ai model report

Is qnguyen3/QUAN-Transcribe-1.0 safe to load?

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

View on HuggingFace

// posture
advisories 100provenance 80resolution 40xyz safety 100load safety 60supply chain 100scanner trust 65code execution 100
fig. 01 — posture on eight axes, 100 is clean. Weakest: resolution at 40.
// the finding
not scoredno advisory applies to a version this model pinsUNKNOWN

LOWShips safetensors plus 2 pickle checkpoint(s) for other tooling (best.pt, lm/vi_4gram.bin); 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.

1 more finding on this model.

Author
qnguyen3
Task
automatic-speech-recognition
License
gemma
Downloads
480
Remote code
not required
Access
gated on HuggingFace
// dependencies

0 direct

PackageEvidenceAdvisoriesWorst

Risk computed 2026-10-20 at 22:53 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.