transcriber.py 文件源码

def cut_and_send(infile, outfile, length):
    # print(infile)
    # print(outfile)
    # print(length)
    # return
    myaudio = AudioSegment.from_file(infile, "wav")
    chunk_length_ms = length  # pydub calculates in millisec
    chunks = make_chunks(myaudio, chunk_length_ms)  # Make chunks of one sec

    for i, chunk in enumerate(chunks):
        chunk_name = "chunk{0}.wav".format(i)
        print("exporting", chunk_name)
        chunk.export(chunk_name, format="wav")
        r = sr.Recognizer()
        with sr.AudioFile(chunk_name) as source:
            audio = r.record(source)
        # recognize speech using Google Speech Recognition
        try:
            # to use another API key, use `r.recognize_google(audio, key="GOOGLE_SPEECH_RECOGNITION_API_KEY")`
            # instead of `r.recognize_google(audio)`
            txt = r.recognize_google(audio) + " "
            with open(outfile, 'a') as f:
                f.write(txt)
        except sr.UnknownValueError:
            print("Ehm... sorry not understood this one.")
        except sr.RequestError as e:
            print("Request failed; {0}".format(e))
        os.remove(chunk_name)