gitea-mirror/F5-TTS
1
0
Fork 0
mirror of https://github.com/SWivid/F5-TTS.git synced 2025-12-05 20:40:12 -08:00
Code Issues Packages Projects Releases Wiki Activity
643 Commits 1 Branch 13 Tags
main
Commit Graph

643 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
SWivid
9ae46c8360 Replace jieba pkg with rjieba - a jieba-rs Python binding 1.1.10 2025-11-28 13:08:07 +00:00
SWivid
3eecd94baa support back avg upsampling for batch, cover up non-mask case 2025-11-09 11:56:03 +00:00
SWivid
d9a69452ce formatting 2025-11-09 18:25:30 +08:00
Yushen CHEN
bc15df2b57 Merge pull request #1212 from QingyuLiu0521/fix/AverageUpsampling 
Fix Average Upsampling conflict logic, introduced from the previous batch inference fix.
 2025-11-09 18:23:38 +08:00
QingyuLiu0521
9b2357a1b9 Fix Average Upsampling 2025-11-08 18:39:06 -05:00
Yushen CHEN
1dcb4e10f7 Add torchcodec dependency to pyproject.toml 2025-11-03 16:44:11 +08:00
SWivid
529d856133 clean-up eval scripts 2025-10-27 14:38:57 +00:00
SWivid
7abadc4c72 fix typo in eval scripts 2025-10-26 14:28:17 +00:00
SWivid
e67d50841e runtime trtllm: fix batch inference skipping last words in shorter sentences #1039 #1179 2025-10-24 09:12:08 +00:00
SWivid
6b07fb03b2 clean-up ruff lint 2025-10-24 08:30:55 +00:00
SWivid
a051a68552 pytorch imple. fix batch inference skipping last words in shorter sentences issue #1039 #1179 2025-10-24 05:50:25 +00:00
Yushen CHEN
f2a4f8581f Update runtime README 2025-10-22 08:37:32 +08:00
SWivid
a17c5ae435 pytorch imple.: fix batch 1 inference from last commit 2025-10-22 00:31:56 +00:00
SWivid
a0b8fb5df2 runtime trtllm: minor fixes. pytorch: update text_embedding logic to correct v0 batching. 2025-10-22 00:19:45 +00:00
SWivid
c8bfc3aa3d runtime trtllm: support v1 and custom 2025-10-21 22:02:25 +00:00
SWivid
8d3ec72159 runtime trtllm: clean-up v0 code, several fixes. 2025-10-20 10:30:58 +00:00
SWivid
65ada48a62 set attn related default value for unet-t backbone: #1192 2025-10-09 06:51:25 +00:00
SWivid
77d3ec623b v1.1.9 1.1.9 2025-09-13 13:42:33 +08:00
SWivid
186799d6dc remove numpy<=1.26.4 for python_version>=3.11 #1162; update links 2025-09-13 13:40:55 +08:00
Yushen CHEN
31bb78f2ab Update badge links 2025-09-03 15:12:24 +08:00
SWivid
e61824009a v1.1.8 1.1.8 2025-08-28 12:33:37 +00:00
SWivid
06a74910bd add option for text embedding late average upsampling 2025-08-28 11:46:11 +00:00
Yushen CHEN
ac3c43595c delete .github/workflows/sync-hf.yaml for online space stablility 2025-08-27 06:52:18 +08:00
Jim
605fa13b42 Fix raw.arrow missing rows (#1145) 
* fix raw.arrow missing rows

