femto-jev decision model
femto-jev is a small text and speech decision model with open weights. Check its separate speech frontend, reported tests and out-of-list limits.
By igorktech · Hugging Face weights, 15:42:55 UTC: 11 Nov 2026
A small typed-decision encoder for text, with a separate femto-asr speech frontend. It scores options in a forward pass per question. The maker’s speech tests show that audio frames help on familiar recording conditions but add no benefit on unseen phone speech.
Quick answers
What is femto-jev by igorktech?
femto-jev: A small typed-decision encoder for text, with a separate femto-asr speech frontend.
Who makes femto-jev?
femto-jev: igorktech
Are femto-jev's weights open?
femto-jev: Public weights and single-file Python inference; no text generation Licence: Apache-2.0, with upstream notices
Facts
- Size
- Maker reports 7.7M decision-model parameters and 30 MB fp32 weights; speech frontend adds 2.39M parameters
- Inputs
- The maker reports text or 16 kHz mono speech input through femto-asr; choice, yes/no and score questions
- Access
- Public weights and single-file Python inference; no text generation
- Licence
- Apache-2.0, with upstream notices
- Limits
- English; out-of-list spoken commands are not reliably rejected. Confidence is not an out-of-distribution rejection guarantee
Claims and sources
- The maker reports 73.2% accuracy across 400 typed-decisions test cases containing 2,000 decisions. The model trained on that dataset’s training split. SLURP accuracy is 71.4% with transcript plus frames, against 58.6% with transcript alone; on unseen MInDS-14 phone speech the figures are 55.8% and 56.1%. vendor reportedsource
Links
Source: Card and weights → Source: Inference code → Source: Licence → Source: Configuration →
Related projects
No related projects are listed in the registry.