{
  "id": "microsoft-vibevoice-asr",
  "name": "VibeVoice-ASR",
  "developer": "Microsoft",
  "family": "VibeVoice-ASR",
  "variant": "VibeVoice-ASR",
  "model": {
    "parameters": "8.67402B",
    "total_parameters_billions": 8.674021857,
    "context": {
      "value": 131072,
      "display": "131,072 tokens",
      "status": "verified",
      "evidence": [
        {
          "source": "config.json",
          "detail": "decoder_config.max_position_embeddings"
        }
      ]
    },
    "modality": "Audio → text",
    "tags": [
      "transformers",
      "safetensors",
      "vibevoice",
      "ASR",
      "Transcriptoin",
      "Diarization",
      "Speech-to-Text",
      "automatic-speech-recognition",
      "en",
      "zh",
      "es",
      "pt",
      "de",
      "ja",
      "ko",
      "fr",
      "ru",
      "id",
      "sv",
      "it"
    ]
  },
  "weights": {
    "status": "verified-available",
    "repository": "https://huggingface.co/microsoft/VibeVoice-ASR",
    "access": "public",
    "exact_files": [
      "model-00001-of-00008.safetensors",
      "model-00002-of-00008.safetensors",
      "model-00003-of-00008.safetensors",
      "model-00004-of-00008.safetensors",
      "model-00005-of-00008.safetensors",
      "model-00006-of-00008.safetensors",
      "model-00007-of-00008.safetensors",
      "model-00008-of-00008.safetensors",
      "model.safetensors.index.json"
    ],
    "file_count": 9,
    "formats": [
      "Safetensors"
    ],
    "precision_availability": {
      "bf16": {
        "available": true,
        "status": "verified"
      },
      "fp16": {
        "available": false,
        "status": "verified"
      },
      "fp8": {
        "available": false,
        "status": "verified"
      },
      "int8": {
        "available": false,
        "status": "verified"
      },
      "int4": {
        "available": false,
        "status": "verified"
      },
      "gguf": {
        "available": false,
        "status": "verified"
      }
    },
    "dtype_evidence": [
      "BF16",
      "FLOAT32"
    ],
    "evidence": [
      {
        "source": "https://huggingface.co/api/models/microsoft/VibeVoice-ASR",
        "type": "Hugging Face model API siblings"
      }
    ]
  },
  "license": {
    "id": "mit",
    "name": "MIT",
    "url": null,
    "status": "verified",
    "commercial_use": {
      "status": "allowed",
      "label": "Commercial use allowed under MIT conditions",
      "basis": null
    },
    "repository_license_files": [],
    "verification": {
      "status": "metadata-only",
      "checked_at": "2026-10-02",
      "source": null
    }
  },
  "hardware": {
    "status": "estimated",
    "weight_only_gb": {
      "bf16_fp16": 17.35,
      "fp8_int8": 8.67,
      "int4": 4.34
    },
    "note": "Weight-only decimal-GB estimate from total parameter count; excludes KV cache, activations, runtime overhead, optimizer state and sharding."
