sapoepsilon/whispera-voice-commands

🤗 Hugging Face sourcetext-generationmit494M params988 MBsafetensors✓ 2 checksumsupdated today

Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo sapoepsilon/whispera-voice-commands ./model-folder

Needs a seeder →

Whispera Voice Commands (MLX)

This repo hosts a small MLX-compatible model fine-tuned to convert natural-language (voice-like) macOS commands into structured JSON:

{"category":"apps","operation":"open","app":"chrome"}

That JSON is intended to be mapped to real shell commands using the templates/patterns in macos_operations.json from the main project repo.

Project: https://github.com/sapoepsilon/whisperaModel

Usage (mlx_lm)

mlx_lm.generate --model sapoepsilon/whispera-voice-commands --prompt "open safari" --max-tokens 100 --temp 0.1

Notes

This is a fused (merged) model for convenience (base + LoRA adapters).
Outputs are JSON only; you should parse the first {...} block and then apply your own command templates.