Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
facebook
/
wav2vec2-xlsr-53-espeak-cv-ft
like
22
Automatic Speech Recognition
Transformers
PyTorch
common_voice
wav2vec2
speech
audio
phoneme-recognition
Inference Endpoints
arxiv:
2109.11680
License:
apache-2.0
Model card
Files
Files and versions
Community
10
Train
Deploy
Use this model
5414c23
wav2vec2-xlsr-53-espeak-cv-ft
/
special_tokens_map.json
patrickvonplaten
add model
cf4fcb8
almost 3 years ago
raw
Copy download link
history
blame
No virus
85 Bytes
{
"bos_token"
:
"<s>"
,
"eos_token"
:
"</s>"
,
"unk_token"
:
"<unk>"
,
"pad_token"
:
"<pad>"
}