python语音识别代码_python实现百度语音识别api

好的，我可以为您提供一份Python语音识别代码，实现百度语音识别API的功能。请注意，在使用之前需要先进行百度AI开发者账号的注册和创建应用，获取API Key和Secret Key。

# 导入需要的模块
import os
import time
import urllib.request
import urllib.parse
import json
import base64
import hashlib
import pyaudio

# 设置API Key和Secret Key
API_KEY = 'your_api_key'
SECRET_KEY = 'your_secret_key'

# 获取Token，用于后续的API调用
def get_token():
    token_url = 'https://aip.baidubce.com/oauth/2.0/token'
    grant_type = 'client_credentials'
    token_data = {'grant_type': grant_type, 'client_id': API_KEY, 'client_secret': SECRET_KEY}
    token_data_encoded = urllib.parse.urlencode(token_data).encode('utf-8')
    token_request = urllib.request.Request(token_url, token_data_encoded)
    token_response = urllib.request.urlopen(token_request)
    token_content = token_response.read().decode('utf-8')
    token_json = json.loads(token_content)
    access_token = token_json['access_token']
    return access_token

# 进行语音识别
def speech_recognition():
    token = get_token()
    speech_url = 'https://vop.baidu.com/server_api'
    speech_data = {
        'format': 'pcm',
        'rate': 16000,
        'channel': 1,
        'cuid': 'python',
        'token': token,
        'speech': '',
        'len': 0,
        'dev_pid': 1536  # 1536为普通话，其它语种需要修改为对应的dev_pid
    }
    speech_data_encoded = json.dumps(speech_data).encode('utf-8')
    speech_request = urllib.request.Request(speech_url, speech_data_encoded)
    speech_request.add_header('Content-Type', 'application/json')
    speech_response = urllib.request.urlopen(speech_request)
    speech_content = speech_response.read().decode('utf-8')
    speech_json = json.loads(speech_content)
    result = speech_json['result'][0].strip()
    return result

# 录音，用于获取语音数据
def record_audio():
    CHUNK = 1024
    FORMAT = pyaudio.paInt16
    CHANNELS = 1
    RATE = 16000
    RECORD_SECONDS = 5
    WAVE_OUTPUT_FILENAME = 'audio.wav'
    p = pyaudio.PyAudio()
    stream = p.open(format=FORMAT, channels=CHANNELS, rate=RATE, input=True, frames_per_buffer=CHUNK)
    frames = []
    print('开始录音...')
    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()
    p.terminate()
    wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
    wf.setnchannels(CHANNELS)
    wf.setsampwidth(p.get_sample_size(FORMAT))
    wf.setframerate(RATE)
    wf.writeframes(b''.join(frames))
    wf.close()

if __name__ == '__main__':
    while True:
        input('按下回车键开始录音，录音结束后按下回车键停止录音...')
        record_audio()
        result = speech_recognition()
        print('语音识别结果：', result)

以上代码实现了一个简单的语音识别程序，可以通过调用百度语音识别API实现语音转文字的功能。需要注意的是，该程序需要使用pyaudio和wave两个Python模块，需要提前安装。另外，在使用之前需要修改代码中的API Key和Secret Key为自己的值。