wav2vec2-base-960h
The base model pretrained and fine-tuned on 960 hours of Librispeech on 16kHz sampled speech audio.
audio → text · made by AI at Meta
Sold by
Nobody in the catalogue publishes a price for this yet.
About
wav2vec2-base-960h — a text model from AI at Meta.
It takes audio and returns text. It was published in March 2022. The catalogue files it under transcribe. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- AI at Meta
- Register
- model
- Takes
- audio
- Returns
- text
- Published
- March 2022
- Parameters
- 94 million · read from its own weights
- Licence
- apache-2.0
Known as 1 name
facebook/wav2vec2-base-960h