All models

Sunflower ASR · Luganda

Sunbird AI

Luganda speech to text.

Coming soonCandidate model · No Embiro endpoint yet

What the model can do.

Publisher capabilities, subject to evaluation before any Embiro deployment.

InputAudio
OutputText
  • Audio

Before it goes live.

Embiro service limits, hosting capacity and endpoint compatibility are not confirmed. The specifications below describe the publisher’s model, not an available Embiro service.

API access, when it’s ready.

This model is on the shortlist.

There is no callable Embiro model ID for Sunflower ASR · Luganda yet. We’ll publish tested requests, pricing and serving limits when it becomes available.

Explore models with pilot API access

Under the hood.

Publisher specifications. These do not override the Embiro service limits above.

Published context
Not specified
Parameters
1.55B
Model size
Light

Luganda transcription candidate using the pinned Sunflower checkpoint. Awaiting live deployment validation before API access; Crane remains the Luganda beta. Earlier diagnostic transcripts required substantial correction.

Read the publisher’s model card

No verified benchmark scores are listed in this catalogue for this model.