speaker-diarization-3.1 vs whisper-bemba-stt

Specs, VRAM requirements and download trends — updated 21 September 2026.

pyannote · A
Params
Context
30d
8.0 M
mit · commercial OK
AbelZimba · B
Params
240 M
Context
30d
534 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification speaker-diarization-3.1 whisper-bemba-stt
Parameters 240 M
Architecture WhisperForConditionalGeneration
Context length
Licence mit
Commercial use Allowed Unknown
Languages
Downloads 30d 7,950,173 534,315
Downloads all time 347.7 M 2.8 M
Quantizations on the Hub SAFETENSORS
Gated Yes — accept licence No
First seen on the Hub 2023-11-16 2026-01-13

Download trend

Daily snapshots, last 56 days (28 Jul – 21 Sep)

10.0 M499 K
speaker-diarization-3.1 whisper-bemba-stt

VRAM side by side

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

whisper-bemba-stt · fp16 1.6 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons