whisper large-v3 模型文件下载链接

#源码里找到的

_MODELS = {
    "tiny.en": "https://openaipublic.azureedge.net/main/whisper/models/d3dd57d32accea0b295c96e26691aa14d8822fac7d9d27d5dc00b4ca2826dd03/tiny.en.pt",
    "tiny": "https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt",
    "base.en": "https://openaipublic.azureedge.net/main/whisper/models/25a8566e1d0c1e2231d1c762132cd20e0f96a85d16145c3a00adf5d1ac670ead/base.en.pt",
    "base": "https://openaipublic.azureedge.net/main/whisper/models/ed3a0b6b1c0edf879ad9b11b1af5a0e6ab5db9205f891f668f8b0e6c6326e34e/base.pt",
    "small.en": "https://openaipublic.azureedge.net/main/whisper/models/f953ad0fd29cacd07d5a9eda5624af0f6bcf2258be67c92b79389873d91e0872/small.en.pt",
    "small": "https://openaipublic.azureedge.net/main/whisper/models/9ecf779972d90ba49c06d968637d720dd632c55bbf19d441fb42bf17a411e794/small.pt",
    "medium.en": "https://openaipublic.azureedge.net/main/whisper/models/d7440d1dc186f76616474e0ff0b3b6b879abc9d1a4926b7adfa41db2d497ab4f/medium.en.pt",
    "medium": "https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt",
    "large-v1": "https://openaipublic.azureedge.net/main/whisper/models/e4b87e7e0bf463eb8e6956e646f1e277e901512310def2c24bf0e11bd3c28e9a/large-v1.pt",
    "large-v2": "https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt",
    "large-v3": "https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt",
    "large": "https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt",
}

加速下载

aria2c -x 16 https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt --all-proxy=http://host.docker.internal:7890

我这是在容器里用代理,代理选项可去除

这是gpt4给我的代码:

我想写一个python程序,在我发出“过”的语音时,打印“过”(实际上是执行某种操作,我会将它嵌入到其他程序中,目前只打印字符串),在我发出“下一个”的语音时,打印“下一个”,我想使用https://huggingface.co/openai/whisper-large-v3实现

import whisper
import sounddevice as sd
import numpy as np

# 录音设置
duration = 5  # 录音时长(秒)
samplerate = 16000  # 采样率


def record_audio(duration, samplerate):
    """录制音频"""
    recording = sd.rec(
        int(duration * samplerate), samplerate=samplerate, channels=1, dtype="float32"
    )
    sd.wait()
    return recording


def transcribe_audio(audio, model):
    """使用Whisper模型转录音频"""
    audio = np.squeeze(audio)  # 确保音频是一维的
    result = model.transcribe(audio)
    return result["text"]


def main():
    # 加载Whisper模型
    model = whisper.load_model("large-v3")

    while True:
        print("开始录音...")
        audio = record_audio(duration, samplerate)
        print("录音结束,正在识别...")

        # 识别语音
        text = transcribe_audio(audio, model)

        # 根据识别结果执行操作
        if "过" in text:
            print("过")
        elif "下一个" in text:
            print("下一个")
        else:
            print("未识别到指令")
            print(text)


if __name__ == "__main__":
    main()

你可能感兴趣的:(whisper,large-v3,openai,语音识别)