643 Commits

Author SHA1 Message Date
root
4681a1c177 remove annotation 2025-04-03 02:35:26 +00:00
root
5b178397e0 remove unused codes 2025-04-03 02:34:28 +00:00
Yuekai Zhang
2724f9f101 add Nvidia Triton TensorRT-LLM solution 2025-04-02 19:04:45 -07:00
SWivid
7258b09529 v1.0.10 support custom chat model 2025-03-31 21:15:26 +08:00
SWivid
784e3862b4 add microsoft/Phi-4-mini-instruct to chat model list #937 2025-03-31 21:14:39 +08:00
SWivid
6f6968b034 formatting 2025-03-31 19:45:38 +08:00
maximechen
9bd2d13be1 Merge branch 'huanglizhuo-feat/support-custom-chat-model' 2025-03-31 19:22:08 +08:00
maximechen
b7c41af9cd reorganize and distinguish behavior from local and space 2025-03-31 19:11:52 +08:00
huanglizhuo
eaa7fd8a01 Reapply pre-commit hooks 2025-03-29 20:58:42 +09:00
Yushen CHEN
f34465d118 v1.0.9 several fixes 2025-03-28 23:12:13 +08:00
lizhuo
393993321d fix: use pydantic<=2.10.6 to address dependency conflict with gradio-app #930 2025-03-28 23:10:41 +08:00
lizhuo
29d3326bed update: JA latest HF path in SHARED.md #928
* fix: update japanese latest hf path
* update the huggingface url
2025-03-28 22:36:17 +08:00
Zhikang Niu
67e43dc0fb Merge pull request #926 from huanglizhuo/fix/shared-file-path
fix the SHARED.md file path
2025-03-28 17:14:54 +08:00
huanglizhuo
8469025b1c fix the shared.md file path 2025-03-28 17:52:08 +09:00
Zhikang Niu
5bd8cd7aed update: better save last & per ckpt logic #924
Co-authored-by: Yushen CHEN <45333109+SWivid@users.noreply.github.com>
2025-03-28 13:53:12 +08:00
SWivid
7236536f9a update utils_infer.py 2025-03-25 17:24:20 +08:00
SWivid
6b7f6eefdc fix typo in trainer.py with 4ae5347282 formatting #909 2025-03-25 16:17:03 +08:00
SWivid
b9156c0ad5 v1.0.8 fix a fatal bug with log_samples since 37eb3b50da 1.0.8 2025-03-25 07:49:19 +08:00
SWivid
3ad3211915 Update F5TTS_Small.yaml 2025-03-25 07:11:35 +08:00
Zhikang Niu
f6726a78cc Update F5TTS_Small.yaml 2025-03-23 22:27:02 +08:00
SWivid
1d0cf2b8ba add device option for infer-cli, patch-1 2025-03-22 17:35:16 +08:00
SWivid
1d82b7928e add device option for infer-cli 2025-03-22 17:30:23 +08:00
SWivid
4ae5347282 pre-commit update and formatting 2025-03-21 23:01:00 +08:00
SWivid
621559cbbe v1.0.7 2025-03-21 14:40:52 +08:00
SWivid
526b09eebd add no_zero_init v1 variant path to SHARED.md 2025-03-21 14:37:14 +08:00
SWivid
9afa80f204 add option in finetune gradio to save non-ema model weight 2025-03-21 13:36:11 +08:00
SWivid
c6b3189bbd v1.0.6 improves docker usage 2025-03-20 22:48:36 +08:00
Yushen CHEN
c87ce39515 Merge pull request #890 from MicahZoltu/patch-1
Improves documentation around docker usage.
2025-03-20 22:45:40 +08:00
Micah Zoltu
10ef27065b Improves documentation around docker usage. 2025-03-20 21:37:48 +08:00
SWivid
f374640f34 Merge branch 'main' of github.com:SWivid/F5-TTS 2025-03-20 13:54:52 +08:00
SWivid
d5f4c88aa4 update issue templates 2025-03-20 13:54:15 +08:00
Yushen CHEN
f968e13b6d Update README.md 2025-03-20 10:15:47 +08:00
SWivid
339b17fed3 update README.md for infer & train 2025-03-20 10:14:22 +08:00
SWivid
79302b694a update README.md for infer & train 2025-03-20 10:03:54 +08:00
SWivid
a1e88c2a9e v1.0.5 update finetune_gradio.py for clearer guidance 2025-03-17 21:50:50 +08:00
SWivid
1ab90505a4 v1.0.4 fix finetune_gradio.py vocab extend with .safetensors ckpt 2025-03-17 16:22:26 +08:00
SWivid
7e4985ca56 v1.0.3 fix api.py 1.0.3 2025-03-17 02:39:20 +08:00
SWivid
f05ceda4cb v1.0.2 fix: torch.utils.checkpoint.checkpoint add use_reentrant=False 2025-03-15 16:34:32 +08:00
Yushen CHEN
2bd39dd813 Merge pull request #859 from ZhikangNiu/main
fix #858 and pass use_reentrant explicitly in checkpoint_activation mode
2025-03-15 16:23:50 +08:00
ZhikangNiu
f017815083 fix #858 and pass use_reentrant explicitly in checkpoint_activation mode 2025-03-15 15:48:47 +08:00
Yushen CHEN
297755fac3 v1.0.1 VRAM usage management #851 2025-03-14 17:31:44 +08:00
Yushen CHEN
d05075205f Merge pull request #851 from niknah/vram-usage
VRAM usage on long texts gradually uses up memory.
2025-03-14 17:25:56 +08:00
Yushen CHEN
8722cf0766 Update utils_infer.py 2025-03-14 17:23:20 +08:00
niknah
48d1a9312e VRAM usage on long texts gradually uses up memory. 2025-03-14 16:53:58 +11:00
Yushen CHEN
128f4e4bf3 Update publish-pypi.yaml 1.0.0 2025-03-13 00:08:36 +08:00
SWivid
2695e9305d v1.0.0 release 2025-03-12 23:47:04 +08:00
SWivid
69909ac167 update README.md 2025-03-12 18:40:07 +08:00
SWivid
79bbde5d76 update README.md add a glance of few demo 2025-03-12 18:37:14 +08:00
SWivid
bf651d541e update README.md for v1.0.0 2025-03-12 17:39:30 +08:00
SWivid
ca6e49adaa 1.0.0 F5-TTS v1 base model with better training and inference performance 2025-03-12 17:23:10 +08:00