---------

Co-authored-by: SWivid <swivid@qq.com>
 2025-07-22 19:38:44 +08:00
Yushen CHEN
5f35f27230 update pyproject.toml 2025-07-15 17:28:41 +08:00
Yushen CHEN
c96c3aeed8 Update pyproject.toml 1.1.7 2025-07-14 14:36:26 +08:00
Yushen CHEN
9b60fe6a34 update pyproject.toml, set gradio<=5.35.0 until fix #1126 2025-07-14 14:29:19 +08:00
SWivid
a275798a2f last fix patch-1 2025-07-08 18:44:47 +08:00
SWivid
efc7a7498b fix #1111 #1037 remove redundant unwrap_model for AcceleratedOptimizer; which has no attribute '_modules' thus conflict with has_compiled_regions check introduced in accelerate v1.7.0 2025-07-08 18:39:43 +08:00
SWivid
9842314127 update slicer in finetune_gradio, legacy min_length 2s changed to 20s 2025-07-08 16:59:46 +08:00
SWivid
69b0e0110e v1.1.6 fla support, several changed for finetune and infer-cli 1.1.6 2025-07-03 00:08:42 +08:00
SWivid
52c84776e5 fine-grained speed control for infer-cli. #1112 2025-07-02 23:41:55 +08:00
Danh Tran
ebbd7bd91f Update WAV File Naming and Dependencies 📝🔊 (#1091) 
* Update infer_cli.py

* Update pyproject.toml

* formalized

---------

Co-authored-by: SWivid <swivid@qq.com>
 2025-06-24 23:23:00 +08:00
Yushen CHEN
ac42286d04 update finetune_gradio.py, not to force lower case 
Not to force lower case, otherwise train infer mismatch with main infer code
 2025-06-23 16:37:51 +08:00
Yushen CHEN
d937efa6f3 fix finetune_gradio.py, not to force lower case 2025-06-23 16:22:33 +08:00
Yushen CHEN
8975fca803 Merge pull request #1084 from starkwj/main 
Speedup inference by batching CFG in DiT
 2025-06-12 03:54:04 +08:00
SWivid
8b0053ad0c backward compatibility 2025-06-12 03:52:12 +08:00
SWivid
b3ef4ed1d7 correct imple., minor fixes 2025-06-12 03:32:19 +08:00
starkwj
b1a9438496 Batch cfg DiT forward 2025-06-11 09:03:30 +00:00
Zhikang Niu
0914170e98 Add flash_attn2 support attn_mask, minor fixes (#1066) 
* add flash attn2 support
* update flash attn config in F5TTS
* fix minor bug of get the length of ref_mel

---------

Co-authored-by: SWivid <swivid@qq.com>
 2025-06-11 12:14:32 +08:00
SWivid
c6ebad0220 switch sync-hf workflow logic on release, avoid hidden space error with pypi/local_editable mismatch 2025-06-06 07:23:54 +08:00
SWivid
cfaba6387f refresh hf-space first 2025-06-06 07:22:02 +08:00
SWivid
646f34b20f v1.1.5 pypi 1.1.5 2025-06-06 07:08:59 +08:00
Jerrister Zheng
2e2acc6ea2 Update: Empirically Pruned Step Sampling (#1077) 
* update Empirically Pruned Step Sampling

---------

Co-authored-by: Fast-F5-TTS <2942755472@qq.com>
Co-authored-by: SWivid <swivid@qq.com>
 2025-06-04 22:59:30 +08:00
SWivid
6fbe7592f5 rebase default sample_rate to 24khz for runtime 2025-06-04 11:22:31 +08:00
Alice Yanagi
7e37bc5d9a Fix the duration computation in triton_trtllm/client_grpc.py (#1071) 
* Update client_grpc.py

Using `actual_duration` to compute metrics like RTF.
 2025-06-04 11:18:00 +08:00
SWivid
35f130ee85 minor update for infer-gradio 2025-06-04 06:11:49 +08:00
SWivid
e6469f705f update shared.md 2025-06-03 22:09:13 +08:00
SWivid
31cd818095 formatting 2025-06-03 21:23:47 +08:00
Yushen CHEN
1d13664b24 Merge pull request #1063 from ionite34/dev 
Fix finetune training with spaces in file paths
 2025-06-03 21:18:41 +08:00