speaker-diarization-3.1 vs mms-300m-1130-forced-aligner

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

pyannote · A
Params
Context
30d
8.9 M
mit · commercial OK
MahmoudAshraf · B
Params
320 M
Context
30d
2.5 M
cc-by-nc-4.0 · non-commercial

Specification comparison

Differences are highlighted; identical values are muted.

Specification speaker-diarization-3.1 mms-300m-1130-forced-aligner
Parameters 320 M
Architecture Wav2Vec2ForCTC
Context length
Licence mit cc-by-nc-4.0
Commercial use Allowed Not allowed
Languages 158
Downloads 30d 8,909,178 2,488,238
Downloads all time 333.7 M 72.6 M
Quantizations on the Hub SAFETENSORS
Gated Yes — accept licence No
First seen on the Hub 2023-11-16 2024-05-02

Download trend

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

8.9 M2.4 M
speaker-diarization-3.1 mms-300m-1130-forced-aligner

VRAM side by side

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

mms-300m-1130-forced-aligner · fp16 1.9 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons