TOOLS_Python标记和保留非静音段的方法实现

基于静音段识别，实现两个方法：
1.将非静音段的起始时间输出；
2.将其余非静音段合并导出；

import os
from pydub import AudioSegment
from pydub.silence import split_on_silence, detect_silence

def tag_nosilence_vocals_by_detect_silence(filePath):
    """
        标记出非静音段干声
        只支持mp3格式
        
        返回：
            嵌套非静音段开始和结束时间（毫秒级）的数组
    """
    sound = AudioSegment.from_mp3(filePath)   
    print(sound.dBFS, sound.duration_seconds)
    
    chunks = detect_silence(sound,
        min_silence_len=1500,     
        silence_thresh=-60,
    )
    nosilence_list = []
    tag_chunk = None
    for i, chunk in enumerate(chunks):  
        if tag_chunk is None:
            c_nosilence_list = [0,chunk[0]]
        else:
            c_nosilence_list = [tag_chunk[1],chunk[0]]
        tag_chunk = chunk
        nosilence_list.append(c_nosilence_list)
        if i == len(chunks):
            c_nosilence_list = [tag_chunk[1],len(sound)]
            nosilence_list.append(c_nosilence_list)

    return [item for item in nosilence_list if item[1] - item[0] > 1000]


def merge_nosilence_vocals_by_split_on_silence(srcFilePath,tgtFilePath):
    """
        合并非静音段干声
        只支持mp3格式
        
        返回：
            合并后的音频（mp3）路径（若合并结果入校和返回None）
    """
    sound = AudioSegment.from_mp3(srcFilePath)   
    print(sound.dBFS, sound.duration_seconds)

    chunks = split_on_silence(sound,
        min_silence_len=1500,     
        silence_thresh=-60,
        keep_silence=100     
    )
    sum_u=sound[:1] 
    for i, chunk in enumerate(chunks):   
        sum_u=sum_u+chunk        
    sum_u.export(Path(tgtFilePath), format="mp3")
    
    if len(sum_u) > 1500:
        return tgtFilePath