 Yushen CHENandGitHub
|
9c614e9657
|
v1.1.22
|
2026-07-23 17:19:55 +08:00 |
|
|
Yushen CHENandGitHub
|
c03c5e16dc
|
Merge pull request #1309 from Wing900/fix/fix-duration-chunk-allocation
fix: allocate fix_duration across chunks to avoid N× duration blow-up
|
2026-07-23 17:16:23 +08:00 |
|
|
Yushen CHENandGitHub
|
2ae2c9bd9b
|
Merge pull request #1298 from Kaihui-AMD/docs/update-amd-rocm-install
Update AMD ROCm install to 7.2 for RDNA 3.5/4 support
|
2026-05-18 20:46:11 +08:00 |
|
|
Yushen CHENandGitHub
|
2f53ded68e
|
Merge pull request #1294 from AAtomical/fix/path-traversal-finetune-gradio
fix: path traversal in finetune Gradio handlers
|
2026-05-13 10:06:36 +08:00 |
|
|
Yushen CHENandGitHub
|
650c177b14
|
Merge pull request #1290 from will422-l/fix/gradio-version-cap
fix: cap Gradio version to <6.11 to prevent UI freeze
Fixes #1289 thanks to @gmtrnv
|
2026-04-17 12:01:39 +08:00 |
|
|
Yushen CHENandGitHub
|
25874ca255
|
Bump version from 1.1.18 to 1.1.19
|
2026-04-16 10:56:40 +08:00 |
|
|
Yushen CHENandGitHub
|
22299b38f7
|
Merge pull request #1285 from ZhikangNiu/main
reuse resamplers and cache vocos MelSpectrogram instances
|
2026-04-04 16:50:43 +08:00 |
|
|
Yushen CHENandGitHub
|
82fc4fe622
|
Bump version from 1.1.17 to 1.1.18
|
2026-03-24 20:20:15 +08:00 |
|
|
Yushen CHENandGitHub
|
2414e3d492
|
Merge pull request #1281 from zhuxiaoxuhit/fix/remove-ineffective-threadpoolexecutor
remove ineffective ThreadPoolExecutor in infer_batch_process
|
2026-03-24 19:31:29 +08:00 |
|
|
Yushen CHENandGitHub
|
deb5540edb
|
Merge pull request #1280 from ZhikangNiu/main
Add F5TTS v1 Small + LibriTTS training config
|
2026-03-23 20:14:40 +08:00 |
|
|
Yushen CHENandGitHub
|
4533426c72
|
Bump version from 1.1.16 to 1.1.17
|
2026-03-04 19:34:03 +08:00 |
|
|
Yushen CHENandGitHub
|
ab75dc2837
|
Merge pull request #1271 from mlxu995/patch-1
Add show_info parameter to preprocess_ref_audio_text
|
2026-03-04 18:56:46 +08:00 |
|
|
Yushen CHENandGitHub
|
097772c917
|
Merge pull request #1269 from ZhikangNiu/main
feat:add mmdit flash attn support
fix: autocast when use flash_attn to enable log_sample
|
2026-02-27 01:20:09 +08:00 |
|
|
Yushen CHENandGitHub
|
54c50eb8f6
|
Bump version from 1.1.15 to 1.1.16
|
2026-02-16 12:37:19 +08:00 |
|
|
Yushen CHENandGitHub
|
65250152da
|
Merge pull request #1267 from QingyuLiu0521/qyl/pr-dit-only
Optimize DiT text embedding with batched per-sample seq handling
|
2026-02-16 12:28:17 +08:00 |
|
|
Yushen CHENandGitHub
|
04459f71e6
|
Merge pull request #1266 from ZhikangNiu/main
Make wandb project/run_name/resume_id configurable via Hydra yaml, backward compatible with defaults
|
2026-02-16 11:10:17 +08:00 |
|
|
Yushen CHENandGitHub
|
ecfdccb890
|
Merge pull request #1265 from ZhikangNiu/main
Use torch.utils.checkpoint in mmdit forward loop when enabled to reduce memory usage.
|
2026-02-14 11:14:57 +08:00 |
|
|
Yushen CHENandGitHub
|
fc0fa67a03
|
Update eval README with ctranslate2 installation instructions
Added installation instructions for ctranslate2 based on CUDA and cuDNN versions.
