tsukumi
fa7123c422
Fix: ONNX BERT model/tokenizer is not preloaded by default to avoid wasting VRAM
2024-09-18 05:11:15 +09:00
tsukumi
7d721fdf2b
Fix: CUDAExecutionProvider was not being used to infer Style-Bert-VITS2 ONNX models even though CUDA was available
2024-09-18 04:37:23 +09:00
tsukumi
5e2c83c6c7
Improve: Support ONNX inference, add ONNX conversion script
2024-09-17 16:55:03 +09:00
tsukumi
80dd6dbc22
Improve: Use the device_map option in transformers to load BERT models directly to the GPU
2024-09-17 05:22:06 +09:00
litagin02
ab158d1a7b
Change to manually download default models instead of auto
2024-06-02 15:31:55 +09:00
litagin02
f10dade139
Add uv pip install pip
2024-06-01 21:22:59 +09:00
litagin02
1b656b37fa
Feat: koharune-ami
2024-05-26 17:17:32 +09:00
litagin02
2274087da4
Fmt only (maybe)
2024-05-25 18:15:36 +09:00
litagin02
8976a3ed2f
Refactor: Use PathConfig and pathlib instead of paths.yml loading
2024-05-25 10:25:22 +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
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
tsukumi
c594f7ea7a
Refactor: change execution location of pyopenjtalk.initialize()
...
Considering library design, this function with many side effects should not be executed in a library.
2024-03-09 00:26:51 +00:00
tsukumi
d22a11ebb2
Fix: a bug that prevented speech synthesis in app.py
2024-03-08 22:09:47 +00:00
tsukumi
fe7e31e080
Refactor: moved common/tts_model.py to style_bert_vits2/
2024-03-08 09:34:44 +00:00
tsukumi
a672aeefd9
Fix: maintain compatibility with Python 3.9
2024-03-08 08:45:56 +00:00
tsukumi
fac4f9a8ab
Refactor: rename text_processing to nlp
...
"text_processing" is clearer, but the import statement is longer.
"nlp" is shorter and makes it clear that it is natural language processing.
2024-03-08 06:20:44 +00:00
tsukumi
8add1b4202
Fix: maintain compatibility with Python 3.9
2024-03-08 06:14:50 +00:00
tsukumi
da7747cc67
Merge branch 'dev' of github.com:litagin02/Style-Bert-VITS2
2024-03-08 05:49:52 +00:00
litagin02
25ed226acb
Add speaker list api
2024-03-08 11:19:03 +09:00
tsukumi
f8f798d10a
Refactor: moved text/ to style_bert_vits2/text_processing/(language)/
2024-03-07 04:48:11 +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
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
bc1058270c
Delete pyopenjtalk import
2024-03-05 12:16:14 +09:00
litagin02
ebea1be519
Refactor and improve: handling with yomi error, add preprocess options
2024-02-27 13:37:24 +09:00
litagin02
8caa895a6f
Maybe v2.3
2024-02-26 15:10:00 +09:00
litagin02
a6ae2bd15a
Add text_normalize api
2024-02-26 01:49:06 +09:00
litagin02
f749950be2
Update
2024-02-25 22:28:02 +09:00
litagin02
e76dca6fbb
Update dict api
2024-02-25 13:15:00 +09:00
litagin02
1dac495be1
Add line length count limit option
2024-02-23 21:39:21 +09:00
litagin02
20b3326b79
Update editor server
2024-02-23 20:34:16 +09:00
litagin02
337ca71ec2
Add downloading front build zip
2024-02-23 16:19:15 +09:00
litagin02
e16cdad6e9
Feat: add editor server backend
2024-02-23 13:21:14 +09:00
