tsukumi
b7cd512978
Fix: During ONNX inference, the tensor of the return value of the tokenizer is now obtained in Numpy's NDArray format to eliminate the dependency on PyTorch
2024-09-23 07:40:17 +09:00
tsukumi
dcca37b9a8
Add: Support for speech synthesis in English and Chinese for ONNX inference in Non-JP-Extra models
2024-09-23 07:14:44 +09:00
tsukumi
fe253611d3
Fix: nltk to 3.8.1 or lower
...
Due to reports that updating nltk to 3.8.2 or later significantly slows down learning, including English.
2024-09-23 06:22:47 +09:00
tsukumi
db0acd7b5f
Add: Support for ONNX inference and ONNX conversion of Non-JP-Extra models
2024-09-23 05:59:12 +09:00
tsukumi
cc1d6120fe
Fix: Default value of False for compatibility with older models where the HyperParameters.data.use_jp_extra field does not exist
...
JP-Extra models always have use_jp_extra=True, but non-JP-Extra models do not always.
2024-09-23 05:26:19 +09:00
tsukumi
0e0b4bea31
Fix: Disable optimization on InferenceSession initialization to speed up loading of ONNX models
2024-09-22 23:08:00 +09:00
tsukumi
16115a366b
Improve: .safetensors models under a directory specified with --model can be automatically converted to ONNX
2024-09-22 16:37:15 +09:00
tsukumi
291e635e9e
Improve: ONNX conversion logic improved, and support for noise_scale(_w) model argument
2024-09-22 16:14:25 +09:00
tsukumi
9b27ba9777
Improve: Graphical display of ONNX conversion script logs
2024-09-18 06:11:10 +09:00
tsukumi
449927616a
Fix: Suppress many warning logs
2024-09-18 05:48:37 +09:00
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
