.980]  双十一骆驼在天猫户外服饰品类
[00:01:06.980 --> 00:01:08.860]  拿下销售额和销量双料冠军
[00:01:08.860 --> 00:01:09.980]  销量达到百万级
[00:01:09.980 --> 00:01:10.620]  在抖音
[00:01:10.620 --> 00:01:13.200]  骆驼销售同比增幅高达百分之296
[00:01:13.200 --> 00:01:15.920]  旗下主打的三合一高性价比冲锋衣成为爆品
[00:01:15.920 --> 00:01:17.260]  哪怕不看双十一
[00:01:17.260 --> 00:01:18.020]  随手一搜
[00:01:18.020 --> 00:01:21.040]  骆驼在冲锋衣的七日销售榜上都是图榜的存在
[00:01:21.040 --> 00:01:22.480]  这是线上的销售表现
[00:01:22.480 --> 00:01:24.200]  至于线下还是网友总结的好
[00:01:24.200 --> 00:01:26.740]  如今在南方街头的骆驼比沙漠里的都多
[00:01:26.740 --> 00:01:27.540]  爬个华山
[00:01:27.540 --> 00:01:28.320]  满山的骆驼
[00:01:28.320 --> 00:01:29.840]  随便逛个街撞山了
[00:01:29.840 --> 00:01:31.060]  至于骆驼为啥这么火
[00:01:31.060 --> 00:01:31.800]  便宜啊
[00:01:31.800 --> 00:01:33.400]  拿卖的最好的丁真同款
[00:01:33.400 --> 00:01:35.500]  幻影黑三合一冲锋衣举个例子
[00:01:35.500 --> 00:01:36.000]  线下买
[00:01:36.000 --> 00:01:37.440]  标牌价格2198
[00:01:37.440 --> 00:01:38.940]  但是跑到网上看一下
[00:01:38.940 --> 00:01:40.460]  标价就变成了699
[00:01:40.460 --> 00:01:41.220]  至于折扣
[00:01:41.220 --> 00:01:42.360]  日常也都是有的
[00:01:42.360 --> 00:01:43.440]  400出头就能买到
[00:01:43.440 --> 00:01:44.960]  甚至有时候能低到300价
[00:01:44.960 --> 00:01:46.140]  要是你还嫌贵
[00:01:46.140 --> 00:01:48.200]  路头还有200块出头的单层冲锋衣
[00:01:48.200 --> 00:01:49.080]  就这个价格
[00:01:49.080 --> 00:01:51.520]  搁上海恐怕还不够两次CityWalk的报名费
[00:01:51.520 --> 00:01:52.560]  看了这个价格
[00:01:52.560 --> 00:01:53.560]  再对比一下北面
[00:01:53.560 --> 00:01:54.640]  1000块钱起步
[00:01:54.640 --> 00:01:56.000]  你就能理解为啥北面
[00:01:56.000 --> 00:01:58.120]  这么快就被大学生踢出了校服序列了
[00:01:58.120 --> 00:02:00.380]  我不知道现在大学生每个月生活费多少
[00:02:00.380 --> 00:02:02.160]  反正按照我上学时候的生活费
[00:02:02.160 --> 00:02:03.200]  一个月不吃不喝
[00:02:03.200 --> 00:02:05.080]  也就买得起俩袖子加一个帽子
[00:02:05.080 --> 00:02:06.420]  难怪当年全是假北面
[00:02:06.420 --> 00:02:07.400]  现在都是真路头
[00:02:07.400 --> 00:02:08.640]  至少人家是正品啊
[00:02:08.640 --> 00:02:10.080]  我翻了一下社交媒体
[00:02:10.080 --> 00:02:12.060]  发现对路头的吐槽和买了路头的
[00:02:12.060 --> 00:02:13.340]  基本上是1比1的比例
[00:02:13.340 --> 00:02:15.040]  吐槽最多的就是衣服会掉色
[00:02:15.040 --> 00:02:15.960]  还会串色
[00:02:15.960 --> 00:02:17.100]  比如图增洗个几次
[00:02:17.100 --> 00:02:18.240]  穿个两天就掉光了
[00:02:18.240 --> 00:02:19.600]  比如不同仓库发的货
[00:02:19.600 --> 00:02:20.600]  质量参差不齐
[00:02:20.600 --> 00:02:22.300]  买衣服还得看户口拼出身
[00:02:22.300 --> 00:02:23.660]  至于什么做工比较差
[00:02:23.660 --> 00:02:24.300]  内胆多
