python进阶-13-语音识别

1.文字转语音

安装模块:

pip install pyttsx3

异常:

ModuleNotFoundError: No module named 'pythoncom'

解决:

pip install pywin32

代码:

使用pyttsx3

# coding=utf-8
import pyttsx3 as pyttsx

engine = pyttsx.init()
# 调节语速
rate = engine.getProperty('rate')
engine.setProperty('rate', rate - 100)
engine.say('吴佩祯我爱你')
engine.runAndWait()

使用SAPI(无需安装模块)

# coding=utf-8
from win32com.client import Dispatch
speaker = Dispatch('SAPI.SpVoice')
speaker.Speak('吴佩祯我爱你')
del speaker

2.文本文件转语音

使用SpeechLib模块

安装:

pip install comtypes

代码:

# coding=utf-8
from comtypes.client import CreateObject
from comtypes.gen import SpeechLib
engine = CreateObject('SAPI.SpVoice')
stream = CreateObject('SAPI.SpFileStream')
infile = 'demo.txt'
outfile = 'demo_audio.wav'
stream.open(outfile, SpeechLib.SSFMCreateForWrite)
# 读取文件内容
f = open(infile, 'r', encoding='utf-8')
theText = f.read()
f.close()
engine.speak(theText)
stream.close()

3.文本文件转语音

使用开源第三方模块PocketSphinx

pip install PocketSphinx
pip install SpeechRecognition

异常:

 error: command 'swig.exe' failed: 

解决:
改用下载安装的方式,下载地址:
https://www.lfd.uci.edu/~gohlke/pythonlibs/#pocketsphinx
执行:

python -m pip install .\pocketsphinx-0.1.15-cp37-cp37m-win_amd64.whl

代码实现:

import speech_recognition as sr
audio_file='demo_audio.wav'
r=sr.Recognizer()
#打开语音文件
with sr.AudioFile(audio_file) as source:
    audio=r.record(source)

#将语音转换为文本
# print('文本内容：',r.recognize_sphinx(audio))
print('文本内容：',r.recognize_sphinx(audio,language='zh-CN'))

异常:

ecognize_sphinx raise UnknownValueError() # no transcriptions available

另外,似乎不支持mp3和wmv格式,坑