mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 10:02:22 +00:00

History

Add function display_and_save_batch in wenetspeech/pruned_transducer_stateless2/train.py (#528 )

* Add function display_and_save_batch in egs/wenetspeech/ASR/pruned_transducer_stateless2/train.py

* Modify function: display_and_save_batch

* Delete empty line in pruned_transducer_stateless2/train.py

* Modify code format

2022-08-13 11:09:54 +08:00

local

Fix preparing char based lang and add multiprocessing for wenetspeech text segmentation (#513 )

2022-08-03 19:19:40 +08:00

pruned_transducer_stateless2

Add function display_and_save_batch in wenetspeech/pruned_transducer_stateless2/train.py (#528 )

2022-08-13 11:09:54 +08:00

pruned_transducer_stateless5

Sort results to make it more convenient to compare decoding results (#522 )

2022-08-12 07:12:50 +08:00

prepare.sh

Fix preparing char based lang and add multiprocessing for wenetspeech text segmentation (#513 )

2022-08-03 19:19:40 +08:00

README.md

[WIP] Pruned-transducer-stateless5-for-WenetSpeech (offline and streaming) (#447 )

2022-07-28 12:54:27 +08:00

RESULTS.md

Add other decoding methods (nbest, nbest oracle, nbest LG) for wenetspeech pruned rnnt2 (#482 )

2022-07-29 12:03:08 +08:00

shared

[Ready to merge] Pruned Transducer Stateless2 for WenetSpeech (char-based) (#349 )

2022-05-23 17:13:01 +08:00

README.md

Introduction

This recipe includes some different ASR models trained with WenetSpeech.

./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
`pruned_transducer_stateless5`	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.