[00:02:24.300 --> 00:02:24.880]  走线糙
[00:02:24.880 --> 00:02:26.380]  不防水之类的就更多了
[00:02:26.380 --> 00:02:27.360]  但是这些吐槽
[00:02:27.360 --> 00:02:29.160]  并不意味着会影响路头的销量
[00:02:29.160 --> 00:02:30.820]  甚至还会有不少自来水表示
[00:02:30.820 --> 00:02:32.680]  就这价格要啥自行车啊
[00:02:32.680 --> 00:02:34.080]  所谓性价比性价比
[00:02:34.080 --> 00:02:35.340]  脱离价位谈性能
[00:02:35.340 --> 00:02:36.980]  这就不符合消费者的需求嘛
[00:02:36.980 --> 00:02:38.480]  无数次价格战告诉我们
[00:02:38.480 --> 00:02:39.500]  只要肯降价
[00:02:39.500 --> 00:02:40.960]  就没有卖不出去的产品
[00:02:40.960 --> 00:02:41.820]  一件冲锋衣
[00:02:41.820 --> 00:02:43.500]  1000多你觉得平平无奇
[00:02:43.500 --> 00:02:44.900]  500多你觉得差点意思
[00:02:44.900 --> 00:02:46.480]  200块你就要秒下单了
[00:02:46.480 --> 00:02:48.520]  到99恐怕就要拼点手速了
[00:02:48.520 --> 00:02:49.560]  像冲锋衣这个品类
[00:02:49.560 --> 00:02:50.720]  本来价格跨度就大
[00:02:50.720 --> 00:02:52.660]  北面最便宜的Gortex冲锋衣
[00:02:52.660 --> 00:02:53.740]  价格3000起步
[00:02:53.740 --> 00:02:56.360]  大概是同品牌最便宜冲锋衣的三倍价格
[00:02:56.360 --> 00:02:57.060]  至于十足鸟
[00:02:57.060 --> 00:02:59.020]  搭载了Gortex的硬壳起步价
[00:02:59.020 --> 00:02:59.780]  就要到4500
[00:02:59.780 --> 00:03:01.080]  而且同样是Gortex
[00:03:01.080 --> 00:03:02.860]  内部也有不同的系列和档次
[00:03:02.860 --> 00:03:03.520]  做成衣服
[00:03:03.520 --> 00:03:05.780]  中间的差价恐怕就够买两件骆驼了
[00:03:05.780 --> 00:03:06.620]  至于智能控温
[00:03:06.620 --> 00:03:07.320]  防水拉链
[00:03:07.320 --> 00:03:07.900]  全压胶
[00:03:07.900 --> 00:03:09.760]  更加不可能出现在骆驼这里了
[00:03:09.760 --> 00:03:11.780]  至少不会是三四百的骆驼身上会有的
[00:03:11.780 --> 00:03:12.660]  有的价外的衣服
[00:03:12.660 --> 00:03:14.040]  买的就是一个放弃幻想
[00:03:14.040 --> 00:03:15.660]  吃到肚子里的科技鱼很活
[00:03:15.660 --> 00:03:16.840]  是能给你省钱的
[00:03:16.840 --> 00:03:18.320]  穿在身上的科技鱼很活
[00:03:18.320 --> 00:03:20.040]  装装件件都是要加钱的
[00:03:20.040 --> 00:03:21.440]  所以正如罗曼罗兰所说
[00:03:21.440 --> 00:03:23.040]  这世界上只有一种英雄主义
[00:03:23.040 --> 00:03:24.860]  就是在认清了骆驼的本质以后
[00:03:24.860 --> 00:03:26.060]  依然选择买骆驼
[00:03:26.060 --> 00:03:26.900]  关于骆驼的火爆
[00:03:26.900 --> 00:03:28.180]  我有一些小小的看法
[00:03:28.180 --> 00:03:28.960]  骆驼这个东西
[00:03:28.960 --> 00:03:30.220]  它其实就是个潮牌
[00:03:30.220 --> 00:03:31.940]  看看它的营销方式就知道了
[00:03:31.940 --> 00:03:32.920]  现在打开小红书
[00:03:32.920 --> 00:03:35.120]  日常可以看到骆驼穿搭是这样的
[00:03:35.120 --> 00:03:36.900]  加一点氛围感是这样的
[00:03:36.900 --> 00:03:37.400]  对比一下
[00:03:37.400 --> 00:03:39.240]  其他品牌的风格是这样的
[00:03:39.240 --> 00:03:40.020]  这样的
