在Python中使用wav文件录制音频和语音到文本的转换

pip install pyaudio

import wave
import pyaudio

def record_audio(filename, duration):
    chunk = 1024
    format = pyaudio.paInt16
    channels = 1
    rate = 16000

    p = pyaudio.PyAudio()

    stream = p.open(format=format,
                    channels=channels,
                    rate=rate,
                    input=True,
                    frames_per_buffer=chunk)

    print("开始录制音频...")

    frames = []
    for i in range(0, int(rate / chunk * duration)):
        data = stream.read(chunk)
        frames.append(data)

    print("录制完成！")

    stream.stop_stream()
    stream.close()
    p.terminate()

    wf = wave.open(filename, 'wb')
    wf.setnchannels(channels)
    wf.setsampwidth(p.get_sample_size(format))
    wf.setframerate(rate)
    wf.writeframes(b''.join(frames))
    wf.close()

# 调用函数来录制音频
record_audio('recording.wav', 5)

pip install SpeechRecognition

import speech_recognition as sr

def convert_speech_to_text(filename):
    r = sr.Recognizer()

    with sr.AudioFile(filename) as source:
        audio = r.record(source) 

    text = r.recognize_google(audio, language='zh-CN')
    return text

# 调用函数将音频转换为文本
text = convert_speech_to_text('recording.wav')
print("转换结果：", text)