Python中将语音转换为文本的实现方法

pip3 install SpeechRecognition pydub

import speech_recognition as sr

filename = "16-122828-0002.wav"

# initialize the recognizer
r = sr.Recognizer()

# open the file
with sr.AudioFile(filename) as source:
    # listen for the data (load audio to memory)
    audio_data = r.record(source)
    # recognize (convert from speech to text)
    text = r.recognize_google(audio_data)
    print(text)

# importing libraries 
import speech_recognition as sr 
import os 
from pydub import AudioSegment
from pydub.silence import split_on_silence

# create a speech recognition object
r = sr.Recognizer()

# a function to recognize speech in the audio file
# so that we don't repeat ourselves in in other functions
def transcribe_audio(path):
    # use the audio file as the audio source
    with sr.AudioFile(path) as source:
        audio_listened = r.record(source)
        # try converting it to text
        text = r.recognize_google(audio_listened)
    return text

# a function that splits the audio file into chunks on silence
# and applies speech recognition
def get_large_audio_transcription_on_silence(path):
    """Splitting the large audio file into chunks
    and apply speech recognition on each of these chunks"""
    # open the audio file using pydub
    sound = AudioSegment.from_file(path)  
    # split audio sound where silence is 500 miliseconds or more and get chunks
    chunks = split_on_silence(sound,
        # experiment with this value for your target audio file
        min_silence_len = 500,
        # adjust this per requirement
        silence_thresh = sound.dBFS-14,
        # keep the silence for 1 second, adjustable as well
        keep_silence=500,
    )
    folder_name = "audio-chunks"
    # create a directory to store the audio chunks
    if not os.path.isdir(folder_name):
        os.mkdir(folder_name)
    whole_text = ""
    # process each chunk 
    for i, audio_chunk in enumerate(chunks, start=1):
        # export audio chunk and save it in
        # the `folder_name` directory.
        chunk_filename = os.path.join(folder_name, f"chunk{i}.wav")
        audio_chunk.export(chunk_filename, format="wav")
        # recognize the chunk
        try:
            text = transcribe_audio(chunk_filename)
        except sr.UnknownValueError as e:
            print("Error:", str(e))
        else:
            text = f"{text.capitalize()}. "
            print(chunk_filename, ":", text)
            whole_text += text
    # return the text for all chunks detected
    return whole_text
        ```




 &emsp;&emsp;  <font face="楷体"   size=4>


注意：您需要安装Pydub才能pip使上述代码正常工作。

上述函数使用模块split_on_silence()中的函数pydub.silence在静音时将音频数据分割成块。该min_silence_len参数是用于分割的最小静音长度（以毫秒为单位）。

silence_thresh是阈值，任何比这更安静的东西都将被视为静音，我将其设置为平均dBFS - 14，keep_silence参数是在检测到的每个块的开头和结尾处留下的静音量（以毫秒为单位）。

这些参数并不适合所有声音文件，请尝试根据您的大量音频需求尝试这些参数。

之后，我们迭代所有块并将每个语音音频转换为文本，然后将它们加在一起，这是一个运行示例：

path = "7601-291468-0006.wav"
print("\nFull text:", get_large_audio_transcription_on_silence(path))
注意：您可以在此处7601-291468-0006.wav获取文件。

输出：

```python
audio-chunks\chunk1.wav : His abode which you had fixed in a bowery or country seat. 
audio-chunks\chunk2.wav : At a short distance from the city. 
audio-chunks\chunk3.wav : Just at what is now called dutch street. 
audio-chunks\chunk4.wav : Sooner bounded with proofs of his ingenuity. 
audio-chunks\chunk5.wav : Patent smokejacks. 
audio-chunks\chunk6.wav : It required a horse to work some. 
audio-chunks\chunk7.wav : Dutch oven roasted meat without fire. 
audio-chunks\chunk8.wav : Carts that went before the horses. 
audio-chunks\chunk9.wav : Weather cox that turned against the wind and other wrongheaded contrivances. 
audio-chunks\chunk10.wav : So just understand can found it all beholders. 

Full text: His abode which you had fixed in a bowery or country seat. At a short distance from the city. Just at what is now called dutch street. Sooner bounded with proofs of his ingenuity. Patent smokejacks. It required a horse to work some. Dutch oven roasted meat without fire. Carts that went before the horses. Weather cox that turned against the wind and other wrongheaded contrivances. So just understand can found it all beholders.

# a function that splits the audio file into fixed interval chunks
# and applies speech recognition
def get_large_audio_transcription_fixed_interval(path, minutes=5):
    """Splitting the large audio file into fixed interval chunks
    and apply speech recognition on each of these chunks"""
    # open the audio file using pydub
    sound = AudioSegment.from_file(path)  
    # split the audio file into chunks
    chunk_length_ms = int(1000 * 60 * minutes) # convert to milliseconds
    chunks = [sound[i:i + chunk_length_ms] for i in range(0, len(sound), chunk_length_ms)]
    folder_name = "audio-fixed-chunks"
    # create a directory to store the audio chunks
    if not os.path.isdir(folder_name):
        os.mkdir(folder_name)
    whole_text = ""
    # process each chunk 
    for i, audio_chunk in enumerate(chunks, start=1):
        # export audio chunk and save it in
        # the `folder_name` directory.
        chunk_filename = os.path.join(folder_name, f"chunk{i}.wav")
        audio_chunk.export(chunk_filename, format="wav")
        # recognize the chunk
        try:
            text = transcribe_audio(chunk_filename)
        except sr.UnknownValueError as e:
            print("Error:", str(e))
        else:
            text = f"{text.capitalize()}. "
            print(chunk_filename, ":", text)
            whole_text += text
    # return the text for all chunks detected
    return whole_text

print("\nFull text:", get_large_audio_transcription_fixed_interval(path, minutes=1/6))

$ pip3 install pyaudio

$ sudo apt-get install python-pyaudio python3-pyaudio
$ pip3 install pyaudio

$ brew install portaudio
$ pip3 install pyaudio

import speech_recognition as sr

with sr.Microphone() as source:
    # read the audio data from the default microphone
    audio_data = r.record(source, duration=5)
    print("Recognizing...")
    # convert speech to text
    text = r.recognize_google(audio_data)
    print(text)

text = r.recognize_google(audio_data, language="es-ES")