mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 01:52:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update results for torchaudio RNN-T. (#322)

Browse Source
This commit is contained in:
Fangjun Kuang 2022-04-20 11:15:10 +08:00 committed by GitHub
parent fce7f3cd9a
commit 3607c516d6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
egs/librispeech/ASR/RESULTS.md
View File

@ -7,7 +7,7 @@ This is with a reworked version of the conformer encoder, with many changes.
#### Training on fulll librispeech #### Training on fulll librispeech
using commit `34aad74a2c849542dd5f6359c9e6b527e8782fd6`. Using commit `34aad74a2c849542dd5f6359c9e6b527e8782fd6`.
See <https://github.com/k2-fsa/icefall/pull/288> See <https://github.com/k2-fsa/icefall/pull/288>
The WERs are: The WERs are:
@ -353,8 +353,12 @@ You can find a pretrained model by visiting
##### 2022-04-19 ##### 2022-04-19
[transducer_stateless2](./transducer_stateless2) [transducer_stateless2](./transducer_stateless2)
This version uses torchaudio's RNN-T loss. This version uses torchaudio's RNN-T loss.
Using commit `fce7f3cd9a486405ee008bcbe4999264f27774a3`.
See <https://github.com/k2-fsa/icefall/pull/316>
| | test-clean | test-other | comment | | | test-clean | test-other | comment |
|-------------------------------------|------------|------------|--------------------------------------------------------------------------------| |-------------------------------------|------------|------------|--------------------------------------------------------------------------------|
| greedy search (max sym per frame 1) | 2.65 | 6.30 | --epoch 59 --avg 10 --max-duration 600 | | greedy search (max sym per frame 1) | 2.65 | 6.30 | --epoch 59 --avg 10 --max-duration 600 |