icefall

mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-08 09:32:20 +00:00

History

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

Fix CI tests. (#1974 )

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

tdnn

Fix CI tests. (#1974 )

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

transducer

apply black on all files

2022-11-17 09:42:17 -05:00

prepare.sh

Support CTC decoding on CPU using OpenFst and kaldi decoders. (#1244 )

2023-09-26 16:36:19 +08:00

README.md

Fix doc URLs (#1660 )

2024-06-21 11:10:14 +08:00

shared

Add recipe for the yes_no dataset. (#16 )

2021-08-23 11:36:29 +08:00

README.md

Yesno recipe

This is the simplest ASR recipe in icefall.

It can be run on CPU and takes less than 30 seconds to get the following WER:

[test_set] %WER 0.42% [1 / 240, 0 ins, 1 del, 0 sub ]

Please refer to https://k2-fsa.github.io/icefall/recipes/Non-streaming-ASR/yesno/index.html for detailed instructions.