litagin02
5fda2103ed
Merge pull request #89 from kale4eat/dev-pyopenjtalk-worker
...
複数プロセス利用時にユーザー辞書を活用するためのpyopenjtalk別プロセス化
2024-03-08 10:06:50 +09:00
tsukumi
70f8d53a1e
Add: empty __init__.py
2024-03-07 09:09:24 +00:00
tsukumi
e57cfbf072
Remove: remove currently unused code in style_bert_vits2/models/commons.py
2024-03-07 08:46:13 +00:00
tsukumi
bffd5a67bb
Fix: import error
2024-03-07 08:36:22 +00:00
tsukumi
f8f798d10a
Refactor: moved text/ to style_bert_vits2/text_processing/(language)/
2024-03-07 04:48:11 +00:00
tsukumi
d36401849b
Refactor: moved monotonic_align/ to style_bert_vits2/models/monotonic_alignment.py
2024-03-07 04:36:05 +00:00
tsukumi
1450bfd06f
Remove: remove webui.py, which is no longer maintained in Style-Bert-VITS2
...
Since app.py and server_editor.py already exist as alternative Web UI, there is no need to revive webui.py in the future.
2024-03-07 04:21:48 +00:00
tsukumi
def6d88425
Refactor: style_bert_vits2/text_processing/cleaner.py integrated into style_bert_vits2/text_processing/__init__.py
...
This was often used in 3 function sets and felt like a wasteful division with few lines.
2024-03-07 04:19:40 +00:00
tsukumi
b01168309d
Remove: remove currently unused code in utils.py
2024-03-07 04:08:56 +00:00
tsukumi
4f11b011fd
Refactor: minor adjustments
2024-03-07 03:54:02 +00:00
tsukumi
62919e904e
Refactor: moved the module for extracting BERT features from text in each language to style_bert_vits2/text_processing/(language)/bert_feature.py
2024-03-07 03:34:58 +00:00
tsukumi
c3c0dd8b32
Refactor: add style_bert_vits2/text_processing/bert_models.py to hold loaded BERT models/tokenizer and replace all from_pretrained() to load_model/load_tokenizer
2024-03-07 03:31:38 +00:00
kale4eat
2994873e38
add no client timeout
...
summarize the except statement at disconnection
2024-03-07 09:40:21 +09:00
tsukumi
e826faf62e
Refactor: moved text/cleaner.py to style_bert_vits2/text_processing/
2024-03-07 00:24:28 +00:00
tsukumi
89825e68d8
Refactor: moved model, attentions definitions and inference code to style_bert_vits2/models/
...
The code has not yet been cleaned up, just moved.
2024-03-06 23:43:25 +00:00
tsukumi
a52fda7a88
Refactor: moved common/subprocess_utils.py to style_bert_vits2/utils/subprocess.py
2024-03-06 23:11:27 +00:00
tsukumi
ca4c03c67b
Fix: import error
2024-03-06 23:03:06 +00:00
tsukumi
1936344c0c
Refactor: remove old code that can be deleted and update where modules are imported
2024-03-06 22:51:25 +00:00
tsukumi
f880641eb5
Remove: modules under common/ that have been rewritten
2024-03-06 22:29:12 +00:00
tsukumi
9546495434
Refactor: moved commons.py to style_bert_vits2/models/ and added type definitions and comments
2024-03-06 22:17:03 +00:00
tsukumi
46c83cf89a
Refactor: moved the user dictionary implementation ported from VOICEVOX to style_bert_vits2/text_processing/japanese/user_dict/
2024-03-06 22:16:42 +00:00
tsukumi
918d168ae7
Refactor: rewrote Japanese natural language processing code imported from server_editor.py
...
The logic has not been changed, only renaming, splitting and moving modules on a per-function basis.
Existing code will be left in place for the time being to avoid breaking the training code, which is not subject to refactoring this time.
2024-03-06 20:56:21 +00:00
kale4eat
419d0e5bed
Delete debugging traces
2024-03-06 22:38:44 +09:00
tsukumi
f26def4369
Remove: code that is not referenced anywhere
2024-03-06 12:39:24 +00:00
tsukumi
e4cd4f8423
Fix: ignore .venv/
2024-03-06 07:38:51 +00:00
kale4eat
ed90af1b87
Enhanced server error handling
...
Add signal handling for when the process is killed
2024-03-06 12:13:27 +09:00
kale4eat
45c6bde2e7
In Windows, create new console and hide it
...
Minor Correction:
* logging
* change status return type
2024-03-06 11:19:55 +09:00
kale4eat
2ab025d5fe
Run in a separate process group to avoid receiving signals by Ctrl + C
...
Minor Correction:
* logging
* declaration of terminate
2024-03-06 09:45:25 +09:00
kale4eat
98ff976ec0
modify logging
2024-03-05 15:04:27 +09:00
kale4eat
85f5b9bd25
replace pyopenjtalk import with worker
2024-03-05 12:18:05 +09:00
kale4eat
1eb8fb4b08
add openjtalk worker pkg
2024-03-05 12:17:15 +09:00
kale4eat
bc1058270c
Delete pyopenjtalk import
2024-03-05 12:16:14 +09:00
litagin02
81baabbb30
wip
2024-03-04 11:46:09 +09:00
litagin02
46935c6917
Try to fix encoding error
2024-03-01 20:35:12 +09:00
litagin02
8b17d4de32
Try to fix colab encoding error
2024-03-01 20:10:23 +09:00
litagin02
beb6a641be
clean
2024-03-01 19:39:37 +09:00
litagin02
f3475287b2
Improve: sort wav files before transcription, use pathlib
2024-03-01 19:25:21 +09:00
litagin02
3275124d42
Merge branch 'master' of github.com:litagin02/Style-Bert-VITS2
2024-03-01 10:03:23 +09:00
litagin02
7e4108add5
Try to fix colab encoding error
2024-03-01 10:03:02 +09:00
litagin02
fc049e1168
Merge pull request #82 from gordon0414/hparams-repo-id-integration
...
Fix AttributeError by adding missing 'repo_id' to HParams
2024-02-29 16:26:54 +09:00
Jungwon Chang
8fee645f8d
Fix AttributeError by initializing 'repo_id' in HParams for Hugging Face Hub uploads
2024-02-29 15:00:10 +09:00
litagin02
c86def5fdf
Merge pull request #81 from litagin02/dev
...
2.3.1
2024-02-27 20:56:47 +09:00
litagin02
76bfa51f4b
Add changelog, upd dockerignore
2024-02-27 20:48:38 +09:00
litagin02
512423c41d
Fix colab, improve yomi_error doc, CLI yomi_error option
2024-02-27 19:07:24 +09:00
litagin02
abd5347f13
Merge pull request #75 from frodo821/master
...
モデルのマージに球面線形補間を使えるようにした
2024-02-27 18:13:45 +09:00
litagin02
e077fd60a9
Merge branch 'master' into dev
2024-02-27 13:44:57 +09:00
litagin02
ebea1be519
Refactor and improve: handling with yomi error, add preprocess options
2024-02-27 13:37:24 +09:00
frodo821
a48e5cbc51
スタイルロード時にデフォルトですべての組み合わせが入るようにした
2024-02-27 04:39:09 +09:00
frodo821
d0b5bc8682
モデルのマージに球面線形補間を使えるようにした
2024-02-27 04:38:47 +09:00
litagin02
3a1dc7c58f
Fix using path instead of str
2024-02-26 21:27:02 +09:00
