Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
facebook
/
data2vec-audio-large-960h
like
7
Follow
AI at Meta
3,390
Automatic Speech Recognition
Transformers
PyTorch
librispeech_asr
English
data2vec-audio
speech
hf-asr-leaderboard
Eval Results
Inference Endpoints
arxiv:
2202.03555
License:
apache-2.0
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
27aba26
data2vec-audio-large-960h
/
special_tokens_map.json
patrickvonplaten
add model
1e95390
over 2 years ago
raw
Copy download link
history
blame
Safe
85 Bytes
{
"bos_token"
:
"<s>"
,
"eos_token"
:
"</s>"
,
"unk_token"
:
"<unk>"
,
"pad_token"
:
"<pad>"
}