whisper-large-v3-turbo vs hubert-large-ls960-ft
Specs, VRAM requirements and download trends — updated 10 November 2026.
facebook · B · Open weights
Params
—
Context
—
30d
646 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | whisper-large-v3-turbo | hubert-large-ls960-ft |
|---|---|---|
| Parameters | 810 M | — |
| Architecture | WhisperForConditionalGeneration | HubertForCTC |
| Context length | — | — |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 99 | 1 |
| Downloads 30d | 5,175,000 | 646,093 |
| Downloads all time | 127.5 M | 20.6 M |
| Quantizations on the Hub | SAFETENSORS | — |
| Gated | No | No |
| First seen on the Hub | 2024-10-01 | 2022-03-02 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
8.0 M313 K
whisper-large-v3-turbo
hubert-large-ls960-ft
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
whisper-large-v3-turbo · fp16
2.4 GB / 24 GB