|
2026-01-28 19:15:57 +08:00 |
|
|
Yushen CHENandGitHub
|
a3c2ea9784
|
Merge pull request #1261 from ZhikangNiu/main
Ignore padding at the end of the GT mel spectrogram when training sample
|
2026-01-26 18:58:47 +08:00 |
|
|
Yushen CHENandGitHub
|
b9d923088c
|
Increase default max_duration from 4096 to 65536 in cfm.py (#1260)
|
2026-01-25 23:58:21 +08:00 |
|
|
Yushen CHENandGitHub
|
c279a2b7d5
|
Merge pull request #1256 from ZhikangNiu/main
change prepare_csv_wavs from relative path to absolute path and get duration info with soundfile and torchaudio
|
2026-01-22 20:00:54 +08:00 |
|
|
Yushen CHENandGitHub
|
37a2633d35
|
Fix epoch updates count logic as drop_last
|
2026-01-21 21:36:57 +08:00 |
|
|
Yushen CHENandGitHub
|
27e20fcf39
|
Merge pull request #1242 from acadarmeria/fix-speech-edit-mel-domain
Fix speech editing boundary artifacts by working in mel domain
|
2025-12-26 17:35:57 +08:00 |
|
|
Yushen CHENandGitHub
|
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 |
|
|
Yushen CHENandGitHub
|
1dcb4e10f7
|
Add torchcodec dependency to pyproject.toml
|
2025-11-03 16:44:11 +08:00 |
|
|
Yushen CHENandGitHub
|
f2a4f8581f
|
Update runtime README
|
2025-10-22 08:37:32 +08:00 |
|
|
Yushen CHENandGitHub
|
31bb78f2ab
|
Update badge links
|
2025-09-03 15:12:24 +08:00 |
|
|
Yushen CHENandGitHub
|
ac3c43595c
|
delete .github/workflows/sync-hf.yaml for online space stablility
|
2025-08-27 06:52:18 +08:00 |
|
|
Yushen CHENandGitHub
|
5f35f27230
|
update pyproject.toml
|
2025-07-15 17:28:41 +08:00 |
|
|
Yushen CHENandGitHub
|
c96c3aeed8
|
Update pyproject.toml
|
2025-07-14 14:36:26 +08:00 |
|
|
Yushen CHENandGitHub
|
9b60fe6a34
|
update pyproject.toml, set gradio<=5.35.0 until fix #1126
|
2025-07-14 14:29:19 +08:00 |
|
|
Yushen CHENandGitHub
|
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 CHENandGitHub
|
d937efa6f3
|
fix finetune_gradio.py, not to force lower case
|
2025-06-23 16:22:33 +08:00 |
|
|
Yushen CHENandGitHub
|
8975fca803
|
Merge pull request #1084 from starkwj/main
Speedup inference by batching CFG in DiT
|
2025-06-12 03:54:04 +08:00 |
|
|
Yushen CHENandGitHub
|
1d13664b24
|
Merge pull request #1063 from ionite34/dev
Fix finetune training with spaces in file paths
|
2025-06-03 21:18:41 +08:00 |
|
|
Yushen CHENandGitHub
|
b27471ea06
|
Merge pull request #1072 from hvoss-techfak/main
German Model support
|
2025-06-03 21:18:25 +08:00 |
|
|
Yushen CHENandGitHub
|
2de214c122
|
Merge pull request #1014 from fakerybakery/fix-gradio-app-250503
Fix Gradio app
|
2025-05-04 09:14:32 +08:00 |
|
|
Yushen CHENandGitHub
|
b0658bfd24
|
Merge pull request #1013 from petermg/main
Update infer_gradio.py
|
2025-05-04 03:33:22 +08:00 |
|
|
Yushen CHENandGitHub
|
178cb8afe6
|
Merge pull request #986 from fakerybakery/emilia-v2
Add processing script for new Emilia dataset format
|
2025-04-19 14:16:37 +08:00 |
|
|
Yushen CHENandGitHub
|
13fd6f8e07
|
Merge pull request #971 from tbxark-fork/main
chore: Update the model checkpoint path to use the cache path.
|
2025-04-14 15:54:50 +08:00 |
|
|
Yushen CHENandGitHub
|
2374f8ec39
|
Merge pull request #948 from yuekaizhang/trtllm_benchmark
[TRT-LLM] add benchmark code
|
2025-04-03 18:27:21 +08:00 |
|
|
Yushen CHENandGitHub
|
d1f6c95fe8
|
Merge pull request #944 from yuekaizhang/triton
Support GPU Depolyment Solution with Triton and TensorRT-LLM
|
2025-04-03 13:42:37 +08:00 |
|
|
Yushen CHENandGitHub
|
f34465d118
|
v1.0.9 several fixes
|
2025-03-28 23:12:13 +08:00 |
|
|
Yushen CHENandGitHub
|
c87ce39515
|
Merge pull request #890 from MicahZoltu/patch-1
Improves documentation around docker usage.
