mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-08 09:32:20 +00:00
Code Issues Packages Projects Releases Wiki Activity
icefall/egs/alimeeting/ASR
History
Fangjun Kuang fba5e67d5e
Fix CI tests. (#1974) 
- Introduce unified AMP helpers (create_grad_scaler, torch_autocast) to handle 
  deprecations in PyTorch ≥2.3.0

- Replace direct uses of torch.cuda.amp.GradScaler and torch.cuda.amp.autocast 
  with the new utilities across all training and inference scripts

- Update all torch.load calls to include weights_only=False for compatibility with 
  newer PyTorch versions
2025-07-01 13:47:55 +08:00
..
local
Whisper large fine-tuning on wenetspeech, mutli-hans-zh (#1483)
2024-03-07 19:04:27 +08:00
pruned_transducer_stateless2
Fix CI tests. (#1974)
2025-07-01 13:47:55 +08:00
prepare.sh
fixed a typo in prepare.sh for alimeeting recipes (#1747)
2024-09-08 17:10:17 +08:00
README.md
[Ready to merge] Pruned_transducer_stateless2 for alimeeting dataset (#378)
2022-06-04 13:47:46 +08:00
RESULTS.md
[Ready to merge] Pruned_transducer_stateless2 for alimeeting dataset (#378)
2022-06-04 13:47:46 +08:00
shared
[Ready to merge] Pruned_transducer_stateless2 for alimeeting dataset (#378)
2022-06-04 13:47:46 +08:00

README.md

Introduction

This recipe includes some different ASR models trained with Alimeeting (far).

./RESULTS.md contains the latest results.

Transducers

There are various folders containing the name transducer in this folder. The following table lists the differences among them.

Encoder Decoder Comment
pruned_transducer_stateless2 Conformer(modified) Embedding + Conv1d Using k2 pruned RNN-T loss

The decoder in transducer_stateless is modified from the paper Rnn-Transducer with Stateless Prediction Network. We place an additional Conv1d layer right after the input embedding layer.