b186499ae9
* SYNC CHANGE TO EMO BRANCH (#162) * Update README.md * 更新 bert_models.json * fix * Update data_utils.py * Update infer.py * performance improve * Feat: support auto split in webui (#158) * Feat: support auto split in webui * [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> * Fix: change /voice api to post (#160) * Fix: change /voice api to post * Fix: support /voice api get * Fix: Add missing torch.cuda.empty_cache() (#161) --------- Co-authored-by: Sora <atri@suzakuintsubaki.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Artrajz <969242373@qq.com> * sync (#163) * Update README.md * 更新 bert_models.json * fix * Update data_utils.py * Update infer.py * performance improve * Feat: support auto split in webui (#158) * Feat: support auto split in webui * [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> * Fix: change /voice api to post (#160) * Fix: change /voice api to post * Fix: support /voice api get * Fix: Add missing torch.cuda.empty_cache() (#161) * del emo * del emo * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: Sora <atri@suzakuintsubaki.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Artrajz <969242373@qq.com> * Add files via upload * Update infer.py * add emo * add emo * Update default_config.yml * Fix slice segments GPU perf (#165) * Fix slice segments GPU perf * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update commons.py --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Update infer.py * Update models.py * Update infer.py * remove spec cache * Update data_utils.py * Update data_utils.py * Update train_ms.py * Revert "Fix slice segments GPU perf (#165)" (#169) This reverts commit 28430fc76bc628297bb59d8f8d25100dbe46ab59. * Update train_ms.py * Update train_ms.py * Update data_utils.py * Update data_utils.py * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update train_ms.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update default_config.yml * Switch to Japanese wwm DeBERTa (#172) * Switch to Japanese wwm DeBERTa * [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> * Fix wrong ellipsis g2p (#173) * Switch to Japanese wwm DeBERTa * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix ellipsis g2p * [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> * Add files via upload * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix English phones not aligned with BERT features (#174) * Fix English phones not aligned with BERT features * [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> * Fix english bert gen (#175) * Update webui.py * Update webui.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add NCCL timeout * Update train_ms.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update train_ms.py * Update default_config.yml * Update infer.py * Update models.py * Update train_ms.py * Update infer.py * Update emo_gen.py * Feat: Support load and infer 2.0 models (#178) * Feat: Support load and infer 2.0 models * [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> * 复用相同逻辑，修正静音添加错误 (#181) * Refactor: reuse the same part of voice api. * Fix: server_fastapi.py * Update train_ms.py * Update data_utils.py * Update data_utils.py * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update data_utils.py * Update data_utils.py * Add files via upload * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update default_config.yml * Update utils.py * Update train_ms.py * Update utils.py * Update default_config.yml * Update data_utils.py * Update default_config.yml * Update train_ms.py * Update train_ms.py * Update config.py * Update utils.py * Update train_ms.py * Update train_ms.py * feat: add voice mix and tone mix (#187) * feat: add voice mix and tone mix * [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> Co-authored-by: Stardust·减 <star_dust_chen@foxmail.com> * 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: Sora <atri@suzakuintsubaki.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Artrajz <969242373@qq.com> Co-authored-by: Leng Yue <lengyue@lengyue.me> Co-authored-by: OedoSoldier <31711261+OedoSoldier@users.noreply.github.com> Co-authored-by: 潮幻Mark <sunyunfei201@gmail.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))
|