Fangjun Kuang 8136ad775b

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

See also https://github.com/k2-fsa/sherpa-onnx/issues/514

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

..

__init__.py

…

asr_datamodule.py

…

beam_search.py

…

decode.py

Modified beam search with RNNLM rescoring (#1002)

2023-04-17 16:43:00 +08:00

decoder.py

…

encoder_interface.py

…

export-for-ncnn.py

…

export-onnx-zh.py

…

export-onnx.py

…

export.py

…

gigaspeech.py

…

jit_pretrained.py

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

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

joiner.py

…

librispeech.py

…

lstm.py

…

lstmp.py

…

model.py

…

ncnn-decode.py

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

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

onnx_check.py

…

onnx_pretrained.py

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

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

optim.py

…

pretrained.py

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

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

scaling_converter.py

…

scaling.py

…

streaming-ncnn-decode.py

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

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

streaming-onnx-decode.py

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

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

test_lstmp.py

…

train.py

…