hubert-large-ls960-ft
The large model fine-tuned on 960h of Librispeech on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz.
Params
—
Context
—
Downloads 30d
646 K
Likes
84
Download history
daily snapshots · 40 days
▲ 334 K in the last 30 days (106.7%)
646 K313 K
Oct 12Oct 22Nov 1Nov 10
646 K313 K
Oct 2Oct 15Oct 28Nov 10
Specifications
- Architecture
- HubertForCTC
- Vocabulary
- 32
- Layers / heads
- 24 / 16
- Licence
- apache-2.0
- First seen on the Hub
- 2022-03-02
- Training datasets
- libri-light, librispeech_asr
- LibriSpeech (clean) (reported)
- 1.9
- Added to our catalog
- 2026-10-02
Compare with any automatic-speech-recognition model