Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
espnet
/
powsm
like
9
Follow
ESPnet
340
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
42436d8
powsm
1.38 GB
1 contributor
History:
14 commits
cjli
Upload textnorm_retrained/exp/s2t_stats_raw_bpe40000/train/feats_stats.npz with huggingface_hub
42436d8
verified
about 1 month ago
data
add model files
4 months ago
exp
add train/feats_stats.npz
4 months ago
textnorm_retrained
Upload textnorm_retrained/exp/s2t_stats_raw_bpe40000/train/feats_stats.npz with huggingface_hub
about 1 month ago
.gitattributes
Safe
1.52 kB
initial commit
4 months ago
README.md
Safe
3.45 kB
update arxiv
4 months ago
meta.yaml
Safe
341 Bytes
patch yaml file
4 months ago