InterconnectsArtifacts Hub
withVAILVAIL
All models

Kyutai STT 2.6B English

byKyutaiKyutai· 06 Jun 2025
MultimodalSpecial purpose

The French Kyutai team continues to release open audio models. This speech-to-text model is their latest addition.

Specs
Params2.6B
LicenseCC-BY-4.0
Tags
modelsmodels/llmsmodels/llms/multi-modalartifacts/11
Resources
Hugging Face — kyutai/stt-2.6b-enPaper / tech reportAppeared in Artifacts Log #11
Adoption · Interconnects
RAM score
—
Hugging Face Downloads
0
last 30d
22
all time
HF Likes
124

Relative Adoption Metric contextualizes downloads against the model's size bucket.

Related Models

More from Kyutai

Helium-1-2b
KyutaiKyutai30 Apr 2025
Hibiki-M MLX
KyutaiKyutai04 Feb 2025
MoshiVis
KyutaiKyutai27 Jan 2025
moshiko-pytorch-bf16
KyutaiKyutaiRelease date unavailable

Similar Models

OmniAudio-2.6B
NexaAINexaAI11 Dec 2024
Phi-3.5-vision-instruct
MicrosoftMicrosoftRelease date unavailable
Canary-Qwen-2.5B
NVIDIANVIDIA17 Jul 2025
DeepSeek-VL2
DeepSeekDeepSeek13 Dec 2024