whisper-base vs wav2vec2-large-xlsr-53-russian

Specs, VRAM requirements and download trends — updated 10 November 2026.

openai · A · Open weights
Params
70 M
Context
—
30d
4.6 M
apache-2.0 · commercial OK
jonatasgrosman · B · Open weights
Params
—
Context
—
30d
3.8 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification whisper-base wav2vec2-large-xlsr-53-russian
Parameters 70 M —
Architecture WhisperForConditionalGeneration Wav2Vec2ForCTC
Context length — —
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 99 1
Downloads 30d 4,637,569 3,771,876
Downloads all time 55.3 M 145.2 M
Quantizations on the Hub SAFETENSORS —
Gated No No
First seen on the Hub 2022-09-26 2022-03-02

Download trend

Daily snapshots, last 90 days (13 Aug – 10 Nov)

4.6 M1.5 M
whisper-base wav2vec2-large-xlsr-53-russian A overtook B on 6 Nov

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

whisper-base · fp16 0.8 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons