mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-08 09:32:20 +00:00
1d44da845b
* Begin to add RNN-T training for librispeech. * Copy files from conformer_ctc. Will edit it. * Use conformer/transformer model as encoder. * Begin to add training script. * Add training code. * Remove long utterances to avoid OOM when a large max_duraiton is used. * Begin to add decoding script. * Add decoding script. * Minor fixes. * Add beam search. * Use LSTM layers for the encoder. Need more tunings. * Use stateless decoder. * Minor fixes to make it ready for merge. * Fix README. * Update RESULT.md to include RNN-T Conformer. * Minor fixes. * Fix tests. * Minor fixes. * Minor fixes. * Fix tests.
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/librispeech/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 \
--full-libri 1 \
--max-duration 250 \
--lr-factor 2.5