{
 "schema_version": "1.7.0",
 "id": "x_NXMC-2023-0031",
 "modified": "2026-10-19T02:33:38.839Z",
 "published": "2026-10-18T09:00:52.565Z",
 "summary": "whisper-large-v3: tokenizer change at 9ef08b9 (2023-11-16)",
 "details": "whisper-large-v3: EOS changed from 50256 to 50257; anything fine-tuned or served against the old value stops at a different token; BOS changed from 50256 to 50257; prompts built by the old tokenizer start with a different token (2023-11-16).\n\nRepository: https://huggingface.co/openai/whisper-large-v3. Revisions from 9ef08b92d5117306d28a6bcba2ca4ba407155f65 onward carry this change; a pin at ca3e273640c81277b244489dc4a55c3eb9764436 or earlier does not.\n\nChanged keys:\n- bos_token_id: 50256 -> 50257 (tokenizer)\n- eos_token_id: 50256 -> 50257 (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": "9ef08b92d5117306d28a6bcba2ca4ba407155f65"
      }
     ]
    }
   ],
   "database_specific": {
    "model": "openai/whisper-large-v3",
    "previous_revision": "ca3e273640c81277b244489dc4a55c3eb9764436"
   }
  }
 ],
 "references": [
  {
   "type": "INTRODUCED",
   "url": "https://huggingface.co/openai/whisper-large-v3/commit/9ef08b92d5117306d28a6bcba2ca4ba407155f65"
  },
  {
   "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": "config",
    "key": "bos_token_id",
    "before": 50256,
    "after": 50257,
    "class": "tokenizer"
   },
   {
    "file": "config",
    "key": "eos_token_id",
    "before": 50256,
    "after": 50257,
    "class": "tokenizer"
   }
  ],
  "impact": {
   "memory": false,
   "serving": true,
   "tokenizer": true,
   "licence": null
  },
  "breaking": true,
  "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": {
    "before": 50256,
    "after": 50257
   },
   "bos": {
    "before": 50256,
    "after": 50257
   }
  },
  "commit_date": "2023-11-16T11:44:34.000Z",
  "detected_at": "2026-10-18T09:00:52.565Z",
  "detected_by": "backfill",
  "days_since_first_commit": 8,
  "license": "CC-BY-4.0"
 }
}