【人工智障】之一 语音识别

首先，配置appid AK SK

from aip import AipSpeech

""" 你的 APPID AK SK """
APP_ID = '11312730'
API_KEY = 'I7rDa8SGYVM4yFHGjuzdgOrO'
SECRET_KEY = 'BguQbuYvyeqhFsVFfNNe2hieYOsvp5yL'

 

语音合成

  client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)

result  = client.synthesis('我是李文强，给大家说句绕口令，'
                           '八百标兵奔北坡, 炮兵并排北边跑, 炮兵怕把标兵碰, '
                           '标兵怕碰炮兵炮. 八百标兵奔北坡, 北坡八百炮兵炮. '
                           '标兵怕碰炮兵炮, 炮兵怕把标兵碰.，',
                           'zh', 1, {
    'vol': 5,
    'per': 4
})

# 识别正确返回语音二进制 错误则返回dict 参照下面错误码
if not isinstance(result, dict):
    with open('audio.mp3', 'wb') as f:
    # with open('audio.pcm', 'wb') as f:
        f.write(result)

 

语音识别

# 读取文件
def get_file_content(filePath):
    os.system(f"ffmpeg -y  -i {filePath} -acodec pcm_s16le -f s16le -ac 1 -ar 16000 {filePath}.pcm")
    # os.system(f"ffmpeg -y  -i {filePath} -acodec pcm_s16le -f s16le -ac 1 -ar 16000 {filePath}.pcm")
    with open(f"{filePath}.pcm", 'rb') as fp:
        return fp.read()

# 识别本地文件
res = client.asr(get_file_content('audio.mp3'), 'pcm', 16000, {
    'dev_pid': 1536,
})

print(res.get("result")[0])

 给我说(必须提供一个mp3文件)

from aip import AipSpeech
import os

APP_ID = '11312730'
API_KEY = 'I7rDa8SGYVM4yFHGjuzdgOrO'
SECRET_KEY = 'BguQbuYvyeqhFsVFfNNe2hieYOsvp5yL'

client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)

def audio2text(filename):
    os.system(f"ffmpeg -y  -i {filename} -acodec pcm_s16le -f s16le -ac 1 -ar 16000 {filename}.pcm")
    with open(f"{filename}.pcm","rb") as fp:
        res = client.asr(fp.read(), "pcm", 16000, {
            'dev_pid': 1536,
        })
        print(res.get("result")[0])
        return res.get("result")[0]

def text2audio(text):
    result = client.synthesis(text, 'zh', 1, {
        "spd": 4,
        "vol": 5,
        "pit": 8,
        "per": 4
    })
    if not isinstance(result, dict):
        with open("audio.mp3", "wb") as f:
            f.write(result)
    os.system("audio.mp3")

text = audio2text("audio.mp3")
if "你叫什么名字" in text:
    text2audio("我的名字叫**")
else:
    text2audio(f"你刚刚是说，{text}")