A speech-input LLM that feeds Whisper encoder features through a learned projector into Llama 3.2 1B Instruct, so it can respond to spoken input without a separate transcription step. It replies in text, so pair it with a TTS voice.
ggerganov/whisper.cpp
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelSpeech to textEst. Single-board computerEstimated minimum compute for inference: Raspberry Pi 5 class CPU. Not a benchmark.MITWorks with GotchiGotchi Local can download this as an offline speech fallback on your computer.
About
GGML-format conversions of the OpenAI Whisper checkpoints, from tiny to large, for the whisper.cpp C/C++ inference engine.
Why it matters for physical AI
Gotchi Local downloads the tiny and base English files from this repo for offline transcription on your computer.
Summary written by FrontierOS in our own words. The upstream card and license govern use. Metadata checked 27 Sep 2026. Read the full card on Hugging Face
Files, weights and version history live on Hugging Face. FrontierOS indexes this repo; it does not host or mirror it.
hf download ggerganov/whisper.cppUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.
Which offline voices should Gotchi Local ship next?
Today Gotchi Local can download Whisper.cpp for transcription and a Piper voice for speech, both from Hugging Face, as offline fallbacks for when it is not using the FrontierOS backend.
How Gotchi uses models today
The Watcher listens and shows your pet. Heavy models do not run on the device itself.
More speech to text
Browse allA faster Whisper large-v3 derivative whose decoder is cut from 32 layers to 4, giving multilingual transcription in roughly 100 languages at a small accuracy cost (it was not fine-tuned for translation).
The small size of the Moonshine Streaming family, an English-only encoder-decoder recognizer that uses a sliding-window encoder so it can transcribe live audio with low latency on edge hardware.