diff --git a/download_video.py b/download_video.py index 05ccce7..3ab1a7f 100644 --- a/download_video.py +++ b/download_video.py @@ -28,7 +28,7 @@ def generate_infos(): def download_video(info): link = info["link"] filename = info["filename"] - os.system(f"youtube-dl -f 0 {link} -o ./video_data/{filename}.mp4") + os.system(f"youtube-dl -f 0 {link} -o ./video_data/{filename}.mp4 --no-check-certificate") if __name__ == "__main__": diff --git a/text/cleaners.py b/text/cleaners.py index 6c7b809..adc6fd8 100644 --- a/text/cleaners.py +++ b/text/cleaners.py @@ -29,19 +29,14 @@ def korean_cleaners(text): return text -# def chinese_cleaners(text): -# '''Pipeline for Chinese text''' -# text = number_to_chinese(text) -# text = chinese_to_bopomofo(text) -# text = latin_to_bopomofo(text) -# text = re.sub(r'([ˉˊˇˋ˙])$', r'\1。', text) -# return text - def chinese_cleaners(text): - from pypinyin import Style, pinyin + '''Pipeline for Chinese text''' text = text.replace("[ZH]", "") - phones = [phone[0] for phone in pinyin(text, style=Style.TONE3)] - return ' '.join(phones) + text = number_to_chinese(text) + text = chinese_to_bopomofo(text) + text = latin_to_bopomofo(text) + text = re.sub(r'([ˉˊˇˋ˙])$', r'\1。', text) + return text def zh_ja_mixture_cleaners(text):