6444839ec0
Update requirements.txt
2023-04-28 11:27:00 +08:00
8a4fdd263a
Update requirements.txt
2023-04-28 10:39:41 +08:00
0fe10b449e
Update preprocess_v2.py
2023-04-25 14:19:19 +08:00
f8b398f587
rearranged repo
2023-04-22 09:51:41 +08:00
3d7e4220d4
rearranged repo
2023-04-21 21:39:41 +08:00
2612e5dbcc
rearranged repo
2023-04-21 21:19:26 +08:00
eb7eb8a022
rearranged repo
2023-04-21 21:17:45 +08:00
05dbf649a1
Merge remote-tracking branch 'origin/main'
2023-04-21 20:43:12 +08:00
e33f8919d0
added new base model (pure Chinese)
2023-04-21 20:43:02 +08:00
8e1893daf7
Update cleaners.py
2023-04-20 15:19:52 +08:00
b3e7ad0e50
Update download_video.py
2023-04-19 17:24:39 +08:00
b35f4bc727
Merge pull request #187 from huangynn/patch-1
...
Update download_video.py
2023-04-18 15:40:25 +08:00
2f9f7c4b31
Update download_video.py
...
solve SSL: CERTIFICATE_VERIFY_FAILED problem
2023-04-17 16:27:57 +08:00
8160bd71d0
Merge pull request #180 from himekifee/main
...
Discord link
2023-04-15 18:43:12 +08:00
2c1276b8d9
Discord link
2023-04-15 09:22:27 +01:00
1f19649e92
Update long_audio_transcribe.py
2023-04-12 14:02:40 +08:00
0f1fc8cb99
Update requirements.txt
2023-04-11 15:12:51 +08:00
4f316f2f64
Update mel_processing.py
2023-04-04 18:47:20 +08:00
c90fb9f63c
Merge pull request #148 from RealityError/main
...
用命令行方法生成VITS语音
2023-04-04 12:55:39 +08:00
02e3fd0a09
Update requirements.txt
2023-04-04 12:46:50 +08:00
41173bfec7
Adaptation to torch 2.0
2023-04-04 12:32:10 +08:00
c4ab2501e4
提交命令行生成
...
命令行生成语音文件
2023-04-04 11:59:01 +08:00
ff4078c098
Update requirements.txt
2023-03-21 21:34:19 +08:00
7b4273f514
Update DATA.MD
2023-03-14 15:17:44 +08:00
cbadc7c0db
Update README_ZH.md
2023-03-14 10:42:14 +08:00
56972cc455
Update README.md
2023-03-14 10:41:02 +08:00
94a36f612f
Merge remote-tracking branch 'origin/main'
2023-03-09 13:22:40 +08:00
0630c258ea
changed num_workers
2023-03-09 13:22:27 +08:00
d79aadb786
Added additional instructions for MoeGoe usage
2023-03-09 12:49:20 +08:00
aa01f7b73e
Merge pull request #76 from lrioxh/main
...
中英日韩文本加tag
2023-03-07 13:37:39 +08:00
eff14d53e5
fix inference UI
2023-03-07 10:36:02 +08:00
d06efc5fe7
fix inference UI
2023-03-07 10:23:41 +08:00
e7f0574fc8
Add tags via re
2023-03-07 09:58:05 +08:00
5aea258e26
Add tags via re
2023-03-07 09:44:43 +08:00
ea491a457f
Add tags via re
2023-03-07 09:39:56 +08:00
5093ba0b9a
supported auxiliary data for CJ model
2023-03-06 21:00:40 +08:00
bbe2638855
Merge remote-tracking branch 'origin/main'
2023-03-06 16:21:20 +08:00
8a04e3e824
bug fix
2023-03-06 16:21:10 +08:00
fbe46caa3d
Add files via upload
2023-03-05 16:33:29 +08:00
1fa2fa8642
Update video2audio.py
2023-03-05 16:25:52 +08:00
1698f0dd8a
Update download_video.py
2023-03-05 16:25:38 +08:00
11b2ea0f88
Merge pull request #60 from eve2ptp/main
...
multithreading event
2023-03-05 16:25:14 +08:00
4a17d6580c
Delete denoise_audio.py
2023-03-05 16:18:39 +08:00
4c45e6a74c
multithreading event
2023-03-05 14:55:32 +08:00
de2a885ab2
will print transcribed text from long audios
2023-03-04 19:02:57 +08:00
f45e33c1ad
Merge remote-tracking branch 'origin/main'
2023-03-04 14:09:44 +08:00
15c4db56ba
will print transcribed text from long audios
2023-03-04 14:09:30 +08:00
da3670a2d8
Merge pull request #49 from BushyToaster88/fix-torch-stft-error-on-gpus-sm-53
...
fix-torch-stft-error-on-gpus-sm-53
2023-03-03 14:10:23 +08:00
b92361b99f
fix-torch-stft-error-on-gpus-sm-53
...
This pull request addresses an issue that arises when executing the finetune_speaker_v2.py script on GPUs with compute capability less than SM_53. The error occurs at line 104 of mel_processing.py, where the torch.stft() function is called with a half data type. To fix this, I updated the data type to float.
2023-03-03 16:17:28 +11:00
8137fb9e06
Merge pull request #44 from justinjohn0306/main
...
Use gloo backend on Windows for Pytorch
2023-03-02 16:50:40 +08:00
Songting