Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
espnet
/
owsm_v4_base_102M
like
1
Follow
ESPnet
293
Automatic Speech Recognition
ESPnet
espnet/yodas_owsmv4
multilingual
audio
speech-translation
language-identification
arxiv:
2406.09282
arxiv:
2401.16658
arxiv:
2309.13876
License:
cc-by-4.0
Model card
Files
Files and versions
xet
Community
1
Use this model
main
owsm_v4_base_102M
/
exp
411 MB
3 contributors
History:
2 commits
pyf98
add logs
5594659
8 months ago
s2t_stats_raw_bpe50000
add model
8 months ago
s2t_train_conv2d8_size384_e6_d6_mel128_raw_bpe50000
add logs
8 months ago