Dev emo (#171)
* 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>
This commit is contained in:
Stardust·减
@@ -266,15 +266,16 @@ rep_map = {
|
||||
"？": "?",
|
||||
"\n": ".",
|
||||
"．": ".",
|
||||
"...": "…",
|
||||
"···": "…",
|
||||
"・・・": "…",
|
||||
"…": "...",
|
||||
"···": "...",
|
||||
"・・・": "...",
|
||||
"·": ",",
|
||||
"・": ",",
|
||||
"、": ",",
|
||||
"$": ".",
|
||||
"“": "'",
|
||||
"”": "'",
|
||||
'"': "'",
|
||||
"‘": "'",
|
||||
"’": "'",
|
||||
"（": "'",
|
||||
@@ -317,6 +318,7 @@ def text_normalize(text):
|
||||
res = japanese_convert_numbers_to_words(res)
|
||||
# res = "".join([i for i in res if is_japanese_character(i)])
|
||||
res = replace_punctuation(res)
|
||||
res = res.replace("゙", "")
|
||||
return res
|
||||
|
||||
|
||||
@@ -340,7 +342,7 @@ def handle_long(sep_phonemes):
|
||||
return sep_phonemes
|
||||
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("./bert/deberta-v2-large-japanese")
|
||||
tokenizer = AutoTokenizer.from_pretrained("./bert/deberta-v2-large-japanese-char-wwm")
|
||||
|
||||
|
||||
def align_tones(phones, tones):
|
||||
@@ -365,9 +367,35 @@ def align_tones(phones, tones):
|
||||
return res
|
||||
|
||||
|
||||
def rearrange_tones(tones, phones):
|
||||
res = [0] * len(tones)
|
||||
for i in range(len(tones)):
|
||||
if i == 0:
|
||||
if tones[i] not in punctuation:
|
||||
res[i] = 1
|
||||
elif tones[i] == prev:
|
||||
if phones[i] in punctuation:
|
||||
res[i] = 0
|
||||
else:
|
||||
res[i] = 1
|
||||
elif tones[i] > prev:
|
||||
res[i] = 2
|
||||
elif tones[i] < prev:
|
||||
res[i - 1] = 3
|
||||
res[i] = 1
|
||||
prev = tones[i]
|
||||
return res
|
||||
|
||||
|
||||
def g2p(norm_text):
|
||||
sep_text, sep_kata, acc = text2sep_kata(norm_text)
|
||||
sep_tokenized = [tokenizer.tokenize(i) for i in sep_text]
|
||||
sep_tokenized = []
|
||||
for i in sep_text:
|
||||
if i not in punctuation:
|
||||
sep_tokenized.append(tokenizer.tokenize(i))
|
||||
else:
|
||||
sep_tokenized.append([i])
|
||||
|
||||
sep_phonemes = handle_long([kata2phoneme(i) for i in sep_kata])
|
||||
# 异常处理，MeCab不认识的词的话会一路传到这里来，然后炸掉。目前来看只有那些超级稀有的生僻词会出现这种情况
|
||||
for i in sep_phonemes:
|
||||
@@ -383,6 +411,7 @@ def g2p(norm_text):
|
||||
aaa = distribute_phone(phone_len, word_len)
|
||||
word2ph += aaa
|
||||
phones = ["_"] + [j for i in sep_phonemes for j in i] + ["_"]
|
||||
# tones = [0] + rearrange_tones(tones, phones[1:-1]) + [0]
|
||||
tones = [0] + tones + [0]
|
||||
word2ph = [1] + word2ph + [1]
|
||||
assert len(phones) == len(tones)
|
||||
|
||||
Reference in New Issue
Block a user