Commit Graph

374 Commits

Author SHA1 Message Date
jerrister
5aa4766033 Fix sample timesteps 2024-11-26 14:03:00 +08:00
Yushen CHEN
c9b4d43a2b Merge pull request #520 from haydonryan/main
Add output filename parameter to infer_cli.
2024-11-24 12:09:28 +08:00
Yushen CHEN
f1b44e9943 Update infer_cli.py; minor update, remove duplicate print 2024-11-24 12:03:33 +08:00
Haydon Ryan
6b72d67270 Adding parameter for output filename. Closes #519 2024-11-23 17:57:41 -06:00
Haydon Ryan
9c2a51e4cc Fixing incorrect parameter help text 2024-11-23 16:26:49 -06:00
ZhikangNiu
65be707aa9 update load local vocoder in trainer 2024-11-23 18:52:38 +08:00
Yushen CHEN
934592adcb Merge pull request #516 from SWivid/bugfix/fix-vocoder-bug
fix vocoder generate sample and #467
2024-11-23 18:41:24 +08:00
Yushen CHEN
c65b9d380d Update trainer.py 2024-11-23 18:31:58 +08:00
ZhikangNiu
ec3bb7b62d fix vocoder generate sample and #467 2024-11-23 18:20:28 +08:00
Zhikang Niu
8ee20d39b4 Update Dockerfile 2024-11-23 00:09:02 +08:00
ZhikangNiu
58f78353d3 update prepare libritts script 2024-11-23 00:03:43 +08:00
ZhikangNiu
837c158573 update bigvgan Dockerfile 2024-11-23 00:03:17 +08:00
ZhikangNiu
07c181bb57 fix #510 2024-11-22 23:17:41 +08:00
Yushen CHEN
ab2ad3b005 Update README.md 2024-11-20 00:52:56 +08:00
Yushen CHEN
f9733bf16f Update README.md 2024-11-20 00:41:13 +08:00
Yushen CHEN
eb84cbab0f Merge pull request #487 from mame82/issue-480
Fixes both issues from #480
2024-11-19 15:39:39 +08:00
mame82
7895721ff8 Fixes both issues from #480 2024-11-18 20:13:25 +01:00
SWivid
194bf1e853 formatting 2024-11-18 22:33:13 +08:00
Yushen CHEN
058b4461be Merge pull request #485 from atlonxp/main
Update dataset.py, change recursive __getitem__ to while loop; fix finetune_gradio.py #480
2024-11-18 22:31:36 +08:00
Yushen CHEN
5f7944a748 Update dataset.py, formatting 2024-11-18 22:28:03 +08:00
atlonxp
07b100e96f Update get_random_sample_transcribe when absolute path is used in finetune_gradio.py
Update `get_random_sample_transcribe` to handle absolute paths in `finetune_gradio.py`

- Added support for processing absolute file paths during transcription.
- Updated logic to correctly handle and return audio file paths with absolute URLs.
- Example use case: URLs like `https://localhost:55555/speech/150/150896/150-150896-40.wav.wav`.
- Correct one should be: `https://localhost:55555/speech/150/150896/150-150896-40.wav`.
2024-11-18 21:08:49 +07:00
atlonxp
14e923a427 Update dataset.py
change recursive approach to while loop, avoiding potential memory leak.
2024-11-18 20:53:47 +07:00
Yushen CHEN
5cc02536a6 Merge pull request #473 from tjb4578/bugfix/socket-server-repeated-final-chunk
Removed redundant final chunk logic from socket_server.py
2024-11-18 16:25:10 +08:00
SWivid
84db0029ce fix. 476#issuecomment-2481877878 2024-11-18 13:16:25 +08:00
SWivid
cb8ce3306d update. compatibility with mps device #477 thanks to @aboutmydreams 2024-11-17 18:57:28 +08:00
SWivid
0f80f25c5f minor fix. speech_edit & eval_infer_batch 2024-11-17 06:25:07 +08:00
SWivid
4b9441f8e0 minor update 2024-11-17 05:54:57 +08:00
Yushen CHEN
333d99ab6c Merge pull request #476 from lpscr/main
add in gradio finetune 8bit value fix some stuff and add new transcripe into easy
2024-11-17 00:46:38 +08:00
unknown
96946f85fa import transcribe from utils_infer 2024-11-16 18:39:52 +02:00
unknown
c4d7252cf8 remove the get_nested_value no use 2024-11-16 18:34:20 +02:00
unknown
bb4d538dc5 add transcribe function 2024-11-16 18:26:42 +02:00
unknown
e636d98090 add transcribe function 2024-11-16 18:18:42 +02:00
unknown
96e24d3605 add 8bit and fix some value 2024-11-16 18:17:51 +02:00
unknown
1bbec4ac7e add 8bit and fix some value 2024-11-16 18:06:45 +02:00
Tyler Banks
829d265ee1 Removed redundant final chunk logic
Handle socket server edge case
2024-11-15 23:33:04 -05:00
SWivid
2a844ae064 minor update patch-1 2024-11-15 19:15:34 +08:00
SWivid
6f13ad4349 minor update 2024-11-15 18:50:35 +08:00
Yushen CHEN
ecbf6447dd Merge pull request #469 from JarodMica/main_repo_update
Allow for local path specification of HF models/repos
2024-11-15 18:22:06 +08:00
Jarod Mica
334367d070 Add JA model to SHARED.md 2024-11-15 02:10:33 -08:00
Jarod Mica
929b5ae313 run pre-commit 2024-11-15 01:50:20 -08:00
Jarod Mica
d1d8139bab Allow for local path specification of HF models/repos 2024-11-15 01:46:26 -08:00
Yushen CHEN
8f65f9f3e4 Update SHARED.md 2024-11-14 00:14:28 +08:00
SWivid
159797d7c4 formatting 2024-11-14 00:10:42 +08:00
Yushen CHEN
944d32862e Merge pull request #462 from RASPIAUDIO/patch-1
Shared Model Cards for french from @RASPIAUDIO
2024-11-13 23:26:05 +08:00
RASPIAUDIO
da00b90aae Update SHARED.md 2024-11-13 16:24:21 +01:00
RASPIAUDIO
e995c123e2 ressources added 2024-11-13 15:35:18 +01:00
RASPIAUDIO
4577644f5c added french 2024-11-13 15:30:22 +01:00
SWivid
be53fb179c fix. force reload from custom cache file to override infer_gradio init loaded value in case webpage refreshed 2024-11-11 14:46:50 +08:00
Yushen CHEN
da059e86b2 Update SHARED.md; typo 2024-11-11 11:20:11 +08:00
SWivid
a23ec25b39 v0.1.1 2024-11-11 11:19:04 +08:00