wav2vec2-large-xlsr-53-japanese vs whisper-medium

Specs, VRAM requirements and download trends — updated 2 November 2026.

jonatasgrosman · A · Open weights
Params
—
Context
—
30d
16.2 M
apache-2.0 · commercial OK
openai · B · Open weights
Params
760 M
Context
—
30d
379 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification wav2vec2-large-xlsr-53-japanese whisper-medium
Parameters — 760 M
Architecture Wav2Vec2ForCTC WhisperForConditionalGeneration
Context length — —
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 1 99
Downloads 30d 16,184,839 379,408
Downloads all time 127.3 M 20.7 M
Quantizations on the Hub — SAFETENSORS
Gated No No
First seen on the Hub 2022-03-02 2022-09-26

Download trend

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

17.9 M305 K
wav2vec2-large-xlsr-53-japanese whisper-medium

VRAM side by side

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

whisper-medium · fp16 4.0 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons