gitea-mirror/F5-TTS
1
0
Fork 0
mirror of https://github.com/SWivid/F5-TTS.git synced 2025-12-29 14:15:18 -08:00
Code Issues Packages Projects Releases Wiki Activity
455 Commits 1 Branch 15 Tags
d1f708d442877cf447dccacbbdee005e625f16fd
Commit Graph

455 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
unknown
d1f708d442 0.4.3 Bug-fixes for finetune-gradio component mismatch & checkpoint loading error loop 2025-01-27 21:22:29 +08:00
Yushen CHEN
1e7d6da992 Merge pull request #746 from mwzkhalil/patch-1 
Update finetune_gradio.py, set weights_only=True
 2025-01-27 21:12:14 +08:00
Yushen CHEN
c2cf31e0c5 Merge pull request #729 from hcsolakoglu/fix-ckpt-rotation 
Exclude pretrained models from the checkpoint rotation logic
 2025-01-27 19:57:05 +08:00
Yushen CHEN
46266f1d14 Merge pull request #741 from Chiyan200/main 
Fix Settings Loader Issues: Resolve KeyErrors, Path Handling, and Component Assignment (#731)
 2025-01-27 19:28:22 +08:00
mahwiz khalil
c54f4e7fc0 Update finetune_gradio.py 
The safest approach here is to explicitly set weights_only=True to load only the model weights and avoid executing potentially unsafe code
 2025-01-24 00:31:53 -08:00
Zhikang Niu
129014c5b4 Merge pull request #735 from DDXDB/main 
Added intel XPU support
 2025-01-22 12:52:00 +08:00
98440
6fb913fadf Merge remote-tracking branch 'origin/main' 
# Conflicts:
#	src/f5_tts/api.py
#	src/f5_tts/infer/speech_edit.py
#	src/f5_tts/infer/utils_infer.py
#	src/f5_tts/socket_server.py
#	src/f5_tts/train/finetune_gradio.py
 2025-01-22 03:36:55 +08:00
98440
964064094a Added intel XPU support 2025-01-22 03:36:10 +08:00
[Chiyan200]
24fe39dc3c Fix : Settings Loader Issues: Resolve KeyErrors, Path Handling, and Component Assignment (#731) 2025-01-22 00:07:34 +05:30
[Chiyan200]
a74d0d0f83 Fix: Robust settings loader to handle missing keys, incorrect file paths, and dynamic assignment 
- Ensured default settings are properly merged with file-based settings to prevent KeyErrors.
- Added logic to handle _pinyin and _char suffixes in project names, ensuring correct file paths.
- Implemented tuple-based ordered mapping for consistent and error-free component assignment.
- Added safety check to verify the existence of setting.json before loading.
- Improved maintainability by centralizing default settings and enhancing error handling.
 2025-01-21 23:17:59 +05:30
98440
81ce1d8670 Added intel XPU support 2025-01-20 00:47:57 +08:00
Hasan Can Solakoğlu
2d27d2c1b2 Exclude pretrained models from the checkpoint rotation logic 2025-01-17 19:35:19 +03:00
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