eaefc57d71
* 快速分类音频并把yml格式结果存在训练根目录里 (#190) * Add files via upload * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Update models.py * Update webui.py * Update infer.py * Create compress_model.py * 重新提交，更新Gradio推理UI (#193) * Update webui.py * Update webui.py * 更新 train_ms.py * 更新 models.py * 更新 models.py * 更新 models.py * 更新 train_ms.py * 更新 train_ms.py * 更新 models.py * Update preprocess_text.py * Update config.json * Update train_ms.py * Update webui.py (#206) * Add files via upload (#209) * Update train_ms.py * Update train_ms.py * Update preprocess_text.py * Update train_ms.py * fix (#211) * Update emotion_clustering.py * Add files via upload * Update emotion_clustering.py * add cluster center save * Add files via upload * Update config.py * Update default_config.yml * Update config.py * Update config.py * Update emotion_clustering.py * Update emotion_clustering.py * Update config.py * Update emotion_clustering.py * Update emotion_clustering.py * Update webui.py * Update emotion_clustering.py * Update commons.py * Update emotion_clustering.py * Update webui.py * Update webui.py * Add files via upload * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update webui.py * Update emotion_clustering.py * Update emotion_clustering.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix default_config.yml. * Update infer.py * feat: support infer 2.1 models * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix: support infer 2.1 models 兼容bug修复 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update train_ms.py * Add CLAP * Fix data loader * Fix infer.py * Fix webui.py * Add prompt template * Update clap_gen.py * Fix wrong environ value * Add g for dur disc * Update clap_gen.py * Fix multilang generation * Update config.json * Prompt mode * Improve slice segments performance * Add preprocess webui * Update webui_preprocess.py * Update webui_preprocess.py * Update config.py * Update default_config.yml * Update config.py * Update clap_gen.py * Delete emo_gen.py * Delete get_emo.py * Delete emotional/wav2vec2-large-robust-12-ft-emotion-msp-dim directory * Update README.md * Update README * Split val per lang * Delete emotion_clustering.py * Update default_config.yml * Update default_config.yml * Update config.py * Update preprocess_text.py * Update webui_preprocess.py * Update defalut_config.yml * Update webui_preprocess.py * Update preprocess_text.py * Random augmentation for CLAP * Update data_utils.py * Update preprocess_text.py * Add vq for CLAP features to avoid overfitting * Random dummy inputs * Update webui.py * Update models.py * Update infer.py * Apply Code Formatter Change * Update config.json * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: YYuX-1145 <138500330+YYuX-1145@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Sora <654163754@qq.com> Co-authored-by: Sihan Wang <wangsihan1995@gmail.com> Co-authored-by: Stardust-minus <Stardust-minus@users.noreply.github.com>
188 lines
2.2 KiB
Python
188 lines
2.2 KiB
Python
punctuation = ["!", "?", "…", ",", ".", "'", "-"]
|
|
pu_symbols = punctuation + ["SP", "UNK"]
|
|
pad = "_"
|
|
|
|
# chinese
|
|
zh_symbols = [
|
|
"E",
|
|
"En",
|
|
"a",
|
|
"ai",
|
|
"an",
|
|
"ang",
|
|
"ao",
|
|
"b",
|
|
"c",
|
|
"ch",
|
|
"d",
|
|
"e",
|
|
"ei",
|
|
"en",
|
|
"eng",
|
|
"er",
|
|
"f",
|
|
"g",
|
|
"h",
|
|
"i",
|
|
"i0",
|
|
"ia",
|
|
"ian",
|
|
"iang",
|
|
"iao",
|
|
"ie",
|
|
"in",
|
|
"ing",
|
|
"iong",
|
|
"ir",
|
|
"iu",
|
|
"j",
|
|
"k",
|
|
"l",
|
|
"m",
|
|
"n",
|
|
"o",
|
|
"ong",
|
|
"ou",
|
|
"p",
|
|
"q",
|
|
"r",
|
|
"s",
|
|
"sh",
|
|
"t",
|
|
"u",
|
|
"ua",
|
|
"uai",
|
|
"uan",
|
|
"uang",
|
|
"ui",
|
|
"un",
|
|
"uo",
|
|
"v",
|
|
"van",
|
|
"ve",
|
|
"vn",
|
|
"w",
|
|
"x",
|
|
"y",
|
|
"z",
|
|
"zh",
|
|
"AA",
|
|
"EE",
|
|
"OO",
|
|
]
|
|
num_zh_tones = 6
|
|
|
|
# japanese
|
|
ja_symbols = [
|
|
"N",
|
|
"a",
|
|
"a:",
|
|
"b",
|
|
"by",
|
|
"ch",
|
|
"d",
|
|
"dy",
|
|
"e",
|
|
"e:",
|
|
"f",
|
|
"g",
|
|
"gy",
|
|
"h",
|
|
"hy",
|
|
"i",
|
|
"i:",
|
|
"j",
|
|
"k",
|
|
"ky",
|
|
"m",
|
|
"my",
|
|
"n",
|
|
"ny",
|
|
"o",
|
|
"o:",
|
|
"p",
|
|
"py",
|
|
"q",
|
|
"r",
|
|
"ry",
|
|
"s",
|
|
"sh",
|
|
"t",
|
|
"ts",
|
|
"ty",
|
|
"u",
|
|
"u:",
|
|
"w",
|
|
"y",
|
|
"z",
|
|
"zy",
|
|
]
|
|
num_ja_tones = 2
|
|
|
|
# English
|
|
en_symbols = [
|
|
"aa",
|
|
"ae",
|
|
"ah",
|
|
"ao",
|
|
"aw",
|
|
"ay",
|
|
"b",
|
|
"ch",
|
|
"d",
|
|
"dh",
|
|
"eh",
|
|
"er",
|
|
"ey",
|
|
"f",
|
|
"g",
|
|
"hh",
|
|
"ih",
|
|
"iy",
|
|
"jh",
|
|
"k",
|
|
"l",
|
|
"m",
|
|
"n",
|
|
"ng",
|
|
"ow",
|
|
"oy",
|
|
"p",
|
|
"r",
|
|
"s",
|
|
"sh",
|
|
"t",
|
|
"th",
|
|
"uh",
|
|
"uw",
|
|
"V",
|
|
"w",
|
|
"y",
|
|
"z",
|
|
"zh",
|
|
]
|
|
num_en_tones = 4
|
|
|
|
# combine all symbols
|
|
normal_symbols = sorted(set(zh_symbols + ja_symbols + en_symbols))
|
|
symbols = [pad] + normal_symbols + pu_symbols
|
|
sil_phonemes_ids = [symbols.index(i) for i in pu_symbols]
|
|
|
|
# combine all tones
|
|
num_tones = num_zh_tones + num_ja_tones + num_en_tones
|
|
|
|
# language maps
|
|
language_id_map = {"ZH": 0, "JP": 1, "EN": 2}
|
|
num_languages = len(language_id_map.keys())
|
|
|
|
language_tone_start_map = {
|
|
"ZH": 0,
|
|
"JP": num_zh_tones,
|
|
"EN": num_zh_tones + num_ja_tones,
|
|
}
|
|
|
|
if __name__ == "__main__":
|
|
a = set(zh_symbols)
|
|
b = set(en_symbols)
|
|
print(sorted(a & b))
|