whisper-large-v3-turbo vs wav2vec2-xls-r-300m-cs-250

Specs, VRAM requirements and download trends — updated 6 August 2026.

openai · A

Params

810 M

Context

—

30d

8.7 M

mit · commercial OK

comodoro · B

Params

320 M

Context

—

30d

1.4 M

apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	whisper-large-v3-turbo	wav2vec2-xls-r-300m-cs-250
Parameters	810 M	320 M
Architecture	WhisperForConditionalGeneration	Wav2Vec2ForCTC
Context length	—	—
Licence	mit	apache-2.0
Commercial use	Allowed	Allowed
Languages	99	1
Downloads 30d	8,715,451	1,394,634
Downloads all time	106.8 M	11.2 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2024-10-01	2022-03-02

Daily snapshots, last 10 days (28 Jul – 6 Aug)

8.7 M1.3 M

whisper-large-v3-turbo wav2vec2-xls-r-300m-cs-250

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

wav2vec2-xls-r-300m-cs-250 · fp16 1.9 GB / 24 GB

✅ Runs comfortably

whisper-large-v3-turbo · fp16 2.4 GB / 24 GB

✅ Runs comfortably