Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
espnet
/
owsm_v3
like
26
Automatic Speech Recognition
ESPnet
mixed_v3
multilingual
audio
speech-translation
arxiv:
2309.13876
License:
cc-by-4.0
Model card
Files
Files and versions
Community
Use this model
9813a67
owsm_v3
/
exp
/
s2t_train_s2t_transformer_conv2d_size1024_e24_d24_lr2.5e-4_warmup10k_finetune_raw_bpe50000
1 contributor
History:
1 commit
pyf98
add files
1baf504
about 1 year ago
images
add files
about 1 year ago
RESULTS.md
365 Bytes
add files
about 1 year ago
config.yaml
491 kB
add files
about 1 year ago
valid.acc.ave_5best.till50epoch.pth
pickle
Detected Pickle imports (3)
"collections.OrderedDict"
,
"torch.FloatStorage"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
3.55 GB
LFS
add files
about 1 year ago