Yifan Yang 95b4c90a5e

Merge 70f13e54d814761432acc1c23e9ef4ffd566df41 into 0904e490c5fb424dc5cb4d14ae468e4d32a07dc4

2025-11-30 11:23:35 +08:00

..

asr_datamodule.py

Add qwen-audio style model training: using whisper + qwen2 (#1652)

2024-06-16 12:14:44 +08:00

decode.py

add weights_only=False to torch.load (#1984)

2025-07-10 15:27:08 +08:00

ds_config_zero1.json

fix deepspeed config

2025-06-18 05:04:00 +00:00

label_smoothing.py

minor fixes for the repo (#1775)

2024-10-21 13:51:56 +08:00

model.py

support zipformer encoder

2025-05-08 14:44:09 +00:00

multi_dataset.py

use padding instead of trimming (suggested by @shylockasr)

2025-06-18 04:25:30 +00:00

requirements.txt

init

2025-04-30 09:58:33 +00:00

train.py

Merge 70f13e54d814761432acc1c23e9ef4ffd566df41 into 0904e490c5fb424dc5cb4d14ae468e4d32a07dc4

2025-11-30 11:23:35 +08:00

whisper_encoder_forward_monkey_patch.py

Add qwen-audio style model training: using whisper + qwen2 (#1652)

2024-06-16 12:14:44 +08:00