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

..

asr_datamodule.py

Simplified memory bank for Emformer (#440)

2022-07-12 19:19:58 +08:00

beam_search.py

Simplified memory bank for Emformer (#440)

2022-07-12 19:19:58 +08:00

decode.py

Fix style issues. (#937)

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

decoder.py

Simplified memory bank for Emformer (#440)

2022-07-12 19:19:58 +08:00

do_not_use_it_directly.py

Rename train2.py to avoid confusion (#1386)

2023-11-17 18:12:59 +08:00

emformer2.py

Add ONNX support for Zipformer and ConvEmformer (#884)

2023-02-09 00:02:38 +08:00

emformer.py

fix conv_emformer2, when using right_context_length=0 (#1076)

2023-05-21 20:31:54 +08:00

encoder_interface.py

Simplified memory bank for Emformer (#440)

2022-07-12 19:19:58 +08:00

export-for-ncnn.py

Rename train2.py to avoid confusion (#1386)

2023-11-17 18:12:59 +08:00

export-onnx.py

Rename train2.py to avoid confusion (#1386)

2023-11-17 18:12:59 +08:00

export.py

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

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

jit_pretrained.py

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

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

joiner.py

Simplified memory bank for Emformer (#440)

2022-07-12 19:19:58 +08:00

lstmp.py

Convert conv-emformer to ncnn (#717)

2022-12-06 16:34:27 +08:00

model.py

Simplified memory bank for Emformer (#440)

2022-07-12 19:19:58 +08:00

onnx_pretrained.py

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

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

optim.py

Simplified memory bank for Emformer (#440)

2022-07-12 19:19:58 +08:00

scaling_converter.py

Convert conv-emformer to ncnn (#717)

2022-12-06 16:34:27 +08:00

scaling.py

Simplified memory bank for Emformer (#440)

2022-07-12 19:19:58 +08:00

stream.py

Simplified memory bank for Emformer (#440)

2022-07-12 19:19:58 +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

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

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

test_emformer.py

Simplified memory bank for Emformer (#440)

2022-07-12 19:19:58 +08:00

train.py

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

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