Steno speech models

The models Steno downloads on Linux and Windows, and on a Mac with the ONNX fallback, where it runs speech recognition through ONNX Runtime.

Path	What
`parakeet-tdt-0.6b-v3-fp32/`	Parakeet TDT 0.6B v3, fp32 ONNX export: `encoder.onnx` with `encoder.weights`, `decoder.onnx`, `joiner.onnx`, `tokens.txt`

Steno pins a commit of this repository and checks every file's size and SHA-256 against its manifest (crates/steno-speech/src/model_store.rs).

Licence: CC BY 4.0, a derivative of NVIDIA's Parakeet TDT 0.6B v3; see ATTRIBUTION.md.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for nicolaischmid/steno-models

Base model

Quantized

(104)

this model