ai model report

Is KittenML/kitten-tts-2 safe to load?

CLEAN risk. 0 of 0 tracked dependencies carry advisories. Driven by No version-matched advisories and no malicious packages..

View on HuggingFace

// posture
advisories 100provenance 100resolution 80xyz safety 100load safety 60supply chain 100scanner trust 55code execution 100
fig. 01 — posture on eight axes, 100 is clean. Weakest: scanner trust at 55.
// the finding
not scoredno advisory applies to a version this model pinsCLEAN

LOWShips safetensors plus 51 pickle checkpoint(s) for other tooling (cpp/default/decoder.pt, cpp/student_w4/decoder.pt, cpp/student_w8/decoder.pt, ...); from_pretrained never loads these, even with use_safetensors=False, but code that torch.load()s them directly (a reference implementation, a training script) executes pickle.

Author
KittenML
Task
text-to-speech
License
other
Downloads
7,737
Remote code
not required
// dependencies

0 direct

PackageEvidenceAdvisoriesWorst

Risk computed 2026-10-11 at 00:51 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.

Model risk is computed from the model's declared and observed Python dependencies and the code it ships. If a finding is wrong, tell us.