Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
patrickvonplaten
/
data2vec-audio-base-10m-4-gram
like
0
Automatic Speech Recognition
Transformers
PyTorch
librispeech_asr
English
data2vec-audio
speech
Inference Endpoints
arxiv:
2202.03555
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
26f757b
data2vec-audio-base-10m-4-gram
/
language_model
/
attrs.json
Patrick von Platen
up
5c86457
over 2 years ago
raw
Copy download link
history
blame
Safe
78 Bytes
{
"alpha"
:
0.5
,
"beta"
:
1.5
,
"unk_score_offset"
:
-10.0
,
"score_boundary"
:
true
}