Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
espnet
/
powsm
like
5
Follow
ESPnet
311
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
/
exp
1.38 GB
1 contributor
History:
2 commits
cjli
add train/feats_stats.npz
e8e2ec7
about 1 month ago
s2t_stats_raw_bpe40000
add train/feats_stats.npz
about 1 month ago
s2t_train_s2t_ebf_conv2d_size768_e9_d9_piecewise_lr5e-4_warmup60k_flashattn_raw_bpe40000
add model files
about 1 month ago