[00:03:40.020 --> 00:03:41.280]  其实对比一下就知道了
[00:03:41.280 --> 00:03:42.600]  其他品牌突出一个时程
[00:03:42.600 --> 00:03:44.240]  能防风就一定要讲防风
[00:03:44.240 --> 00:03:45.960]  能扛冻就一定要讲扛冻
[00:03:45.960 --> 00:03:47.340]  但骆驼在营销的时候
[00:03:47.340 --> 00:03:49.080]  主打的就是一个城市户外风
[00:03:49.080 --> 00:03:50.440]  虽然造型是春风衣
[00:03:50.440 --> 00:03:52.180]  但场景往往是在城市里
[00:03:52.180 --> 00:03:54.220]  哪怕在野外也要突出一个风和日丽
[00:03:54.220 --> 00:03:54.940]  阳光敏媚
[00:03:54.940 --> 00:03:56.500]  至少不会在明显的严寒
[00:03:56.500 --> 00:03:58.020]  高海拔或是恶劣气候下
[00:03:58.020 --> 00:04:00.160]  如果用一个词形容骆驼的营销风格
[00:04:00.160 --> 00:04:00.920]  那就是清洗
[00:04:00.920 --> 00:04:03.060]  或者说他很理解自己的消费者是谁
[00:04:03.060 --> 00:04:03.920]  需要什么产品
[00:04:03.920 --> 00:04:05.260]  从使用场景来说
[00:04:05.260 --> 00:04:06.600]  骆驼的消费者买春风衣
[00:04:06.600 --> 00:04:08.640]  不是真的有什么大风大雨要去应对
[00:04:08.640 --> 00:04:10.880]  春风衣的作用是下雨没带伞的时候
[00:04:10.880 --> 00:04:12.160]  临时顶个几分钟
[00:04:12.160 --> 00:04:13.700]  让你能图书馆跑回宿舍
[00:04:13.700 --> 00:04:14.940]  或者是冬天骑电动车
[00:04:14.940 --> 00:04:16.220]  被风吹得不行的时候
[00:04:16.220 --> 00:04:17.200]  稍微扛一下风
[00:04:17.200 --> 00:04:18.340]  不至于体感太冷
[00:04:18.340 --> 00:04:19.700]  当然他们也会出门
[00:04:19.700 --> 00:04:21.780]  但大部分时候也都是去别的城市
[00:04:21.780 --> 00:04:23.860]  或者在城市周边搞搞简单的徒步
[00:04:23.860 --> 00:04:24.920]  这种情况下
[00:04:24.920 --> 00:04:25.920]  穿个骆驼也就够了
[00:04:25.920 --> 00:04:27.220]  从购买动机来说
[00:04:27.220 --> 00:04:29.260]  骆驼就更没有必要上那些硬核科技了
[00:04:29.260 --> 00:04:30.920]  消费者买骆驼买的是个什么呢
[00:04:30.920 --> 00:04:32.240]  不是春风衣的功能性
[00:04:32.240 --> 00:04:33.380]  而是春风衣的造型
[00:04:33.380 --> 00:04:34.340]  宽松的版型
[00:04:34.340 --> 00:04:36.380]  能精准遮住微微隆起的小肚子
[00:04:36.380 --> 00:04:37.440]  棱角分明的质感
[00:04:37.440 --> 00:04:39.420]  能隐藏一切不完美的整体线条
[00:04:39.420 --> 00:04:41.260]  显瘦的副作用就是显年轻
[00:04:41.260 --> 00:04:42.600]  再配上一条牛仔裤
[00:04:42.600 --> 00:04:43.680]  配上一双大黄靴
[00:04:43.680 --> 00:04:45.100]  大学生的气质就出来了
[00:04:45.100 --> 00:04:47.700]  要是自拍的时候再配上大学宿舍洗漱台
[00:04:47.700 --> 00:04:49.380]  那永远擦不干净的镜子
[00:04:49.380 --> 00:04:50.840]  瞬间青春无敌了
[00:04:50.840 --> 00:04:51.700]  说的更直白一点
[00:04:51.700 --> 00:04:53.060]  人家买的是个锦铃神器
[00:04:53.060 --> 00:04:53.820]  所以说
[00:04:53.820 --> 00:04:55.860]  吐槽穿骆驼都是假户外爱好者的人
[00:04:55.860 --> 00:04:57.460]  其实并没有理解骆驼的定位
[00:04:57.460 --> 00:04:59.780]  骆驼其实是给了想要入门山系穿搭
[00:04:59.780 --> 00:05:01.740]  想要追逐流行的人一个最平价
[00:05:01.740 --> 00:05:02.980]  决策成本最低的选择