|
2025-03-20 22:45:40 +08:00 |
|
|
Yushen CHENandGitHub
|
f968e13b6d
|
Update README.md
|
2025-03-20 10:15:47 +08:00 |
|
|
Yushen CHENandGitHub
|
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 |
|
|
Yushen CHENandGitHub
|
297755fac3
|
v1.0.1 VRAM usage management #851
|
2025-03-14 17:31:44 +08:00 |
|
|
Yushen CHENandGitHub
|
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 CHENandGitHub
|
8722cf0766
|
Update utils_infer.py
|
2025-03-14 17:23:20 +08:00 |
|
|
Yushen CHENandGitHub
|
128f4e4bf3
|
Update publish-pypi.yaml
|
2025-03-13 00:08:36 +08:00 |
|
|
Yushen CHENandGitHub
|
85e6c660b0
|
0.6.0 chunk stream support #803 from kunci115
chunk stream instead of the whole content process, to make it near realtime possibility
|
2025-02-21 21:45:07 +08:00 |
|
|
Yushen CHENandGitHub
|
6e49f3200c
|
Merge pull request #797 from YoungPhlo/feat/browser-autolaunch
feat: Add autolaunch option to Gradio interface
|
2025-02-19 08:21:41 +08:00 |
|
|
Yushen CHENandGitHub
|
e40d4462d2
|
Merge pull request #796 from YoungPhlo/fix/mps-fallback
fix: typo in MPS PyTorch env variable
|
2025-02-18 18:15:16 +08:00 |
|
|
Yushen CHENandGitHub
|
818d9b8476
|
Merge pull request #786 from fakerybakery/hf-demo-upd
Add link back to GitHub repo, clarify local demo
|
2025-02-15 05:01:45 +08:00 |
|
|
Yushen CHENandGitHub
|
5fbcbac6a3
|
Merge pull request #772 from hcsolakoglu/improve-prepare-csv-wavs
Improve prepare_csv_wavs.py
|
2025-02-09 14:34:11 +08:00 |
|
|
Yushen CHENandGitHub
|
906b1af925
|
Merge pull request #765 from hcsolakoglu/dynbatchsampler-epoch-shuffle
Add Per-Epoch Batch Shuffling to DynamicBatchSampler
|
2025-02-05 15:10:08 +08:00 |
|
|
Yushen CHENandGitHub
|
738d502f3b
|
Merge pull request #751 from hcsolakoglu/fix-finetune-gradio-dropdown
Small fix for the checkpoint dropdown menu in finetune gradio
|
2025-01-28 22:52:25 +08:00 |
|
|
Yushen CHENandGitHub
|
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 CHENandGitHub
|
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 CHENandGitHub
|
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 |
|
|
Yushen CHENandGitHub
|
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 |
|
|
Yushen CHENandGitHub
|
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 CHENandGitHub
|
6281b4b8ed
|
Update README.md
|
2024-12-27 15:21:22 +08:00 |
|
|
Yushen CHENandGitHub
|
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 |
|
|
Yushen CHENandGitHub
|
0e1f2fcd93
|
Merge pull request #641 from JarodMica/main_repo_update
Add updated JA model
|
2024-12-18 14:08:09 +08:00 |
|
|
Yushen CHENandGitHub
|
6247780f07
|
Merge pull request #640 from HotDro4illa/russian
Update card: Add Russian model
|
2024-12-18 03:23:49 +08:00 |
|
|
Yushen CHENandGitHub
|
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 CHENandGitHub
|
81f69e57b7
|
Update infer_cli.py; typo
|
2024-12-16 16:31:23 +08:00 |
|
|
Yushen CHENandGitHub
|
c85252f59a
|
Merge pull request #624 from AsmoKoskinen/main
Update SHARED.md
|
2024-12-13 18:57:36 +08:00 |
|
|
Yushen CHENandGitHub
|
1ad35336d8
|
Merge pull request #623 from MithrilMan/italian-card
Added Italian model card
|
2024-12-13 16:00:13 +08:00 |
|
|
Yushen CHENandGitHub
|
c570d88ade
|
Update SHARED.md
|
2024-12-13 15:59:49 +08:00 |
|
|
Yushen CHENandGitHub
|
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 |
|
|
Yushen CHENandGitHub
|
d8e622f004
|
Merge pull request #527 from Jerrister/1126
Fix sample timesteps
|
2024-11-26 14:14:19 +08:00 |
|
|
Yushen CHENandGitHub
|
d81911b0c0
|
Merge pull request #526 from techknowfile/main
Add root_path argument to support reverse proxies
|
2024-11-26 14:06:06 +08:00 |
|
|
Yushen CHENandGitHub
|
c066c324ca
|
Update infer_gradio.py; formatting-1
|
2024-11-26 14:05:07 +08:00 |
|
|
Yushen CHENandGitHub
|
d96bd6f99c
|
Update infer_gradio.py; formatting
|
2024-11-26 14:00:24 +08:00 |
|
|
Yushen CHENandGitHub
|
a5c44ee5e2
|
Update infer_gradio.py; help-1
|
2024-11-26 13:56:19 +08:00 |
|
|
Yushen CHENandGitHub
|
dbd54bb310
|
Update infer_gradio.py; help
|
2024-11-26 13:54:44 +08:00 |
|
|
Yushen CHENandGitHub
|
c9b4d43a2b
|
Merge pull request #520 from haydonryan/main
Add output filename parameter to infer_cli.
