Python音訊轉文字

import speech_recognition as sr
file ="test.wav"
r= sr.Recognizer()
with sr.AudioFile(file) as src:
    audio = r.record(src)
print("音聲データの文字をお越し結果：", r.recognize_google(audio,language="ja"))

speech_recognition：https://github.com/Uberi/speech_recognition

import speech_recognition as sr

file ="tianqi.wav"

r= sr.Recognizer()

with sr.AudioFile(file) as src:
    audio = r.record(src)

print("識別結果：", r.recognize_google(audio,language="zh-tw"))
print("識別結果：", r.recognize_google(audio,language="zh-cn"))

說明，需要使用代理，需要連線網路。