main.py 文件源码

def synthesize(self, text, src, dst):
        """
        Synthesize .wav from text
        src is the folder that contains all syllables .wav files
        dst is the destination folder to save the synthesized file
        """
        print("Synthesizing ...")
        delay = 0
        increment = 355 # milliseconds
        pause = 500 # pause for punctuation
        syllables = lazy_pinyin(text, style=pypinyin.TONE3)

        # initialize to be complete silence, each character takes up ~500ms
        result = AudioSegment.silent(duration=500*len(text))
        for syllable in syllables:
            path = src+syllable+".wav"
            sound_file = Path(path)
            # insert 500 ms silence for punctuation marks
            if syllable in TextToSpeech.punctuation:
                short_silence = AudioSegment.silent(duration=pause)
                result = result.overlay(short_silence, position=delay)
                delay += increment
                continue
            # skip sound file that doesn't exist
            if not sound_file.is_file():
                continue
            segment = AudioSegment.from_wav(path)
            result = result.overlay(segment, position=delay)
            delay += increment

        directory = dst
        if not os.path.exists(directory):
            os.makedirs(directory)

        result.export(directory+"generated.wav", format="wav")
        print("Exported.")