  },
  "lineage": {
    "family": "VibeVoice-ASR",
    "variant": "VibeVoice-ASR",
    "base_model": {
      "status": "not-declared",
      "models": [],
      "relation": null,
      "evidence": []
    }
  },
  "training_assets": {
    "training_recipe": {
      "status": "training-or-recipe-links-present",
      "files": [],
      "links": [
        "https://github.com/microsoft/VibeVoice/blob/main/finetuning-asr/README.md"
      ],
      "evidence": []
    },
    "data_disclosure": {
      "status": "not-disclosed-in-standard-metadata-or-obvious-model-card-section",
      "datasets": [],
      "evidence": []
    },
    "evaluations": "Not classified by automated verifier",
    "intermediate_checkpoints": "Not classified by automated verifier"
  },
  "sources": [
    {
      "type": "model_repository",
      "url": "https://huggingface.co/microsoft/VibeVoice-ASR",
      "tier": "primary"
    },
    {
      "type": "model_api",
      "url": "https://huggingface.co/api/models/microsoft/VibeVoice-ASR",
      "tier": "primary"
    },
    {
      "type": "model_card",
      "url": "https://huggingface.co/microsoft/VibeVoice-ASR/blob/main/README.md",
      "tier": "primary",
      "available": true
    },
    {
      "type": "config",
      "url": "https://huggingface.co/microsoft/VibeVoice-ASR/blob/main/config.json",
      "tier": "primary",
      "available": true
    }
  ],
  "verification": {
    "level": "field-verified",
    "checked_at": "2026-10-03",
    "checked_at_iso": "2026-10-03T13:17:24+00:00",
    "method": "Hugging Face API + repository file list + model card + config.json",
    "mode": "repository-revision-unchanged",
    "full_verified_at": "2026-10-02",
    "readme_accessible": true,
    "config_accessible": true,
    "fields": {
      "license": "verified",
      "commercial_use": "classified",
      "context": "verified",
      "weight_files": "verified",
      "formats": "verified",
      "base_model": "not-declared",
      "training_recipe": "not-disclosed-in-checked-repository",
      "data_disclosure": "not-disclosed-in-standard-metadata-or-obvious-model-card-section",
      "runtime_support": "source-derived-not-runtime-tested"
    },
    "history": [
      {
        "date": "2026-10-03",
        "event": "Repository revision check",
        "detail": "Official Hugging Face repository SHA unchanged; prior field evidence retained."
      },
      {
        "date": "2026-10-02",
        "event": "Repository revision check",
        "detail": "Official Hugging Face repository SHA unchanged; prior field evidence retained."
      },
      {
        "date": "2026-10-02",
        "event": "Field-by-field verification",
        "detail": "Checked Hugging Face API metadata, exact repository file list, model card and config when accessible."
      },
      {
        "date": "2026-10-02",
        "event": "Registry record created",
        "detail": "Previous verification level: discovered-pending."
      }
    ]
  },
  "discovery": {
    "source": "Hugging Face public model index",
    "repo_id": "microsoft/VibeVoice-ASR",
    "rank": 365,
    "downloads": 725155,
    "likes": 1302,
    "last_modified": "2026-01-27T13:12:22+00:00",
    "created_at": "2026-01-21T15:04:18+00:00",
    "library_name": "transformers",
    "pipeline_tag": "automatic-speech-recognition",
    "discovered_at": "2026-10-03T13:17:21+00:00",
    "pinned": false
  },
  "runtime_support": {
    "declared_library": "Transformers",
    "pipeline_tag": "automatic-speech-recognition",
    "declared": [
      "Transformers"
    ],
    "mentioned_in_model_card": [
      "vLLM"
    ],
    "artifact_signals": [],
    "tested_by_openmodelweights": false
  },
  "hub": {
    "last_modified": "2026-01-27T13:12:22.000Z",
    "created_at": "2026-01-21T15:04:18.000Z",
    "downloads": 725155,
    "likes": 1302,
    "sha": "d0c9efdb8d614685062c04425d91e01b6f37d944",
    "library_name": "transformers",
    "pipeline_tag": "automatic-speech-recognition",
    "tags": [
      "transformers",
      "safetensors",
      "vibevoice",
      "ASR",
      "Transcriptoin",
      "Diarization",
      "Speech-to-Text",
      "automatic-speech-recognition",
      "en",
      "zh",
      "es",
      "pt",
      "de",
      "ja",
      "ko",
      "fr",
      "ru",
      "id",
      "sv",
      "it",
      "he",
      "nl",
      "pl",
      "no",
      "tr",
      "th",
      "ar",
      "hu",
      "ca",
      "cs",
      "da",
      "fa",
      "af",
      "hi",
      "fi",
      "et",
      "aa",
      "el",
      "ro",
      "vi",
      "bg",
      "is",
      "sl",
      "sk",
      "lt",
      "sw",
      "uk",
      "kl",
      "lv",
      "hr",
      "ne",
      "sr",
      "tl",
      "yi",
      "ms",
      "ur",
      "mn",
      "hy",
      "jv",
      "arxiv:2601.18184",
      "license:mit",
      "endpoints_compatible",
      "region:us"
    ]
  }
}
