CoolFace
Modelpublic

Chuatury/wav2vec2-mms-1b-cmn-phonetic

sourceHugging Facecc-by-nc-4.0updated 1y agoView on Hugging Face
2likes25downloads
Model Card

wav2vec2-mms-1b-cmn-phonetic

国语读音 ASR,将语音转换为读音以进行自动 TTS 标注

  • —CER 0.022529

输出格式

使用一种修改版的注音实现发音完全对应, 可以转换回注音/拼音

python3
initials = [
    "ㄅ",
    "ㄆ",
    "ㄇ",
    "ㄈ",
    "ㄉ",
    "ㄊ",
    "ㄋ",
    "ㄌ",
    "ㄍ",
    "ㄎ",
    "ㄏ",
    "ㄐ",
    "ㄑ",
    "ㄒ",
    "ㄓ",
    "ㄔ",
    "ㄕ",
    "ㄖ",
    "ㄗ",
    "ㄘ",
    "ㄙ",
    # IPA /j/ sound, when initial is absent while finals start with "ㄧ" or "ㄩ"
    # such as ㄧㄚ /jiɑ/ or ㄧㄝ /jiɛ/ or ㄩㄝ /jyɛ/
    "j",
]

finals = [
    "ㄚ",
    "ㄛ",
    "ㄜ",
    "ㄝ",
    "ㄞ",
    "ㄟ",
    "ㄠ",
    "ㄡ",
    "ㄢ",
    "ㄣ",
    "ㄤ",
    "ㄥ",
    "ㄦ",
    # special medials that can be used as prefixes for other medials
    "ㄧ",
    "ㄧㄛ",
    "ㄧㄚ",
    "ㄧㄝ",
    "ㄧㄠ",
    "ㄧㄡ",
    "ㄧㄢ",
    "ㄧㄣ",
    "ㄧㄤ",
    "ㄧㄥ",
    "ㄨ",
    "ㄨㄚ",
    "ㄨㄛ",
    "ㄨㄞ",
    "ㄨㄟ",
    "ㄨㄢ",
    "ㄨㄣ",
    "ㄨㄤ",
    "ㄨㄥ",
    "ㄩ",
    "ㄩㄝ",
    "ㄩㄢ",
    "ㄩㄣ",
    "ㄩㄥ",
    # https://zh.wikipedia.org/zh-tw/%E7%A9%BA%E9%9F%BB
    "ㄭ+",  # after ㄓ, ㄔ, ㄕ, ㄖ
    "ㄭ-",  # after ㄗ, ㄘ, ㄙ
    # https://zh.wikipedia.org/wiki/%E5%85%92%E5%8C%96
    "r",
]