Model page

Qwen/Qwen3-ASR-1.7B pass

downloads 4.5Mlikes 1.0klicense apache-2.0arch qwen3_asrparams 2349.2Mupdated 2026-01-30

chat template: not in config · view on Hugging Face ↗

Ingot findings

Static battery clean: safetensors weights, license declared, no template/tokenizer drift detected. Deep battery not yet run. Weights battery: embedding-norm scan over 151936 tokens (BF16, 2048-dim) found 2983 undertrained candidates, 0 plain-ASCII. Scanned 2026-08-20 (published from a community scan).

low Undertrained tokens in vocabulary (non-ASCII tail)

Embedding-norm scan flagged 2983 undertrained tokens (norm < 0.3× the vocabulary median), but 0 decode to plain-ASCII strings, so exposure in English-language pipelines is limited. Behavioral confirmation requires the GPU deep battery.

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.

  1. 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.
  2. 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.
  3. 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.

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.

architectureqwen3_asr
parameters2349.2M
vocabulary151,936 tokens
licenseapache-2.0
serializationsafetensors
chat templatenone
glitch-token surface2,983 undertrained candidates, 0 plain-ASCII
Full fingerprint
architecturesQwen3ASRForConditionalGeneration
pipelineautomatic-speech-recognition
repo files12
revision7278e1e70fe2
HF snapshot4.5M downloads · 1.0k likes · updated 2026-01-30 · captured 2026-08-20
embedding tensorthinker.model.embed_tokens.weight · BF16 · 151,936×2048
embedding normsmedian 1.394 · mean 1.3598
lineage checkno claimed base model

Verdict badge

Ship the verdict in your README — it always shows the latest published analysis:

Ingot verdict: pass

[![Ingot scan](https://ingot.tools/api/v1/models/Qwen/Qwen3-ASR-1.7B/badge.svg)](https://ingot.tools/models/Qwen/Qwen3-ASR-1.7B)
Gate it in CI