{
 "schema_version": "1.7.0",
 "id": "x_NXMC-2023-0030",
 "modified": "2026-10-19T02:33:38.839Z",
 "published": "2026-10-18T09:00:52.565Z",
 "summary": "whisper-large-v3: tokenizer change at d8411bd (2023-11-07)",
 "details": "whisper-large-v3: pad token unset to \"<|endoftext|>\"; batched training masks a different id (2023-11-07).\n\nRepository: https://huggingface.co/openai/whisper-large-v3. Revisions from d8411bd4e55c0bca39e60653a0fe26ae8591859a onward carry this change; a pin at 8a2a8a3419314d1d44b89aec06271ca4394778f7 or earlier does not.\n\nChanged keys:\n- tokenizer pad_token: unset -> <|endoftext|> (tokenizer)\n\nThis record says what the change does mechanically. It is not a report that anything broke for anyone.",
 "affected": [
  {
   "ranges": [
    {
     "type": "GIT",
     "repo": "https://huggingface.co/openai/whisper-large-v3",
     "events": [
      {
       "introduced": "d8411bd4e55c0bca39e60653a0fe26ae8591859a"
      }
     ]
    }
   ],
   "database_specific": {
    "model": "openai/whisper-large-v3",
    "previous_revision": "8a2a8a3419314d1d44b89aec06271ca4394778f7"
   }
  }
 ],
 "references": [
  {
   "type": "INTRODUCED",
   "url": "https://huggingface.co/openai/whisper-large-v3/commit/d8411bd4e55c0bca39e60653a0fe26ae8591859a"
  },
  {
   "type": "PACKAGE",
   "url": "https://huggingface.co/openai/whisper-large-v3"
  },
  {
   "type": "WEB",
   "url": "https://www.neurarch.com/changes-feeds/models/openai/whisper-large-v3.html"
  }
 ],
 "database_specific": {
  "source": "neurarch model change tracker",
  "model": "openai/whisper-large-v3",
  "kind": "tokenizer",
  "classes": [
   "tokenizer"
  ],
  "changed_keys": [
   {
    "file": "tokenizer",
    "key": "pad_token",
    "before": null,
    "after": "<|endoftext|>",
    "class": "tokenizer"
   }
  ],
  "impact": {
   "memory": false,
   "serving": true,
   "tokenizer": true,
   "licence": null
  },
  "breaking": false,
  "breaking_rule": "https://www.neurarch.com/changes-feeds/advisories/index.json#breaking_rule",
  "consequence": {
   "params": null,
   "weightsGbBf16": null,
   "trainPeakGb": null,
   "fingerprint": null,
   "context": null,
   "eos": null,
   "bos": null
  },
  "commit_date": "2023-11-07T18:53:52.000Z",
  "detected_at": "2026-10-18T09:00:52.565Z",
  "detected_by": "backfill",
  "days_since_first_commit": 0,
  "license": "CC-BY-4.0"
 }
}