openai/whisper-large-v3-turbo warn
claims base: openai/whisper-large-v3 · chat template: not in config · view on Hugging Face ↗
Ingot findings
Static battery: 1 medium finding(s). Deep battery (behavioral differential, glitch-token pass) not yet run. Weights battery: embedding-norm scan over 51866 tokens (F16, 1280-dim) found 0 undertrained candidates, 0 plain-ASCII. Lineage vs openai/whisper-large-v3: inconsistent. Scanned 2026-08-20 (published from a community scan).
medium License differs from claimed parent (mit vs apache-2.0)
This model declares mit while its claimed base openai/whisper-large-v3 declares apache-2.0. Verify the re-license is permitted before commercial use.
How to fix
Verify the re-license is actually permitted before relying on it.
- Read the parent's license for derivative-work and re-licensing terms — many open-weight licenses (e.g. Llama-family) do not permit arbitrary re-licensing.
- If the re-license is not permitted, the parent's terms govern your use regardless of what this repo declares.
info Embedding-norm glitch scan clean
No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (0.636). The glitch-token data-corruption class has no candidate surface in this model.
How to fixruntime guardweight-level
Keep the affected token strings out of the model's input — the scan-derived runtime guard carries this model's exact blocklist.
- Fetch this model's guard artifact (`/api/v1/guard/<owner>/<model>`): the confirmed corrupting tokens and the low-norm candidate list, derived from the published scan.
- Screen inbound text with it (the `@ingotai/guard` package is a reference implementation) and route flagged records to a different model or human review — verbatim-copy tasks on flagged strings are the failure mode.
- The underlying cause is undertrained embeddings in the weights; a true fix is weight-level (continued pretraining on the affected tokens) — that is not a patch, it's a training job.
medium Weights inconsistent with claimed parent openai/whisper-large-v3
This model declares openai/whisper-large-v3 as its base (relation: unspecified), but mean cosine similarity of 64 sampled token-embedding rows against that parent is only 0.258 (true finetunes, merges, and quantizations sit above 0.8; independently trained weights sit near 0). The lineage label is likely wrong — trained from scratch, derived from a different base, or deliberately mislabeled. Treat provenance claims (training data, safety posture, licensing) as unverified.
How to fix
Fix or verify the `base_model` declaration so lineage checks can run.
- If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
- If you don't: identify the true parent (config architecture + weight shapes narrow it fast) and re-scan with that lineage in mind.
low Weights diverge from claimed parent openai/whisper-large-v3
This model declares openai/whisper-large-v3 as its base (relation: unspecified), but mean cosine similarity of 64 sampled token-embedding rows against that parent is only 0.258 (true finetunes, merges, and quantizations sit above 0.8; independently trained weights sit near 0). Either the lineage label is wrong, or the model was so heavily re-trained, pruned, or distilled that the parent's properties (safety posture, evaluated behavior, licensing basis) should not be assumed to carry over. Verify provenance before relying on the parent's reputation.
How to fix
Fix or verify the `base_model` declaration so lineage checks can run.
- If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
- If you don't: identify the true parent (config architecture + weight shapes narrow it fast) and re-scan with that lineage in mind.
Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.
Fingerprint
The durable weights-and-metadata profile of this model, rebuilt on every scan and deep-battery run. Updated 2026-08-20.
| architecture | whisper · 32 layers · 1280-dim |
| parameters | 808.9M |
| vocabulary | 51,866 tokens |
| license | mit |
| serialization | safetensors |
| chat template | none |
| claimed lineage | openai/whisper-large-v3 |
| lineage verified | inconsistent vs openai/whisper-large-v3 — embedding-row cosine 0.258 |
| glitch-token surface | clean no undertrained tokens |
Full fingerprint
| architectures | WhisperForConditionalGeneration |
| library | transformers |
| pipeline | automatic-speech-recognition |
| repo files | 13 |
| revision | 41f01f3fe87f |
| HF snapshot | 7.9M downloads · 3.3k likes · updated 2024-10-04 · captured 2026-08-20 |
| embedding tensor | model.decoder.embed_tokens.weight · F16 · 51,866×1280 |
| embedding norms | median 0.6361 · mean 0.6352 |
| lineage check | inconsistent — cosine 0.2583 over 64 sampled rows vs openai/whisper-large-v3 |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/openai/whisper-large-v3-turbo)