mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-10 02:22:17 +00:00
f1abce72f8
* Use jsonl for cutsets in the librispeech recipe. * Use lazy cutset for all recipes. * More fixes to use lazy CutSet. * Remove force=True from logging to support Python < 3.8 * Minor fixes. * Fix style issues.
Introduction
The decoder, i.e., the prediction network, is from https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9054419 (Rnn-Transducer with Stateless Prediction Network)
You can use the following command to start the training:
cd egs/tedlium3/ASR
export CUDA_VISIBLE_DEVICES="0,1,2,3"
./transducer_stateless/train.py \
--world-size 4 \
--num-epochs 30 \
--start-epoch 0 \
--exp-dir transducer_stateless/exp \
--max-duration 300