[00:05:02.980 --> 00:05:04.880]  至于那些真正的硬核户外爱好者
[00:05:04.880 --> 00:05:05.800]  骆驼既没有能力
[00:05:05.800 --> 00:05:07.080]  也没有打算触打他们
[00:05:07.080 --> 00:05:07.980]  反过来说
[00:05:07.980 --> 00:05:09.460]  那些自驾穿越边疆国道
[00:05:09.460 --> 00:05:11.680]  或者去阿尔卑斯山区登山探险的人
[00:05:11.680 --> 00:05:13.540]  也不太可能在户外服饰上省钱
[00:05:13.540 --> 00:05:14.900]  毕竟光是交通住宿
[00:05:14.900 --> 00:05:15.600]  请假出行
[00:05:15.600 --> 00:05:16.560]  成本就不低了
[00:05:16.560 --> 00:05:17.320]  对他们来说
[00:05:17.320 --> 00:05:19.140]  户外装备很多时候是保命用的
[00:05:19.140 --> 00:05:21.180]  也就不存在跟风凹造型的必要了
[00:05:21.180 --> 00:05:22.300]  最后我再说个题外话
[00:05:22.300 --> 00:05:23.320]  年轻人追捧骆驼
[00:05:23.320 --> 00:05:24.240]  一个隐藏的原因
[00:05:24.240 --> 00:05:25.940]  其实是羽绒服越来越贵了
[00:05:25.940 --> 00:05:26.620]  有媒体统计
[00:05:26.620 --> 00:05:28.440]  现在国产羽绒服的平均售价
[00:05:28.440 --> 00:05:29.880]  已经高达881元
[00:05:29.880 --> 00:05:31.140]  波斯灯均价最高
[00:05:31.140 --> 00:05:31.900]  接近2000元
[00:05:31.900 --> 00:05:32.880]  而且过去几年
[00:05:32.880 --> 00:05:34.800]  国产羽绒服品牌都在转向高端化
[00:05:34.800 --> 00:05:37.060]  羽绒服市场分为8000元以上的奢侈级
[00:05:37.060 --> 00:05:38.440]  2000元以下的大众级
[00:05:38.440 --> 00:05:39.740]  而在中间的高端级
[00:05:39.740 --> 00:05:41.220]  国产品牌一直没有存在感
[00:05:41.220 --> 00:05:42.140]  所以过去几年
[00:05:42.140 --> 00:05:43.520]  波斯灯天空人这些品牌
[00:05:43.520 --> 00:05:45.260]  都把2000元到8000元这个市场
[00:05:45.260 --> 00:05:46.560]  当成未来的发展趋势
[00:05:46.560 --> 00:05:47.980]  东芯证券研报显示
[00:05:47.980 --> 00:05:49.600]  从2018到2021年
[00:05:49.600 --> 00:05:52.080]  波斯灯均价4年涨幅达到60%以上
[00:05:52.080 --> 00:05:53.080]  过去5个财年
[00:05:53.080 --> 00:05:54.300]  这个品牌的营销开支
[00:05:54.300 --> 00:05:56.020]  从20多亿涨到了60多亿
[00:05:56.020 --> 00:05:57.240]  羽绒服价格往上走
[00:05:57.240 --> 00:05:59.160]  年轻消费者就开始抛弃羽绒服
[00:05:59.160 --> 00:06:00.300]  购买平价春风衣
[00:06:00.300 --> 00:06:02.240]  里面再穿个普通价位的摇篱绒
[00:06:02.240 --> 00:06:03.280]  或者羽绒小夹克
[00:06:03.280 --> 00:06:05.100]  也不比大几千的羽绒服差多少
[00:06:05.100 --> 00:06:05.740]  说到底
[00:06:05.740 --> 00:06:07.120]  现在消费社会发达了
[00:06:07.120 --> 00:06:08.300]  没有什么需求是一定要
[00:06:08.300 --> 00:06:09.740]  某种特定的解决方案
[00:06:09.740 --> 00:06:11.500]  特定价位的商品才能实现的
[00:06:11.500 --> 00:06:12.080]  要保暖
[00:06:12.080 --> 00:06:13.140]  羽绒服固然很好
[00:06:13.140 --> 00:06:15.320]  但春风衣加一些内搭也很暖和
[00:06:15.320 --> 00:06:15.820]  要时尚
[00:06:15.820 --> 00:06:17.860]  大几千块钱的设计师品牌非常不错
[00:06:17.860 --> 00:06:19.360]  但350的拼多多服饰
