mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 10:02:22 +00:00
Code Issues Packages Projects Releases Wiki Activity
icefall/egs/tedlium3/ASR
History
Wei Kang 5c17255eec
Sort results to make it more convenient to compare decoding results (#522) 
* Sort result to make it more convenient to compare decoding results

* Add cut_id to recognition results

* add cut_id to results for all recipes

* Fix torch.jit.script

* Fix comments

* Minor fixes

* Fix torch.jit.tracing for Pytorch version before v1.9.0
2022-08-12 07:12:50 +08:00
..
local
Replace ChunkedLilcomHdf5Writer with LilcomChunkyWriter. (#411)
2022-06-09 11:18:52 +08:00
pruned_transducer_stateless
Sort results to make it more convenient to compare decoding results (#522)
2022-08-12 07:12:50 +08:00
transducer_stateless
Sort results to make it more convenient to compare decoding results (#522)
2022-08-12 07:12:50 +08:00
prepare.sh
Minor fixes to tedlimu3 to make ./prepare.sh working. (#258)
2022-03-20 20:26:03 +08:00
README.md
Tedlium3 pruned transducer stateless (#261)
2022-04-11 17:08:53 +08:00
RESULTS.md
Update results for tedlium3 pruned RNN-T (#307)
2022-04-11 22:19:26 +08:00
shared
Tedlium3 transducer stateless (#233)
2022-03-18 11:39:06 +08:00

README.md

Introduction

This recipe includes some different ASR models trained with TedLium3.

Transducers

There are various folders containing the name transducer in this folder. The following table lists the differences among them.

Encoder Decoder Comment
transducer_stateless Conformer Embedding + Conv1d
pruned_transducer_stateless Conformer 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.