mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-08 09:32:20 +00:00
Code Issues Packages Projects Releases Wiki Activity
icefall/egs/aishell4/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
[Ready to merge] Pruned transducer stateless5 recipe for AISHELL4 (#399)
2022-06-14 22:19:05 +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
[Ready to merge] Pruned transducer stateless5 recipe for AISHELL4 (#399)
2022-06-14 22:19:05 +08:00
README.md
[Ready to merge] Pruned transducer stateless5 recipe for AISHELL4 (#399)
2022-06-14 22:19:05 +08:00
RESULTS.md
[Ready to merge] Pruned transducer stateless5 recipe for AISHELL4 (#399)
2022-06-14 22:19:05 +08:00
shared
[Ready to merge] Pruned transducer stateless5 recipe for AISHELL4 (#399)
2022-06-14 22:19:05 +08:00

README.md

Introduction

This recipe includes some different ASR models trained with Aishell4 (including S, M and L three subsets).

./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_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.