speaker-diarization-3.1 vs wav2vec2-large-xlsr-kazakh

Specs, VRAM requirements and download trends — updated 24 October 2026.

pyannote · A · Open weights
Params
—
Context
—
30d
6.7 M
mit · commercial OK
aismlv · B · Open weights
Params
320 M
Context
—
30d
525 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification speaker-diarization-3.1 wav2vec2-large-xlsr-kazakh
Parameters — 320 M
Architecture — Wav2Vec2ForCTC
Context length — —
Licence mit apache-2.0
Commercial use Allowed Allowed
Languages — 1
Downloads 30d 6,748,760 525,131
Downloads all time 355.3 M 2.7 M
Quantizations on the Hub — SAFETENSORS
Gated Yes — accept licence No
First seen on the Hub 2023-11-16 2022-03-02

Download trend

Daily snapshots, last 89 days (28 Jul – 24 Oct)

10.0 M366 K
speaker-diarization-3.1 wav2vec2-large-xlsr-kazakh

VRAM side by side

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

wav2vec2-large-xlsr-kazakh · fp16 1.9 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons