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

..

__init__.py

Add Zipformer from Dan (#672)

2022-11-12 18:11:19 +08:00

asr_datamodule.py

Fix buffer size of DynamicBucketingSampler (#1468)

2024-01-21 02:10:42 +08:00

beam_search.py

apply black on all files

2022-11-17 09:42:17 -05:00

conformer.py

apply black on all files

2022-11-17 09:42:17 -05:00

decode.py

Fix style issues. (#937)

2023-03-08 22:56:04 +08:00

decoder2.py

apply black on all files

2022-11-17 09:42:17 -05:00

decoder.py

apply black on all files

2022-11-17 09:42:17 -05:00

encoder_interface.py

Add Zipformer from Dan (#672)

2022-11-12 18:11:19 +08:00

export.py

manual correction of black formatting

2022-11-17 14:18:05 -05:00

joiner.py

apply black on all files

2022-11-17 09:42:17 -05:00

model.py

Replace deprecated pytorch methods (#1814)

2024-12-16 10:24:16 +08:00

optim.py

formatted the entire LibriSpeech recipe (#1270)

2023-09-24 17:31:01 +08:00

sampling.py

Replace deprecated pytorch methods (#1814)

2024-12-16 10:24:16 +08:00

scaling_tmp.py

apply black on all files

2022-11-17 09:42:17 -05:00

scaling.py

apply black on all files

2022-11-17 09:42:17 -05:00

train.py

Replace deprecated pytorch methods (#1814)

2024-12-16 10:24:16 +08:00