SWivid
9e51878d18
0.4.2 fix trainer with grad_accum
2025-01-15 18:28:41 +08:00
SWivid
12d6970271
0.4.1 #718 add keep_last_n_checkpoints option
2025-01-15 15:06:55 +08:00
Hasan Can Solakoğlu
76b1b03c4d
Keep Last N Checkpoints ( #718 )
...
* Add checkpoint management feature
- Introduced `keep_last_n_checkpoints` parameter in configuration and training scripts to manage the number of recent checkpoints retained.
- Updated `finetune_cli.py`, `finetune_gradio.py`, and `trainer.py` to support this new parameter.
- Implemented logic to remove older checkpoints beyond the specified limit during training.
- Adjusted settings loading and saving to include the new checkpoint management option.
This enhancement improves the training process by preventing excessive storage usage from old checkpoints.
2025-01-15 12:28:54 +08:00
Yushen CHEN
83efc3f038
Merge pull request #711 from SWivid/fix_grad_accum
...
0.4.0 fix gradient accumulation; change checkpointing logic to per_updates
2025-01-14 23:18:55 +08:00
unknown
0b11f7eae6
0.4.0 fix gradient accumulation; change checkpointing logic to per_updates
2025-01-12 21:26:57 +08:00
SWivid
f992c4e844
update README.md
2025-01-09 15:28:07 +08:00
SWivid
4872afef9f
fix no_ref_audio in cfm.py
2025-01-07 22:01:43 +08:00
hndrbrm
dc2d2d3b2f
Bug Fix: Parsing Argument --finetune always True ( #676 )
...
* Bug Fix: Parsing Argument --finetune always True
* Update finetune_cli.py, fix also log_samples & bnb_optimizer flags
* Update finetune_gradio.py. fix flags
* Update finetune_gradio.py. formatting
---------
Co-authored-by: Yushen CHEN <45333109+SWivid@users.noreply.github.com >
2024-12-29 21:29:50 +08:00
Yushen CHEN
20aa6a1103
Merge pull request #671 from Rek-Malorm/main
...
Update README.md. Add PyTorch installation instruction for AMD GPU
2024-12-27 15:26:53 +08:00
Yushen CHEN
6281b4b8ed
Update README.md
2024-12-27 15:21:22 +08:00
Rek-Malorm
7370ce7243
Provide instructions for AMD GPU
2024-12-27 11:26:20 +13:00
SWivid
3e73553bd9
v0.3.4
2024-12-22 11:09:29 +08:00
Yushen CHEN
ae4717a2ea
Merge pull request #660 from benjamindoron/main
...
utils_infer.py: Fix pathing issue that prevents importing BigVGAN
2024-12-22 11:07:38 +08:00
Benjamin Doron
91538ab206
utils_infer.py: Fix pathing issue that prevents importing BigVGAN
...
Upwards directory traversal goes after getting the base path.
Tested on Linux, using F5-TTS and BigVGAN. Audio is generated.
Signed-off-by: Benjamin Doron <benjamin.doron00@gmail.com >
2024-12-21 20:52:44 -05:00
SWivid
156032ac68
formatting
2024-12-21 23:20:53 +08:00
SWivid
6ab873fb19
Fixed #658
2024-12-21 23:19:11 +08:00
SWivid
deaca8d24c
v0.3.2 add flags and default values to socket_server.py
2024-12-18 20:32:20 +08:00
Yushen CHEN
0e1f2fcd93
Merge pull request #641 from JarodMica/main_repo_update
...
Add updated JA model
2024-12-18 14:08:09 +08:00
Jarod Mica
e278836f87
Add updated JA model
2024-12-17 14:11:32 -08:00
Yushen CHEN
6247780f07
Merge pull request #640 from HotDro4illa/russian
...
Update card: Add Russian model
2024-12-18 03:23:49 +08:00
HotDro4illa
6cd1f9f243
fix
2024-12-17 22:15:36 +03:00
HotDro4illa
50b5e49bd6
update card
2024-12-17 22:13:43 +03:00
SWivid
84978268f0
v0.3.1
2024-12-17 07:59:59 +08:00
SWivid
9a18bbe823
v0.3.1 fix multi-style gradio bug; add features suggested #591
2024-12-17 07:57:33 +08:00
SWivid
61f28ee8a5
v0.3.0 custom model cfg, checkpointing for training, minor fix, etc.
2024-12-16 16:39:56 +08:00
Yushen CHEN
c4c1fde6f2
Merge pull request #628 from SWivid/bugfix/fix/enhancement-pr
...
fix/enhancement pr #399 #400 #529 #534 #591 #611
2024-12-16 16:32:55 +08:00
Yushen CHEN
81f69e57b7
Update infer_cli.py; typo
2024-12-16 16:31:23 +08:00
SWivid
17087321f5
formatting
2024-12-16 16:26:21 +08:00
SWivid
c93462fc68
feature. allow custom model config for gradio infer
2024-12-16 16:25:23 +08:00
ZhikangNiu
649b46e4cb
update README
2024-12-16 14:41:10 +08:00
ZhikangNiu
7c84e91a00
update dit checkpoint_activations and fix#399 #400
2024-12-16 13:24:58 +08:00
SWivid
c6e96d0c83
Fixed #631
2024-12-15 23:21:00 +08:00
SWivid
b7bc6419e7
reorganize infer_cli and stuff
2024-12-15 22:49:31 +08:00
ZhikangNiu
3c60f99714
fix #524 #529
2024-12-14 10:41:19 +08:00
ZhikangNiu
7931fcb7d0
save every line wer results and update utmos evaluation
2024-12-14 10:41:03 +08:00
Yushen CHEN
c85252f59a
Merge pull request #624 from AsmoKoskinen/main
...
Update SHARED.md
2024-12-13 18:57:36 +08:00
Asmo Koskinen
0c541a9b43
Update SHARED.md
...
TYPO, HF Links... Sorry for that...
2024-12-13 12:35:58 +02:00
Yushen CHEN
1ad35336d8
Merge pull request #623 from MithrilMan/italian-card
...
Added Italian model card
2024-12-13 16:00:13 +08:00
Yushen CHEN
c570d88ade
Update SHARED.md
2024-12-13 15:59:49 +08:00
MithrilMan
4e887e244d
Added Italian model card
2024-12-13 00:26:03 +01:00
SWivid
8898d05e37
update train readme. accelerate & hydra config overwrite instruct.
2024-12-07 14:20:59 +08:00
SWivid
9acfea0fd2
formatting. fi & es in shared.md
2024-12-07 14:04:15 +08:00
Yushen CHEN
714fade533
Merge pull request #601 from AsmoKoskinen/f5-tts_finnish_model
...
Finnish Model added at Hugging Face
2024-12-07 13:38:31 +08:00
Asmo Koskinen
625cf8a82b
Finnish Model added at Hugging Face
2024-12-06 22:09:17 +02:00
Asmo Koskinen
ecbc583294
Finnish Model added at Hugging Face
2024-12-06 22:06:43 +02:00
Asmo Koskinen
1d3ac4f7ab
Finnish Model added at Hugging Face
2024-12-06 20:11:52 +02:00
SWivid
6a3659dbf8
minor update. tokenizer
2024-12-06 15:32:29 +08:00
SWivid
1ba1c3cf61
fix training resuming as mentioned in #591
2024-12-06 14:51:24 +08:00
SWivid
7f7fd29675
fix. default fp32 for ZLUDA #578
2024-12-05 11:50:50 +08:00
SWivid
eea65de823
Update README for commonly put question about use_ema.
2024-12-01 16:40:14 +08:00
