mirrors/icefall
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
icefall/egs/aishell/ASR/pruned_transducer_stateless7_streaming
History
pkufool 4ea201f410 minor fixes
2023-11-18 18:35:42 +08:00
..
asr_datamodule.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
beam_search.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
decode_stream.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
decode.py
minor fixes
2023-11-18 18:35:42 +08:00
decoder.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
encoder_interface.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
export-for-ncnn-zh.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
export-for-ncnn.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
export-onnx-zh.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
export-onnx.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
export.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
jit_pretrained.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
jit_trace_export.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
jit_trace_pretrained.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
joiner.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
model.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
ncnn_custom_layer.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
onnx_check.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
onnx_model_wrapper.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
onnx_pretrained.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
optim.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
pretrained.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
README.md
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
scaling_converter.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
scaling.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
streaming_beam_search.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
streaming_decode.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
streaming-ncnn-decode.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
test_model.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
train2.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
train.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
zipformer2.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +08:00
zipformer.py
[WIP] AISHELL-1 pruned transducer stateless7 streaming recipe (#1300)
2023-10-16 16:28:16 +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 ./train2.py. The only purpose of ./emformer2.py and ./train2.py is for exporting to sherpa-ncnn.