python實現人工智能之路--語音識別加語音合成

代碼如下

from aip import AipSpeech
import os

APP_ID = '14940732'
API_KEY = 'tm1jAzv8dnDQM5yzFUk0ED9j'
SECRET_KEY = '2WsPOg8k7GHtPnN2PBIsuf9LRpozYK8A'

client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)


def audio_to_text(filename):
    filename = filename.split('.')[0]
    os.system(f"ffmpeg -y -i {filename}.mp3 -acodec pcm_s16le -f s16le -ac 1 -ar 16000 {filename}.pcm")
    with open(f"{filename}.pcm", 'rb') as fp:
        file_content = fp.read()
        result = client.asr(file_content, 'pcm', 16000, {'dev_pid': 1536})
        print(result)
        result_str = result.get('result')[0]
        return result_str


def text_to_audio(result_str):
    result = client.synthesis(result_str, 'zh', 1,
                              {
                                  'vol': 5,
                                  'spd': 3,
                                  'pit': 8,
                                  'per': 4
                              })

    # 識別正確返回語音二進制 錯誤則返回dict 參照下面錯誤碼
    if not isinstance(result, dict):
        with open('audio.mp3', 'wb') as f:
            f.write(result)
    os.system('audio.mp3')


a = audio_to_text('audio.mp3')
if '你好我的世界' in a:
    text_to_audio(a)
else:
    text_to_audio(f'你剛才是不是在說, {a}嗎?')

提前需下載pip install baidu=aip

以及ffmpeg地址如下https://pan.baidu.com/s/1jonSAa_TG2XuaJEy3iTmHg 提取碼為w6hk