litagin02
5fa6210176
Batch sampler for backward compatibility, reduce tb log
2024-05-26 08:23:38 +09:00
litagin02
a92b0cabff
Improve: slice.py preserves subdir structure
2024-05-26 08:22:39 +09:00
litagin02
7880659d4a
Docs
2024-05-26 08:00:32 +09:00
litagin02
a4f28e4f6f
Improve download
2024-05-25 19:28:22 +09:00
litagin02
5af4e2c6ac
Feat: download model from hf
2024-05-25 19:05:06 +09:00
litagin02
2274087da4
Fmt only (maybe)
2024-05-25 18:15:36 +09:00
litagin02
acf93b80ce
Feat: make style vec by subdirs (for webui)
2024-05-25 18:13:34 +09:00
litagin02
175aa62a26
Feat: make style vectors w.r.t. subdirs structure
2024-05-25 17:14:28 +09:00
litagin02
0c87c6ffd4
Clean, and fix tensorboard protobuf bug
2024-05-25 15:58:19 +09:00
litagin02
8976a3ed2f
Refactor: Use PathConfig and pathlib instead of paths.yml loading
2024-05-25 10:25:22 +09:00
litagin02
2771fbd209
Fix gradio Path serialization error
2024-05-22 07:31:40 +09:00
litagin02
053a6bf785
Fix gradio Path serialize error
2024-05-19 18:31:45 +09:00
litagin02
0a3b57528b
Fix gradio import type annotation bug (temp solution)
2024-05-15 20:39:22 +09:00
litagin02
ac90941eaa
Remove gradio version restriction
2024-05-15 19:23:38 +09:00
litagin02
837c4397db
Merge pull request #118 from tsukumijima/dev
...
音声合成時に読み上げテキストの読みを表す音素列を指定する機能を追加 + 様々な改善
2024-05-15 07:37:46 +09:00
litagin02
ae7c4ea72b
Merge pull request #124 from gordon0414/eng_g2p_fix
...
Optimize English g2p function for improved speed and efficiency
2024-05-15 07:01:02 +09:00
tsukumi
44693e7d6b
Refactor: improve regular expression performance during NLP
...
Improve performance by pre-compiling regular expressions that are executed many times.
2024-05-12 17:53:30 +09:00
gordon0414
7de367b76f
moved tokenizer loading inside of g2p function for code integrity.
2024-05-10 11:55:38 +09:00
gordon0414
3018309199
Optimize g2p function for improved speed and efficiency
...
- Moved global variables (ARPA, _g2p, eng_dict, tokenizer) to top-level scope to avoid redundant initialization.
- Simplified conditions for words with apostrophes.
- Streamlined __post_replace_ph function by removing redundant checks.
- Optimized __refine_syllables function with direct iteration.
- Avoided re-initialization of tokenizer in __text_to_words by moving it to global scope.
- Added performance test in __main__ to validate improvements.
- Resolves issue #104 .
2024-05-09 16:12:15 +09:00
tsukumi
2d6baa3928
Fix: changed the substitute phoneme from「ん」to 「'」 when the pronunciation can't be obtained
2024-05-06 22:17:34 +09:00
tsukumi
87144dd321
Improve: automatically generate configs/paths.yml by copying it from configs/default_paths.yml when running initialize.py
...
If configs/paths.yml itself is included in version control, differences will occur when it is changed in each environment, which is troublesome.
2024-05-06 20:56:07 +09:00
tsukumi
b230832528
Add: allow hyper-parameters and style vectors to be specified directly
2024-05-06 20:43:22 +09:00
tsukumi
0d9034b8bd
Fix text encoding in Server.bat
2024-05-01 11:21:01 +09:00
tsukumi
3730eb50b7
Merge branch 'litagin02:dev' into dev
2024-05-01 10:56:42 +09:00
litagin02
e721c09b87
Fix filename for transcribe to use relative path instead of name
2024-04-27 12:59:47 +09:00
litagin02
9df344b995
Fix nested audio files bug
2024-04-27 12:50:00 +09:00
tsukumi
aa0f9308b1
Refactor: remove dependencies on libraries not required for style_bert_vits2 as a library
...
librosa: Originally not used under style_bert_vits2/.
pyannote.audio: Required only when using the "infer style vector from audio" function during inference, but it is currently almost unused.
scipy: Because it was used in only one utility function that was not needed outside of training.
2024-04-25 00:31:14 +00:00
litagin02
32145e18a3
Merge pull request #111 from hopto-dot/master
...
Add EN translation of Zennの解説記事 to README_en
2024-04-23 19:21:15 +09:00
tsukumi
28f254f449
Improve: remove Gradio dependency from style_bert_vits2 as a library
2024-04-23 05:45:11 +00:00
litagin02
f00344944d
Merge pull request #117 from aka7774/master
...
Add Server.bat
2024-04-22 21:39:57 +09:00
litagin02
a07609cb83
Merge pull request #115 from Naozumi520/patch-1
...
Removed a redundancy bracket in readme.md
2024-04-22 21:39:32 +09:00
tsukumi
9d15d5763d
Refactor: run "hatch run style:fmt"
2024-04-19 04:17:27 +00:00
tsukumi
797c354b1b
Add: the ability to specify a phoneme sequence representing the reading of the text to be read during speech synthesis
...
With this feature, it is possible to specify individual readings for homonyms such as "明日 (ashita/asu)" while maintaining the Kanji representation of the read text.
2024-04-19 04:09:21 +00:00
Aka Diffusion
590937d71b
Add files via upload
2024-04-16 14:52:03 +09:00
Naozumi
aba7814580
Removed a redundancy bracket in readme.md
...
It seems that a redundancy bracket was accidentally added :>
2024-04-12 13:41:57 +08:00
GC
556f8e49f3
fixed link to Style-Bert-VITS2_en.md
2024-04-04 12:53:28 +01:00
GC
f94896420c
Added article translation to en readme
2024-04-04 12:51:55 +01:00
GC
59063cde70
Added english translation of https://zenn.dev/litagin/articles/034819a5256ff4
2024-04-04 12:47:45 +01:00
JawGBoi
18876a077a
Delete Style-Bert-VITS2 JP-Extra (EN).md
2024-04-04 12:45:09 +01:00
JawGBoi
962ea6aee2
Added translation of article
...
Added translation of 「Style-)Bert-VITS2 JP-Extra (日本語特化版)について」
「(Style-)Bert-VITS2 JP-Extra (日本語特化版)について」記事の英語翻訳を追加
2024-04-04 12:43:29 +01:00
litagin02
7a34fd24c1
Fix gradio ver for json serialize error
2024-03-29 21:51:04 +09:00
litagin02
6d5b854cf2
Fix: invalid path for generating neutral style
2024-03-22 15:54:22 +09:00
litagin02
4afe92d75f
Fix: gen style in beginning of train for nested folders
2024-03-22 08:27:43 +09:00
litagin02
d7a3e5696c
docs
2024-03-19 20:16:07 +09:00
litagin02
70d252bcc7
Feat: preserve relative path when resample
2024-03-19 20:14:19 +09:00
litagin02
7c484c7835
Powershell version
2024-03-19 08:51:41 +09:00
litagin02
8c9eb74335
Fix colab
2024-03-18 09:02:50 +09:00
litagin02
8d6eec9d1b
docs
2024-03-16 20:25:15 +09:00
litagin02
defb5253aa
Fix errorcheck
2024-03-16 18:41:29 +09:00
litagin02
251b075942
Remove debug pause
2024-03-16 18:27:28 +09:00
