FluidInference / automatic-speech-recognition updated 3 months ago

parakeet-tdt-0.6b-v3-coreml

On‑device multilingual ASR model converted to Core ML for Apple platforms. This model powers FluidAudio’s batch ASR and is the same model used in our backend. It supports 25 European languages and is optimized for low‑latency, private, offline transcription.

Params
Context
Downloads 30d
400 K
Likes
49
Commercial use: allowed cc-by-4.0 Not gated 25 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days
420 K392 K
Jul 28Jul 31Aug 3Aug 6

Specifications

Licence
cc-by-4.0
First seen on the Hub
2025-08-17
Training datasets
nvidia/Granary, nemo/asr-set-3.0
Added to our catalog
2026-07-28