21 Commits

Author SHA1 Message Date
yifanyeung
62dfe56cbe restore checkpoint save after validation 2025-05-13 06:14:59 +00:00
yfyeung
06667e1f6d add batch shave mechanism
fix

fix
2025-05-12 17:39:15 +00:00
yfyeung
2793ccdf56 remove checkpoint save after validation 2025-05-12 06:36:20 +00:00
yfyeung
c078772e59 skip OOM 2025-05-11 17:23:19 +00:00
yfyeung
9939c2b72d remove duplicated torch autocast 2025-05-11 17:03:44 +00:00
yfyeung
c75767f600 set world_size and rank explicitly
update
2025-05-10 17:47:28 +00:00
Yifan Yang
2420d0c95f
update multi_dataset.py 2025-05-10 02:13:25 +08:00
yfyeung
ec6c8f748d fix data prepare
update
2025-05-09 17:20:38 +00:00
Yifan Yang
489c42b45e support zipformer encoder
update

update

update

update

fix

reformat

support infer

update
2025-05-08 14:44:09 +00:00
Yifan Yang
211c01bc1d format train.py
minor fix train.py
2025-05-08 04:30:02 +00:00
Yifan Yang
23b5a7ce3e format multi_dataset.py 2025-05-08 04:28:57 +00:00
Yifan Yang
9c8c4314de init zipformer_llm_zh 2025-05-07 12:18:41 +00:00
Yifan Yang
dc07bba236 init
fix
2025-04-30 09:58:33 +00:00
Yifan Yang
cd7caf12df
Fix speech_llm recipe (#1936)
* fix training/decoding scripts, cleanup unused code, and ensure compliance with style checks

---------

Co-authored-by: Your Name <you@example.com>
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
2025-04-30 11:41:00 +08:00
Yifan Yang
5ec95e5482
Fix SpeechLLM recipe (#1926) 2025-04-23 16:18:38 +08:00
Fangjun Kuang
d4d4f281ec
Revert "Replace deprecated pytorch methods (#1814)" (#1841)
This reverts commit 3e4da5f78160d3dba3bdf97968bd7ceb8c11631f.
2024-12-18 16:49:57 +08:00
Li Peng
3e4da5f781
Replace deprecated pytorch methods (#1814)
* Replace deprecated pytorch methods

- torch.cuda.amp.GradScaler(...) => torch.amp.GradScaler("cuda", ...)
- torch.cuda.amp.autocast(...) => torch.amp.autocast("cuda", ...)

* Replace `with autocast(...)` with `with autocast("cuda", ...)`


Co-authored-by: Li Peng <lipeng@unisound.ai>
2024-12-16 10:24:16 +08:00
zr_jin
88bacfb9e6
minor fixes for the repo (#1775)
* minor fixes for the repo

Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
2024-10-21 13:51:56 +08:00
Yuekai Zhang
ebbd396c2b
update multi-hans-zh whisper-qwen-7b results (#1677)
* update qwen-7b whisper encoder results

* update qwen-7b whisper encoder results

* fix typo
2024-07-03 19:55:12 +08:00
Yuekai Zhang
ff2bef9e50
update multi-hans whisper-qwen-1.5b results (#1657) 2024-06-19 11:10:31 +08:00
Yuekai Zhang
890eeec82c
Add qwen-audio style model training: using whisper + qwen2 (#1652) 2024-06-16 12:14:44 +08:00