mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 10:02:22 +00:00
Code Issues Packages Projects Releases Wiki Activity
icefall/egs/commonvoice/ASR/pruned_transducer_stateless7_streaming
History
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
Zipformer recipe for CommonVoice (#1546)
2024-04-09 11:37:08 +08:00
beam_search.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
decode_stream.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
decode.py
Zipformer recipe for CommonVoice (#1546)
2024-04-09 11:37:08 +08:00
decoder.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
do_not_use_it_directly.py
Replace deprecated pytorch methods (#1814)
2024-12-16 10:24:16 +08:00
encoder_interface.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
export-for-ncnn-zh.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
export-for-ncnn.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
export-onnx.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
export.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
finetune.py
Replace deprecated pytorch methods (#1814)
2024-12-16 10:24:16 +08:00
generate_model_from_checkpoint.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
jit_pretrained.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
jit_trace_export.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
jit_trace_pretrained.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
joiner.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
model.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
onnx_check.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
onnx_model_wrapper.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
onnx_pretrained.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
optim.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
pretrained.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
README.md
Rename train2.py to avoid confusion (#1386)
2023-11-17 18:12:59 +08:00
scaling_converter.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
scaling.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
streaming_beam_search.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
streaming_decode.py
Zipformer recipe for CommonVoice (#1546)
2024-04-09 11:37:08 +08:00
streaming-ncnn-decode.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00
test_model.py
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +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
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018)
2023-11-09 22:07:28 +08:00

README.md

This recipe implements Streaming Zipformer-Transducer model.

See https://k2-fsa.github.io/icefall/recipes/Streaming-ASR/librispeech/zipformer_transducer.html for detailed tutorials.

./emformer.py and ./train.py are basically the same as ./emformer2.py and ./do_not_use_it_directly.py. The only purpose of ./emformer2.py and ./do_not_use_it_directly.py is for exporting to sherpa-ncnn.