Model Name |
Wav2Vec2
|
Description |
A model pretrained on 16kHz sampled speech audio
|
Use For |
Ideally for short audio of speech
|
Limitations |
Clips will be truncated to a max 6 seconds
|
Graft Default | Yes |
Reference information
Source | |
Trained on |
Libraspeech
|
Paper | |
Embedding Dimension | 768 |