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

..

asr_datamodule.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

beam_search.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

decode_stream.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

decode.py

Fix style issues. (#937)

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

decoder.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

do_not_use_it_directly.py

Replace deprecated pytorch methods (#1814)

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

encoder_interface.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

export-for-ncnn.py

Strengthened style constraints (#1527)

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

export.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

jit_trace_export.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

jit_trace_pretrained.py

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

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

joiner.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

model.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

optim.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

pretrained.py

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

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

scaling_converter.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

scaling.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

streaming_beam_search.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

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

streaming-ncnn-decode.py

export script to ncnn for csj (#912)

2023-02-16 19:47:54 +08:00

TelegramStreamIO.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

test_model.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

tokenizer.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00

train.py

Replace deprecated pytorch methods (#1814)

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

zipformer_for_ncnn_export_only.py

Rename zipformer2 to zipformer_for_ncnn_export_only to avoid confusion. (#1407)

2023-12-08 14:29:24 +08:00

zipformer.py

CSJ pruned_transducer_stateless7_streaming (#892)

2023-02-13 22:19:50 +08:00