Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
espnet
/
powsm
like
7
Follow
ESPnet
320
Automatic Speech Recognition
ESPnet
4 datasets
multilingual
audio
phone-recognition
grapheme-to-phoneme
phoneme-to-grapheme
arxiv:
2510.24992
License:
cc-by-4.0
Model card
Files
Files and versions
xet
Community
1
Use this model
main
powsm
Commit History
update arxiv
b7676ce
cjli
commited on
Oct 30, 2025
small fix
0724cab
cjli
commited on
Oct 29, 2025
fix example script
5809b0d
cjli
commited on
Oct 28, 2025
add train/feats_stats.npz
e8e2ec7
cjli
commited on
Oct 28, 2025
update readme: example script
647fd96
cjli
commited on
Oct 28, 2025
update readme
b59aa36
cjli
commited on
Oct 28, 2025
fix
b9127ba
cjli
commited on
Oct 28, 2025
add tags
0702ca5
cjli
commited on
Oct 28, 2025
patch yaml file
3d15581
cjli
commited on
Oct 28, 2025
add model files
7880503
cjli
commited on
Oct 28, 2025
initial commit
65e63a2
verified
cjli
commited on
Oct 28, 2025