|
2024-11-24 12:09:28 +08:00 |
|
|
Yushen CHENandGitHub
|
f1b44e9943
|
Update infer_cli.py; minor update, remove duplicate print
|
2024-11-24 12:03:33 +08:00 |
|
|
Yushen CHENandGitHub
|
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 CHENandGitHub
|
c65b9d380d
|
Update trainer.py
|
2024-11-23 18:31:58 +08:00 |
|
|
Yushen CHENandGitHub
|
ab2ad3b005
|
Update README.md
|
2024-11-20 00:52:56 +08:00 |
|
|
Yushen CHENandGitHub
|
f9733bf16f
|
Update README.md
|
2024-11-20 00:41:13 +08:00 |
|
|
Yushen CHENandGitHub
|
eb84cbab0f
|
Merge pull request #487 from mame82/issue-480
Fixes both issues from #480
|
2024-11-19 15:39:39 +08:00 |
|
|
Yushen CHENandGitHub
|
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 CHENandGitHub
|
5f7944a748
|
Update dataset.py, formatting
|
2024-11-18 22:28:03 +08:00 |
|
|
Yushen CHENandGitHub
|
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 |
|
|
Yushen CHENandGitHub
|
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 |
|
|
Yushen CHENandGitHub
|
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 |
|
|
Yushen CHENandGitHub
|
8f65f9f3e4
|
Update SHARED.md
|
2024-11-14 00:14:28 +08:00 |
|
|
Yushen CHENandGitHub
|
944d32862e
|
Merge pull request #462 from RASPIAUDIO/patch-1
Shared Model Cards for french from @RASPIAUDIO
|
2024-11-13 23:26:05 +08:00 |
|
|
Yushen CHENandGitHub
|
da059e86b2
|
Update SHARED.md; typo
|
2024-11-11 11:20:11 +08:00 |
|
|
Yushen CHENandGitHub
|
e6e7bd01d3
|
Merge pull request #448 from peanutcocktail/main
Set PYTORCH_ENABLE_MPS_FALLBACK=1 for MPS by default
|
2024-11-11 07:11:19 +08:00 |
|
|
Yushen CHENandGitHub
|
e78ae2ce92
|
Create config.yml
|
2024-11-07 14:23:52 +08:00 |
|
|
Yushen CHENandGitHub
|
da8853838f
|
Update question.yml
|
2024-11-07 13:23:35 +08:00 |
|
|
Yushen CHENandGitHub
|
8a7e8495ff
|
Merge pull request #401 from hcsolakoglu/fix-finetune-cli-bnb-optimizer
Add --bnb_optimizer argument to CLI and pass it to Trainer initialization
|
2024-11-05 20:20:31 +08:00 |
|
|
Yushen CHENandGitHub
|
dbe35da754
|
Update finetune_cli.py; formatting
|
2024-11-05 20:19:53 +08:00 |
|
|
Yushen CHENandGitHub
|
8718b1d821
|
Merge pull request #394 from lpscr/main
Fix the glitch effect at the beginning audio
|
2024-11-05 00:01:48 +08:00 |
|
|
Yushen CHENandGitHub
|
2f914140f4
|
Update utils_infer.py
|
2024-11-05 00:00:29 +08:00 |
|