mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-12-11 06:55:27 +00:00
915e8e399c
- Added CHiME-4 dataset integration in asr_datamodule.py - Added Hugging Face upload script - Added RIR augmentation - Added Self-Distillation Training
Introduction
The encoder consists of LSTM layers in this folder. You can use the following command to start the training:
cd egs/librispeech/ASR
export CUDA_VISIBLE_DEVICES="0,1,2"
./transducer_lstm/train.py \
--world-size 3 \
--num-epochs 30 \
--start-epoch 0 \
--exp-dir transducer_lstm/exp \
--full-libri 1 \
--max-duration 300 \
--lr-factor 3