python编程之百度接口语音识别

  • 首先在百度AI开放平台上创建语音识别应用，创建完毕应用后，得到系统分配给用户的AppID， API Key， secret Key，均为字符串，用于标识用户，为访问做签名验证。
  • 得到验证后，开始编程
    • 1.记录自己声音
    • 2.将记录下来的音频文件上传至云端
    • 3.解析返回后的结果
  • python实现
  • 相关包 pyaudio，baidu-aip
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57

from aip import AipSpeech
import wave
from pyaudio import PyAudio, paInt16

def save_wave_file(filename, data):
    '''save the date to the wavfile'''
    wf = wave.open(filename, 'wb')
    wf.setnchannels(channels)
    wf.setsampwidth(sampwidth)
    wf.setframerate(framerate)
    wf.writeframes(b"".join(data))
    wf.close()


def my_record():
    pa = PyAudio()
    stream = pa.open(format=paInt16, channels=1,
                     rate=framerate, input=True,
                     frames_per_buffer=NUM_SAMPLES)
    my_buf = []
    count = 0
    print('录音开始')
    while count < TIME*10:  # 控制录音时间
        string_audio_data = stream.read(NUM_SAMPLES)
        my_buf.append(string_audio_data)
        count += 1
    print('录音结束')
    save_wave_file('01.pcm', my_buf)
    stream.close()


if __name__ == "__main__":
    framerate = 16000
    NUM_SAMPLES = 2000
    channels = 1
    sampwidth = 2
    TIME = 2
    my_record()

    """ 我的 APPID AK SK """
    APP_ID = '16795182  '
    API_KEY = '8io5s7uv8pjYPUrQp1i8PcIg'
    SECRET_KEY = 'gK2MljvbcF3SKS4p0C2ieq1SCBNY48BD'
    client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)


    # 读取文件
    def get_file_content(filePath):
        with open(filePath, 'rb') as fp:
            return fp.read()

    # 识别本地文件
    result = client.asr(get_file_content('01.pcm'), 'pcm', 16000, {
                'dev_pid': 1536,
    })
    # print(type(result))
    print("语音识别结果：", result['result'])