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
327e038977
Improve: I/O binding during ONNX inference
...
I honestly don't see a big difference...
2024-09-18 04:49:56 +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
e5a05a30cb
Improve: Outputs model load time and inference time
2024-09-17 18:37:00 +09:00
tsukumi
b95420325b
Improve: Changed PyTorch to an optional dependency when used style_bert_vits2 as a library
...
ONNXRuntime has relied on CUDA 12.x / cuDNN 9.x by default since v1.19.0, while PyTorch finally supports cuDNN 9 since v2.4.0.
Therefore, unless the pinning of torch<2.4 is eliminated, CUDA cannot be used with the latest version of ONNXRuntime.
2024-09-17 17:56:59 +09:00
tsukumi
5e2c83c6c7
Improve: Support ONNX inference, add ONNX conversion script
2024-09-17 16:55:03 +09:00
tsukumi
f42b9f0f89
Fix: vocab.txt
2024-09-17 13:44:21 +09:00
tsukumi
9de6e04ad7
Add: Preparation for ONNX inference support ④
2024-09-17 13:25:17 +09:00
tsukumi
ebd4551d1e
Add: Preparation for ONNX inference support ③
2024-09-17 09:16:16 +09:00
tsukumi
b9fdeb4492
Add: Preparation for ONNX inference support ②
2024-09-17 09:02:14 +09:00
tsukumi
eede796c4e
Add: Preparation for ONNX inference support ①
2024-09-17 06:53:11 +09:00
tsukumi
a037b955ac
Refactor: run "hatch run style:fmt"
2024-09-17 05:25:29 +09:00
tsukumi
7c5e839e82
Fix: Converts the given “N” phoneme to “n” when use_jp_extra=False
...
Non-JP-Extra pre-trained models (based on Bert-VITS2 v2.1) do not distinguish between “ん” and consonant “n” due to an implementation miss.
2024-09-17 05:24:16 +09:00
tsukumi
c140c0612a
Fix: Old comment
2024-09-17 05:23:57 +09:00
tsukumi
cfd6bd5bb6
Improve: Models can now be loaded directly onto NVIDIA GPUs
2024-09-17 05:23:02 +09:00
tsukumi
0e71d7ef7c
Fix: Specifying the device_map option in extract_bert_feature()
2024-09-17 05:22:30 +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
tsukumi
bdf20e8911
Refactor: Use bert_models.transfer_model()
2024-09-17 05:21:03 +09:00
tsukumi
f84d2ed48b
Add: Implement bert_models.transfer_model()
2024-09-17 05:19:44 +09:00
tsukumi
40d7ba9583
Fix: tests fail because scipy is not installed in the test environment
2024-09-17 05:19:21 +09:00
litagin02
bcc57e0cb9
docs
2024-09-09 17:30:17 +09:00
litagin02
83f09d5278
Fix: style_by_dirs in WebUI
2024-09-09 17:28:10 +09:00
litagin02
dc5f42e9a1
Fix: use python -m for scripts in gradio_tabs
2024-09-09 17:27:23 +09:00
litagin02
a9c5d18eec
Try to fix colab torch version
2024-09-09 16:30:44 +09:00
litagin02
38adf43924
Fix: colab torchvision bug, explicit torchaudio version
2024-09-09 15:31:30 +09:00
litagin02
a4e5955000
Fix torch<2.4
2024-07-27 12:47:42 +09:00
litagin02
7a99e3e1b7
Update requirements-colab.txt
2024-07-27 12:32:13 +09:00
litagin02
e8367cc4e2
Update requirements-infer.txt
2024-07-27 12:31:53 +09:00
litagin02
b441ff4401
Update requirements.txt
2024-07-27 12:31:29 +09:00
litagin02
1dcc3cbdab
Merge pull request #150 from aka7774/master
...
server_fastapi の /voice で model_name を指定できるようにした
2024-07-11 08:07:38 +09:00
aka7774
73519b41a5
/voice add model_name
2024-07-10 14:36:45 +09:00
litagin02
a8b8c760ff
Merge pull request #149 from Risenafis/merge-spk2id
...
マージ時にspk2idを設定する
2024-07-07 21:42:08 +09:00
Risenafis
ffa393a3d0
set spk2id when merge
2024-07-06 03:47:41 +09:00
litagin02
315360cc1e
Update README.md
2024-06-30 19:22:02 +09:00
litagin02
b6d09bad44
Fix: use sampler instead of batch_sampler for non-custom
2024-06-28 09:34:12 +09:00
litagin02
8832cfb4c9
Add playgrounds ignore
2024-06-28 09:19:28 +09:00
litagin02
1671967068
Style
2024-06-22 17:24:21 +09:00
litagin02
e78d2a6f7e
Feat: use DistributedLengthGroupedSampler (experimental, to be checked)
2024-06-22 17:21:58 +09:00
litagin02
c1381b2c49
Refactor a little
2024-06-22 17:10:44 +09:00
litagin02
402346e493
Fix mid_result assignment
2024-06-22 15:18:57 +09:00
litagin02
189998145d
Merge branch 'master' into dev
2024-06-22 14:57:14 +09:00
litagin02
9eab977138
Style
2024-06-22 14:54:47 +09:00
litagin02
a8f44649ed
Merge pull request #146 from liruk/alpha
...
音声合成画面において、複数のヌルモデルを実行時マージする機能を追加
2024-06-22 14:53:59 +09:00
liruk
b645de0750
ヌルモデル変更時にloadし直す用途で、推論時にforce_reload_modelを追加
2024-06-21 09:19:46 +09:00
liruk
7f2a4a8f3e
コード整理+暫定でヌルモデル使用時は常時load()するように
...
TODO:ヌルモデルの変更を検知できればそれがよさそう。
2024-06-21 09:07:09 +09:00
liruk
c957cab1e5
nullmodel数を増減させたときの問題を一部修正
...
1→0にした時の問題は未修正
2024-06-20 19:42:16 +09:00
liruk
fb99a776ce
推論時ヌルモデルマージ(できるけどバグバグ)
2024-06-19 18:31:27 +09:00
litagin02
50776dd8c0
Update FAQ.md
2024-06-19 08:36:52 +09:00
liruk
86c2a1b087
推論時ヌルモデルマージ(まだ動かないよ)
2024-06-18 19:15:20 +09:00
litagin02
a1fcb433e7
Fix numpy<2
2024-06-17 21:49:00 +09:00
