7 Commits

Author SHA1 Message Date
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
Zengwei Yao
334beed2af
fix usages of returned losses after adding attention-decoder in zipformer (#1689) 2024-07-12 16:50:58 +08:00
zr_jin
eb132da00d
additional instruction for the grad_scale is too small error (#1550) 2024-03-14 11:33:49 +08:00
jimmy1984xu
e472fa6840
fix CutMix init parameter (#1543)
Co-authored-by: jimmyxu <jimmyxu@upblocks.io>
2024-03-11 18:37:26 +08:00
Yifan Yang
5dfc3ed7f9
Fix buffer size of DynamicBucketingSampler (#1468)
* Fix buffer size

* Fix for flake8

---------

Co-authored-by: yifanyeung <yifanyeung@yifanyeung.local>
2024-01-21 02:10:42 +08:00
Wei Kang
238b45bea8
Libriheavy recipe (zipformer) (#1261)
* initial commit for libriheavy

* Data prepare pipeline

* Fix train.py

* Fix decode.py

* Add results

* minor fixes

* black

* black

* Incorporate PR https://github.com/k2-fsa/icefall/pull/1269

---------

Co-authored-by: zr_jin <peter.jin.cn@gmail.com>
2023-11-23 01:22:57 +08:00