Karel Vesely 716b82cc3a

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

- some AudioTransform classes produce audio signals out of range [-1,+1]
   - Resample produced 1.0079
   - The range [-10,+10] was chosen to still be able to reliably
     distinguish from the [-32k,+32k] signal...
- this is related to : https://github.com/lhotse-speech/lhotse/issues/1254

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

..

__init__.py

Narrower and deeper conformer (#330)

2022-05-23 14:39:11 +08:00

asr_datamodule.py

Narrower and deeper conformer (#330)

2022-05-23 14:39:11 +08:00

beam_search.py

Narrower and deeper conformer (#330)

2022-05-23 14:39:11 +08:00

conformer.py

Add onnx export support for pruned_transducer_stateless5 (#883)

2023-02-07 17:47:08 +08:00

decode_stream.py

Support dynamic chunk streaming training in pruned_transcuder_stateless5 (#454)

2022-07-29 16:40:06 +08:00

decode.py

Shallow fusion for Aishell (#954)

2023-04-03 16:20:29 +08:00

decoder.py

Narrower and deeper conformer (#330)

2022-05-23 14:39:11 +08:00

encoder_interface.py

Narrower and deeper conformer (#330)

2022-05-23 14:39:11 +08:00

export-onnx-streaming.py

Fix exporting decoder model to onnx (#1264)

2023-09-22 09:57:15 +08:00

export-onnx.py

Fix exporting decoder model to onnx (#1264)

2023-09-22 09:57:15 +08:00

export.py

Use tokens.txt to replace bpe.model (#1162)

2023-08-12 16:53:59 +08:00

joiner.py

Narrower and deeper conformer (#330)

2022-05-23 14:39:11 +08:00

lstmp.py

fix librispeech ASR pruned_transducer_stateless5 export (#704)

2022-11-25 14:39:56 +08:00

model.py

Narrower and deeper conformer (#330)

2022-05-23 14:39:11 +08:00

onnx_check.py

Add onnx export support for pruned_transducer_stateless5 (#883)

2023-02-07 17:47:08 +08:00

onnx_decode.py

support decoding and computing RTF on test sets with onnx models (#995)

2023-04-12 19:04:50 +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

Add onnx export support for pruned_transducer_stateless5 (#883)

2023-02-07 17:47:08 +08:00

optim.py

Narrower and deeper conformer (#330)

2022-05-23 14:39:11 +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 librispeech ASR pruned_transducer_stateless5 export (#704)

2022-11-25 14:39:56 +08:00

scaling.py

Narrower and deeper conformer (#330)

2022-05-23 14:39:11 +08:00

streaming_beam_search.py

Support dynamic chunk streaming training in pruned_transcuder_stateless5 (#454)

2022-07-29 16:40:06 +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

test_model.py

Fix typo (#1114)

2023-06-02 14:12:42 +08:00

train.py

fixes for init value of diagnostics.TensorDiagnosticOptions (#1269)

2023-09-24 17:06:47 +08:00