speaker-diarization-community-1 vs VibeVoice-ASR

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

pyannote · A

Params

—

Context

—

30d

5.3 M

cc-by-4.0 · commercial OK

microsoft · B

Params

8.7 B

Context

—

30d

695 K

mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	speaker-diarization-community-1	VibeVoice-ASR
Parameters	—	8.7 B
Architecture	—	VibeVoiceForASRTraining
Context length	—	—
Licence	cc-by-4.0	mit
Commercial use	Allowed	Allowed
Languages	—	51
Downloads 30d	5,259,760	694,919
Downloads all time	21.3 M	4.2 M
Quantizations on the Hub	—	SAFETENSORS
Gated	Yes — accept licence	No
First seen on the Hub	2025-04-15	2026-01-21

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

5.3 M679 K

speaker-diarization-community-1 VibeVoice-ASR

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

VibeVoice-ASR · fp16 20.9 GB / 24 GB

⚠️ Tight — reduce context