tuna2134/sbv2-v2
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity
1,081 Commits 2 Branches 0 Tags
94e29d1337b44481c0082cdff78f9eb4f9c17ca2
Commit Graph

1081 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
litagin02
3c1269e520 Add library usage example notebook 2024-03-13 15:41:46 +09:00
litagin02
cd02238b28 Add POST method to server_fastapi.py 2024-03-13 15:28:23 +09:00
litagin02
55c3847176 Add POST method for /voice in server_fastapi.py 2024-03-13 15:26:30 +09:00
litagin02
c028840794 Merge pull request #93 from litagin02/dev-refactor 
Dev refactor
 2024-03-13 15:12:02 +09:00
litagin02
bfcf5091ed Fix running server_editor.py in bat (and dev ver) 2024-03-13 15:07:01 +09:00
litagin02
bc89fde15e Delete local_dir_use_symlinks=False 2024-03-13 14:55:42 +09:00
tsukumi
9e5222619f Refactor: No preloading of BERT models to avoid unnecessary GPU VRAM consumption during training in the Web UI 
Since the BERT features of the dataset are pre-extracted by bert_gen.py, there is no need to load the BERT model at training time.
 2024-03-13 12:09:11 +09:00
litagin02
8baecb138a Skip cuda test 2024-03-13 11:54:24 +09:00
litagin02
c37893a76b Add version suffix dev0 2024-03-13 11:46:56 +09:00
litagin02
28fd715cb8 Restore gc empty_cache in train_ms_jp 2024-03-13 10:25:22 +09:00
litagin02
30d9f2e258 Merge pull request #95 from zunan-islands/dev-refactor 
細かな修正 (#92 を参照)
 2024-03-13 09:45:55 +09:00
tsukumi
fedd019c04 Revert "Refactor: No preloading of BERT models to avoid unnecessary GPU VRAM consumption during training in the Web UI" 
This reverts commit e8a76e547b.
 2024-03-12 19:01:45 +00:00
tsukumi
c4d6a8cdb7 Fix: large number of unnecessary files in built sdist 
Include in sdist only the minimum required files for style-bert-vits2 as a library.
 2024-03-12 18:45:54 +00:00
tsukumi
07d246b98b Refactor: run "hatch run style:fmt" 2024-03-12 18:27:08 +00:00
tsukumi
e8a76e547b Refactor: No preloading of BERT models to avoid unnecessary GPU VRAM consumption during training in the Web UI 
Since the BERT features of the dataset are pre-extracted by bert_gen.py, there is no need to load the BERT model at training time.
 2024-03-12 18:22:34 +00:00
tsukumi
483bc68d57 Refactor: unify invoke format of open() function 2024-03-12 18:00:51 +00:00
tsukumi
74af2c831c Add: cache_dir and revision optional arguments to load_model() / load_tokenizer() 2024-03-12 17:45:10 +00:00
litagin02
69225a3e13 Style 2024-03-12 21:47:59 +09:00
litagin02
6e4dcf0232 Add Data, model_assets to toplevel gitignore 2024-03-12 21:38:27 +09:00
litagin02
bdf394d2c2 Fix: migration to new TTSModelHolder 2024-03-12 20:56:50 +09:00
litagin02
528d2cc4ba Refactor: typing and pathlib 2024-03-12 20:05:32 +09:00
litagin02
f12f20f3da Rollback of SAFE_STDOUT debug 2024-03-12 19:13:13 +09:00
litagin02
4acfc2977e Ensure to write use_jp_extra option to config.json 2024-03-12 19:10:43 +09:00
litagin02
456fe00ae4 Delete old webui bat files 2024-03-12 17:51:09 +09:00
litagin02
77ee026ab6 Update .dockerignore 2024-03-12 17:47:00 +09:00
litagin02
dfb4513ea7 Change default port to None to avoid conflicting 2024-03-12 17:29:24 +09:00
litagin02
005706a456 Fix: colab notebook for 2.4 2024-03-12 17:26:03 +09:00
litagin02
3632d476c1 Clean 2024-03-12 15:24:42 +09:00
litagin02
bc0729d970 Fix: initialize worker and dict for use 2024-03-12 15:23:18 +09:00
litagin02
7736532c75 Match config.json values to default hyper_parameters.py 2024-03-11 17:56:09 +09:00
