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

[WIP] Pruned-transducer-stateless5-for-WenetSpeech (offline and streaming) (#447)

2022-07-28 12:54:27 +08:00

asr_datamodule.py

[WIP] Pruned-transducer-stateless5-for-WenetSpeech (offline and streaming) (#447)

2022-07-28 12:54:27 +08:00

beam_search.py

[WIP] Pruned-transducer-stateless5-for-WenetSpeech (offline and streaming) (#447)

2022-07-28 12:54:27 +08:00

conformer.py

fix bug (#796)

2022-12-28 11:20:38 +08:00

decode_stream.py

apply black on all files

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

decode.py

Add cumstomized score for hotwords (#1385)

2023-11-18 18:47:55 +08:00

decoder.py

[WIP] Pruned-transducer-stateless5-for-WenetSpeech (offline and streaming) (#447)

2022-07-28 12:54:27 +08:00

encoder_interface.py

[WIP] Pruned-transducer-stateless5-for-WenetSpeech (offline and streaming) (#447)

2022-07-28 12:54:27 +08:00

export-onnx-streaming.py

fixed a CI test for wenetspeech (#1476)

2024-01-27 06:41:56 +08:00

export-onnx.py

fixed a CI test for wenetspeech (#1476)

2024-01-27 06:41:56 +08:00

export.py

Fix torchscript export to use tokens.txt instead of lang_dir (#1475)

2024-01-26 19:18:33 +08:00

joiner.py

[WIP] Pruned-transducer-stateless5-for-WenetSpeech (offline and streaming) (#447)

2022-07-28 12:54:27 +08:00

lstmp.py

fix wenet stateless5 jit export error (#735)

2022-12-05 23:35:10 +08:00

model.py

[WIP] Pruned-transducer-stateless5-for-WenetSpeech (offline and streaming) (#447)

2022-07-28 12:54:27 +08:00

onnx_check.py

Strengthened style constraints (#1527)

2024-03-04 23:28:04 +08:00

onnx_pretrained-streaming.py

Use high_freq -400 in computing fbank features. (#1447)

2024-01-04 13:59:32 +08:00

onnx_pretrained.py

Use high_freq -400 in computing fbank features. (#1447)

2024-01-04 13:59:32 +08:00

optim.py

[WIP] Pruned-transducer-stateless5-for-WenetSpeech (offline and streaming) (#447)

2022-07-28 12:54:27 +08:00

pretrained.py

Use high_freq -400 in computing fbank features. (#1447)

2024-01-04 13:59:32 +08:00

scaling_converter.py

fix wenet stateless5 jit export error (#735)

2022-12-05 23:35:10 +08:00

scaling.py

[WIP] Pruned-transducer-stateless5-for-WenetSpeech (offline and streaming) (#447)

2022-07-28 12:54:27 +08:00

streaming_beam_search.py

apply black on all files

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

streaming_decode.py

streaming_decode.py, relax the audio range from [-1,+1] to [-10,+10] (#1448)

2024-01-05 10:21:27 +08:00

train.py

Replace deprecated pytorch methods (#1814)

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