Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
espnet
/
powsm
like
8
Follow
ESPnet
326
Automatic Speech Recognition
ESPnet
4 datasets
multilingual
audio
phone-recognition
grapheme-to-phoneme
phoneme-to-grapheme
arxiv:
2510.24992
arxiv:
2601.14046
License:
cc-by-4.0
Model card
Files
Files and versions
xet
Community
1
Use this model
main
powsm
2.75 GB
1 contributor
History:
20 commits
cjli
Update README.md
21ffa41
verified
6 days ago
data
add model files
3 months ago
exp
add train/feats_stats.npz
3 months ago
textnorm_retrained
Create meta.yaml
12 days ago
.gitattributes
1.52 kB
initial commit
3 months ago
README.md
4.44 kB
Update README.md
6 days ago
meta.yaml
341 Bytes
patch yaml file
3 months ago