litagin02
b3cc705caa Fix: add use_jp_extra parameter to config.json (for non-jp-extra training) 2024-03-11 17:51:55 +09:00
litagin02
44851a6219 Clean and fix docs 2024-03-11 17:05:42 +09:00
litagin02
791b663658 Merge pull request #90 from aka7774/master 
/voice method GET to POST
 2024-03-11 13:00:32 +09:00
litagin02
dada0af2b6 Format import using isort --profile black --gitignore --lai 2 . 2024-03-11 12:37:51 +09:00
litagin02
164b5c4a85 Clean unused tools module (previously used in webui.py) 2024-03-11 10:33:00 +09:00
litagin02
c776c08235 Apply black formatter 2024-03-11 09:47:47 +09:00
litagin02
42ee7d7608 Fix: ensure encoding utf-8 2024-03-11 09:27:36 +09:00
litagin02
03d4b4c97e Merge pull request #92 from zunan-islands/dev 
コードベースを大規模にリファクタリングし、ライブラリ (Python パッケージ) としてほかの Python コードから利用できるように改善
 2024-03-11 09:10:11 +09:00
tsukumi
7f02b0f1d5 Refactor: TTSModelInfo changed from TypedDict to Pydantic model 
Pydantic models are more robust and properties can be accessed by dots.
 2024-03-10 19:21:22 +00:00
tsukumi
859d940916 Fix: failed to start training 2024-03-10 19:15:24 +00:00
tsukumi
be265d42ed Improve: switch pyworld to pyworld-prebuilt and enable it by default 
Prebuilt wheels for almost every OS/architecture (except musl) are now available on PyPI, eliminating the need for a build environment.
ref: https://pypi.org/project/pyworld-prebuilt/
 2024-03-10 18:11:15 +00:00
tsukumi
733a9d838d Fix: clearly include Pydantic v2 in the dependencies 
The Pydantic models in the library are written for Pydantic v2 and will not work with Pydantic v1.
 2024-03-10 15:38:08 +00:00
tsukumi
9c233630ef Refactor: don't keep models in bert_feature module for each language 
BERT models and tokenizers are already stored and managed in the bert_models module and should not be stored here.
In addition, since there may be situations where the user would like to use cpu instead of mps for inference when using it as a library, the automatic switching process to mps was removed.
 2024-03-10 14:18:57 +00:00
tsukumi
00bf496325 Add: VSCode settings 
Enabling type checking with Pylance.
 2024-03-10 13:51:56 +00:00
tsukumi
cdc47a98ce Improve: test code 2024-03-10 11:16:09 +00:00
tsukumi
84b1dbe1b5 Fix: problem with test failures 
Style-Bert-VITS2 has been reported to not work with some PyTorch 2.2 series, but Python 3.12 is only supported in Torch >= 2.2, so Python 3.12 support is not provided for the time being
 2024-03-10 10:48:21 +00:00
tsukumi
afff154da4 Add: test code for style-bert-vits2 as a library 
By executing "hatch run test:test", you can check whether the test passes in all Python 3.9 to 3.12 environments.
 2024-03-10 04:18:39 +00:00
tsukumi
d2fd378b56 Refactor: rename Model / ModelHolder to TTSModel / TTSModelHolder for clarification and add comments to each method 2024-03-10 03:47:17 +00:00
tsukumi
b7d7c78203 Refactor: when pyopenjtalk_worker is called without initialization, continue processing without a worker 
When using style-bert-vits2 as a library, the requirement to be able to launch it in multiple processes may not be necessary. Also, if the library is embedded and exe-ed using PyInstaller or similar, it is difficult to make pyopenjtalk_worker run in a separate process.
Therefore, we changed it so that the worker is used only when it is explicitly initialized.
 2024-03-10 03:04:27 +00:00
tsukumi
a79b1910fb Add: use hatch to build style-bert-vits2 as a library 2024-03-09 18:38:16 +00:00