Python语音识别实现

本文将介绍如何使用Python实现语音识别，从语音输入到文字转换的过程，帮助您理解并使用Python进行语音识别。

一、安装依赖库

首先，我们需要安装一些必要的依赖库，用于处理语音相关的操作。其中最重要的库是SpeechRecognition，它是Python中常用的语音识别库。

pip install SpeechRecognition

二、录音

在进行语音识别之前，我们需要先录音获取音频输入。Python提供了pyaudio库，可以方便地进行音频录制。

# 导入所需库
import pyaudio
import wave

# 设置音频参数
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
CHUNK = 1024
RECORD_SECONDS = 5
WAVE_OUTPUT_FILENAME = "output.wav"

# 录音函数
def record_audio():
    audio = pyaudio.PyAudio()

    stream = audio.open(format=FORMAT, channels=CHANNELS,
                    rate=RATE, input=True,
                    frames_per_buffer=CHUNK)

    print("开始录音...")

    frames = []

    for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
        data = stream.read(CHUNK)
        frames.append(data)

    print("录音结束.")

    stream.stop_stream()
    stream.close()
    audio.terminate()

    wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
    wf.setnchannels(CHANNELS)
    wf.setsampwidth(audio.get_sample_size(FORMAT))
    wf.setframerate(RATE)
    wf.writeframes(b''.join(frames))
    wf.close()

# 调用录音函数
record_audio()

三、语音识别

录音完成后，我们可以将录音文件作为输入进行语音识别。使用SpeechRecognition库可以很容易地实现语音识别功能。

# 导入所需库
import speech_recognition as sr

# 设置语音识别器
r = sr.Recognizer()

# 定义语音识别函数
def recognize_speech():
    # 打开录音文件
    with sr.AudioFile("output.wav") as source:
        # 读取音频文件数据
        audio_data = r.record(source)
        # 使用Google Web Speech API进行语音识别
        text = r.recognize_google(audio_data, language="zh-CN")
        print("语音识别结果：", text)

# 调用语音识别函数
recognize_speech()

四、完整代码

import pyaudio
import wave
import speech_recognition as sr

FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
CHUNK = 1024
RECORD_SECONDS = 5
WAVE_OUTPUT_FILENAME = "output.wav"

def record_audio():
    audio = pyaudio.PyAudio()

    stream = audio.open(format=FORMAT, channels=CHANNELS,
                    rate=RATE, input=True,
                    frames_per_buffer=CHUNK)

    print("开始录音...")

    frames = []

    for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
        data = stream.read(CHUNK)
        frames.append(data)

    print("录音结束.")

    stream.stop_stream()
    stream.close()
    audio.terminate()

    wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
    wf.setnchannels(CHANNELS)
    wf.setsampwidth(audio.get_sample_size(FORMAT))
    wf.setframerate(RATE)
    wf.writeframes(b''.join(frames))
    wf.close()

def recognize_speech():
    r = sr.Recognizer()

    with sr.AudioFile("output.wav") as source:
        audio_data = r.record(source)
        text = r.recognize_google(audio_data, language="zh-CN")
        print("语音识别结果：", text)

record_audio()
recognize_speech()

以上就是使用Python实现语音识别的过程。您可以根据自己的需求对录音和语音识别部分进行相应的调整和扩展。希望本文对您有所帮助，谢谢阅读！