Fangjun Kuang 8905ef5d59 Fix gigaspeech dataset iterator. ...

Previously, it was reset after every epoch, which may cause it to
always use the first part of the gigaspeech dataset if you choose
a small --giga-prob.

2025-11-28 10:51:21 +08:00

..

__init__.py

Add zipformer from Dan using multi-dataset setup (#675)

2022-11-15 16:56:05 +08:00

asr_datamodule.py

Add zipformer from Dan using multi-dataset setup (#675)

2022-11-15 16:56:05 +08:00

beam_search.py

Add zipformer from Dan using multi-dataset setup (#675)

2022-11-15 16:56:05 +08:00

decode.py

Fix CI tests. (#1974)

2025-07-01 13:47:55 +08:00

decoder.py

Add zipformer from Dan using multi-dataset setup (#675)

2022-11-15 16:56:05 +08:00

encoder_interface.py

Add zipformer from Dan using multi-dataset setup (#675)

2022-11-15 16:56:05 +08:00

export-onnx.py

add export-onnx.py for stateless8 (#1302)

2023-10-11 12:20:12 +08:00

export.py

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

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

gigaspeech.py

Add zipformer from Dan using multi-dataset setup (#675)

2022-11-15 16:56:05 +08:00

jit_pretrained.py

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

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

joiner.py

Add zipformer from Dan using multi-dataset setup (#675)

2022-11-15 16:56:05 +08:00

librispeech.py

Add zipformer from Dan using multi-dataset setup (#675)

2022-11-15 16:56:05 +08:00

model.py

Fix CI tests. (#1974)

2025-07-01 13:47:55 +08:00

optim.py

Add zipformer from Dan using multi-dataset setup (#675)

2022-11-15 16:56:05 +08:00

pretrained.py

Fix CI tests. (#1974)

2025-07-01 13:47:55 +08:00

scaling_converter.py

Add zipformer from Dan using multi-dataset setup (#675)

2022-11-15 16:56:05 +08:00

scaling.py

Add zipformer from Dan using multi-dataset setup (#675)

2022-11-15 16:56:05 +08:00

train.py

Fix gigaspeech dataset iterator.

2025-11-28 10:51:21 +08:00

zipformer.py

Add zipformer from Dan using multi-dataset setup (#675)

2022-11-15 16:56:05 +08:00