调用WeNet与百度智能云API进行语音识别

智能语音识别

实验目标：

调用WeNet与百度智能云进行语音识别，并且使用自定义训练集进行训练。

实验任务

调用wenet的解码器，对测试语音进行识别，输出中文语句；
调用百度智能云的api进行语音识别；
尝试构建或下载自定义语音数据集，使用wenet框架进行训练

wenet

配置相关环境

1. 安装必要库

   pip install wenet
   pip install wave
   

2. 下载模型文件chs

   模型文件下载链接

   https://github.com/wenet-e2e/wenet/releases/download/v2.0.1/chs.tar.gz

代码部分

import wave
import wenetruntime as wenet

test_wav = "test.wav"  #选择语音文件
with wave.open(test_wav, 'rb') as fin:
    assert fin.getnchannels() == 1
    wav = fin.readframes(fin.getnframes())

#模型文件夹
model_dir = "chs"
decoder = wenet.Decoder(model_dir=model_dir, lang='chs')
# The wav is 24k, 16bits, and decode every 0.5 seconds
interval = int(0.5 * 24000) * 2
for i in range(0, len(wav), interval):
    last = False if i + interval < len(wav) else True
    chunk_wav = wav[i:min(i + interval, len(wav))]
    ans = decoder.decode(chunk_wav, last)
    print(ans)

执行结果

{
  "nbest" : [{
      "sentence" : "人工智能"
    }],
  "type" : "final_result"
}

百度API

在百度云创建语音识别应用

安装必要库

pip install sys
pip install json
pip install base64
pip install time

代码部分

注意替换其中的API Key、Secret Key

# coding=utf-8

import sys
import json
import base64
import time

IS_PY3 = sys.version_info.major == 3

if IS_PY3:
    from urllib.request import urlopen
    from urllib.request import Request
    from urllib.error import URLError
    from urllib.parse import urlencode
    timer = time.perf_counter
else:
    from urllib.request import urlopen
    from urllib.request import Request
    from urllib.request import URLError
    from urllib import urlencode
    if sys.platform == "win32":
        timer = time.clock
    else:
        # On most other platforms the best timer is time.time()
        timer = time.time

API_KEY = '填入你的KEY'
SECRET_KEY = '填入你的KEY'

# 需要识别的文件
AUDIO_FILE = './audio/16k.wav'  # 只支持 pcm/wav/amr 格式
# 文件格式
FORMAT = AUDIO_FILE[-3:]  # 文件后缀只支持 pcm/wav/amr 格式

CUID = '123456PYTHON'
# 采样率
RATE = 16000  # 固定值

# 普通版

DEV_PID = 1537  # 1537 表示识别普通话，使用输入法模型。根据文档填写PID，选择语言及识别模型
ASR_URL = 'http://vop.baidu.com/server_api'
SCOPE = 'audio_voice_assistant_get'  # 有此scope表示有asr能力，没有请在网页里勾选，非常旧的应用可能没有

class DemoError(Exception):
    pass


"""  TOKEN start """

TOKEN_URL = 'http://aip.baidubce.com/oauth/2.0/token'


def fetch_token():
    params = {'grant_type': 'client_credentials',
              'client_id': API_KEY,
              'client_secret': SECRET_KEY}
    post_data = urlencode(params)
    if (IS_PY3):
        post_data = post_data.encode( 'utf-8')
    req = Request(TOKEN_URL, post_data)
    try:
        f = urlopen(req)
        result_str = f.read()
    except URLError as err:
        print('token http response http code : ' + str(err.code))
        result_str = err.read()
    if (IS_PY3):
        result_str =  result_str.decode()

    print(result_str)
    result = json.loads(result_str)
    print(result)
    if ('access_token' in result.keys() and 'scope' in result.keys()):
        print(SCOPE)
        if SCOPE and (not SCOPE in result['scope'].split(' ')):  # SCOPE = False 忽略检查
            raise DemoError('scope is not correct')
        print('SUCCESS WITH TOKEN: %s  EXPIRES IN SECONDS: %s' % (result['access_token'], result['expires_in']))
        return result['access_token']
    else:
        raise DemoError('MAYBE API_KEY or SECRET_KEY not correct: access_token or scope not found in token response')

"""  TOKEN end """

if __name__ == '__main__':
    token = fetch_token()

    speech_data = []
    with open(AUDIO_FILE, 'rb') as speech_file:
        speech_data = speech_file.read()

    length = len(speech_data)
    if length == 0:
        raise DemoError('file %s length read 0 bytes' % AUDIO_FILE)
    speech = base64.b64encode(speech_data)
    if (IS_PY3):
        speech = str(speech, 'utf-8')
    params = {'dev_pid': DEV_PID,
              'format': FORMAT,
              'rate': RATE,
              'token': token,
              'cuid': CUID,
              'channel': 1,
              'speech': speech,
              'len': length
              }
    post_data = json.dumps(params, sort_keys=False)
    # print post_data
    req = Request(ASR_URL, post_data.encode('utf-8'))
    req.add_header('Content-Type', 'application/json')
    try:
        begin = timer()
        f = urlopen(req)
        result_str = f.read()
        print ("Request time cost %f" % (timer() - begin))
    except URLError as err:
        print('asr http response http code : ' + str(err.code))
        result_str = err.read()

    if (IS_PY3):
        result_str = str(result_str, 'utf-8')
    print(result_str)
    with open("result.txt","w") as of:
        of.write(result_str)

运行结果

{"corpus_no":"7299264180552717747","err_msg":"success.","err_no":0,"result":["北京科技馆。"],"sn":"626746583651699492376"}