facebook / feature-extraction updated 4 years ago

hubert-base-ls960

The base model pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz.

Params
Context
Downloads 30d
498 K
Likes
77
Commercial use: allowed apache-2.0 Not gated 1 languages View on Hugging Face ↗

Download history

daily snapshots · 55 days
▲ 91 K in the last 30 days (22.3%)
905 K407 K
Jul 28Aug 15Sep 2Sep 20

Specifications

Architecture
HubertModel
Vocabulary
32
Layers / heads
12 / 12
Licence
apache-2.0
First seen on the Hub
2022-03-02
Training datasets
librispeech_asr
Added to our catalog
2026-07-28
Compare with any feature-extraction model