[00:06:19.360 --> 00:06:20.520]  搭得好也能出产
[00:06:20.520 --> 00:06:21.620]  要去野外徒步
[00:06:21.620 --> 00:06:22.940]  花五六千买鸟也可以
[00:06:22.940 --> 00:06:25.100]  但迪卡侬也足以应付大多数状况
[00:06:25.100 --> 00:06:25.720]  所以说
[00:06:25.720 --> 00:06:27.420]  花高价买春风衣当然也OK
[00:06:27.420 --> 00:06:28.540]  三四百买件骆驼
[00:06:28.540 --> 00:06:29.880]  也是可以介绍的选择
[00:06:29.880 --> 00:06:31.900]  何况骆驼也多多少少有一些功能性
[00:06:31.900 --> 00:06:32.840]  毕竟它再怎么样
[00:06:32.840 --> 00:06:33.920]  还是个春风衣
[00:06:33.920 --> 00:06:34.800]  理解了这个事情
[00:06:34.800 --> 00:06:35.740]  就很容易分辨
[00:06:35.740 --> 00:06:36.900]  什么是智商税的
[00:06:36.900 --> 00:06:38.740]  那些向你灌输非某个品牌不用
[00:06:38.740 --> 00:06:39.880]  告诉你某个需求
[00:06:39.880 --> 00:06:41.380]  只有某个产品才能满足
[00:06:41.380 --> 00:06:42.160]  某个品牌
[00:06:42.160 --> 00:06:44.220]  就是某个品类绝对的鄙视链顶端
[00:06:44.220 --> 00:06:45.900]  这类营销的智商税含量
[00:06:45.900 --> 00:06:46.860]  必然是很高的
[00:06:46.860 --> 00:06:48.780]  它的目的是剥夺你选择的权利
[00:06:48.780 --> 00:06:51.220]  让你主动放弃比价和寻找平梯的想法
[00:06:51.220 --> 00:06:52.920]  从而避免与其他品牌竞争
[00:06:52.920 --> 00:06:54.280]  而没有竞争的市场
[00:06:54.280 --> 00:06:56.020]  才是智商税含量最高的市场
[00:06:56.020 --> 00:06:57.360]  消费商业洞见
[00:06:57.360 --> 00:06:58.420]  近在IC实验室
[00:06:58.420 --> 00:06:59.000]  我是馆长
[00:06:59.000 --> 00:06:59.840]  我们下期再见
[00:06:59.840 --> 00:07:01.840]  谢谢大家!

output_srt: saving output to 'chs.wav.srt'

whisper_print_timings:     load time =  1232.24 ms
whisper_print_timings:     fallbacks =   1 p /   0 h
whisper_print_timings:      mel time =   507.42 ms
whisper_print_timings:   sample time = 14211.34 ms / 19337 runs (    0.73 ms per run)
whisper_print_timings:   encode time =  9234.67 ms /    19 runs (  486.04 ms per run)
whisper_print_timings:   decode time =    41.85 ms /     2 runs (   20.92 ms per run)
whisper_print_timings:   batchd time = 325320.62 ms / 19329 runs (   16.83 ms per run)
whisper_print_timings:   prompt time =  5857.69 ms /  3869 runs (    1.51 ms per run)
whisper_print_timings:    total time = 356447.78 ms
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ 
rootroot@rootroot-X99-Turbo:~/whisper.cpp$ ./main -l zh -osrt -m models/ggml-large-v3.bin chs.wavConnection closing...Socket close.

Connection closed by foreign host.

Disconnected from remote host(rootroot192.168.186.230) at 18:34:03.

Type `help' to learn how to use Xshell prompt.

[END] 2024/2/2 19:43:47