语音转文本的pyhton程序

以下是一个简单的Python程序，可以将音频文件中的语音转换为文本：

1. 首先，需要安装SpeechRecognition模块。可以使用pip命令来安装。在命令行中输入以下命令：

`pip install SpeechRecognition`

2. 导入SpeechRecognition模块和AudioFile模块

   import speech_recognition as sr
   from pydub import AudioSegment
   from pydub.silence import split_on_silence

3. 定义一个函数，将音频文件分割为小段，以便于识别。这里使用了pydub库中的split_on_silence函数，将音频文件根据静音部分分割成多个小段。

   def get_large_audio_transcription(path):
       r = sr.Recognizer()
       sound = AudioSegment.from_wav(path)
       chunks = split_on_silence(sound,
                                 min_silence_len=500,
                                 silence_thresh=sound.dBFS-14,
                                 keep_silence=500,
                                 )
       folder_name = "audio-chunks"
       if not os.path.isdir(folder_name):
           os.mkdir(folder_name)
       whole_text = ""
       for i, audio_chunk in enumerate(chunks, start=1):
           chunk_filename = os.path.join(folder_name, f"chunk{i}.wav")
           audio_chunk.export(chunk_filename, format="wav")
           with sr.AudioFile(chunk_filename) as source:
               audio_listened = r.record(source)
               try:
                   text = r.recognize_google(audio_listened)
               except sr.UnknownValueError as e:
                   print("Error:", str(e))
               else:
                   text = f"{text.capitalize()}. "
                   print(chunk_filename, ":", text)
                   whole_text += text
       return whole_text

4. 调用该函数并传入音频文件的路径，即可将音频转换为文本。

   path = "path/to/audio_file.wav"
   print("\nFull text:", get_large_audio_transcription(path))

完整代码示例：

import os
import speech_recognition as sr
from pydub import AudioSegment
from pydub.silence import split_on_silence

def get_large_audio_transcription(path):
    r = sr.Recognizer()
    sound = AudioSegment.from_wav(path)
    chunks = split_on_silence(sound,
                              min_silence_len=500,
                              silence_thresh=sound.dBFS-14,
                              keep_silence=500,
                              )
    folder_name = "audio-chunks"
    if not os.path.isdir(folder_name):
        os.mkdir(folder_name)
    whole_text = ""
    for i, audio_chunk in enumerate(chunks, start=1):
        chunk_filename = os.path.join(folder_name, f"chunk{i}.wav")
        audio_chunk.export(chunk_filename, format="wav")
        with sr.AudioFile(chunk_filename) as source:
            audio_listened = r.record(source)
            try:
                text = r.recognize_google(audio_listened)
            except sr.UnknownValueError as e:
                print("Error:", str(e))
            else:
                text = f"{text.capitalize()}. "
                print(chunk_filename, ":", text)
                whole_text += text
    return whole_text

path = "path/to/audio_file.wav"
print("\nFull text:", get_large_audio_transcription(path))