{
  "id": "human-solo",
  "title": "Single speaker: synchronizing recording equipment",
  "kind": "human",
  "meetingId": "IN1014",
  "durationSec": 62.01,
  "sourceStartSec": 1050.22,
  "sourceEndSec": 1112.23,
  "sourceUrl": "https://groups.inf.ed.ac.uk/ami/AMICorpusMirror/amicorpus/HeadsetAudio/IN1014.Mix-Headset.wav",
  "sourcePage": "https://groups.inf.ed.ac.uk/ami/corpus/",
  "sourceDescriptionPage": "https://groups.inf.ed.ac.uk/ami/corpus/nonscenariomeetings.shtml",
  "license": "CC BY 4.0",
  "licenseUrl": "https://creativecommons.org/licenses/by/4.0/",
  "licenseEvidence": "https://groups.inf.ed.ac.uk/ami/corpus/license.shtml",
  "creator": "The AMI Consortium",
  "copyright": "Copyright (C) 2006, The AMI Consortium",
  "attribution": "AMI Meeting Corpus, The AMI Consortium / University of Edinburgh; CC BY 4.0. Contiguous excerpt, original headset mix. No endorsement implied.",
  "modifications": "Single contiguous excerpt from the original 16 kHz mono PCM headset mix. WAV container rebuilt; no stitching, synthetic speech, voice isolation, denoising, silence removal, speed changes or word edits.",
  "audioUrl": "/samples/whisperx/human-solo/recording.wav",
  "referenceUrl": "/samples/whisperx/human-solo/reference.words.json",
  "sourceSpeakerIds": [
    "B"
  ],
  "sourceMeetingHasMoreParticipants": true,
  "audioSha256": "28acdab3999f28a318609b78b89e46959722a02b55ed1e860f3522c405d95890",
  "annotationArchiveSha256": "b56e5babb2496b8795deeeda7e71178d7fbc9963f94276cf2a3f4b56ebbc9f9d",
  "downloadedAt": "2026-10-15T07:42:02.486400+00:00",
  "contentRange": "bytes 33607084-35591403/118171864",
  "sourceFullAudioHash": null,
  "reviewStatus": "Completed: reference-based comparison; no listening audit",
  "processedAt": "2026-10-15T07:43:23.641Z",
  "predictionId": "r2yyfqf5nnrne0d17t1t15rdyc",
  "engine": {
    "name": "WhisperX",
    "provider": "replicate",
    "model": "large-v3",
    "version": "655845d6190ef70573c669245f245892cd039df4b880a1e3a65852c09252f5cc"
  },
  "configuration": {
    "language": "en",
    "task": "transcribe",
    "align_output": true,
    "diarization": true,
    "batch_size": 32,
    "min_speakers": "unset (automatic)",
    "max_speakers": "unset (automatic)",
    "hfModel": "pyannote/speaker-diarization-community-1",
    "cancelAfter": "300s"
  },
  "executionPath": "direct provider call through unchanged production submitPrediction/buildProviderInput/normalizer; test-only Cancel-After header; no app job, credit or DB changes",
  "metrics": {
    "predict_time": 8.270614911,
    "total_time": 8.398045134
  },
  "predictionCreatedAt": "2026-10-15T07:43:13.837Z",
  "predictionStartedAt": "2026-10-15T07:43:13.964430223Z",
  "predictionCompletedAt": "2026-10-15T07:43:22.235045134Z",
  "budget": {
    "publishedHardware": "A100 80GB",
    "publishedRateUSDPerSecond": 0.0014,
    "estimatedUSD": 0.011578860875399999,
    "actualBilledUSD": null
  },
  "outputFiles": {
    "provider": "/samples/whisperx/human-solo/provider.json",
    "json": "/samples/whisperx/human-solo/transcript.json",
    "txt": "/samples/whisperx/human-solo/transcript.txt",
    "srt": "/samples/whisperx/human-solo/transcript.srt",
    "vtt": "/samples/whisperx/human-solo/transcript.vtt"
  },
  "review": {
    "summary": "The model detected one speaker, matching the excerpt reference. Some wording still needs correction.",
    "observations": [
      "The opening reference “And the DIVA” is transcribed as “In the diva”; the wording and technical-name capitalization differ.",
      "The final segment adds “a product”, which is absent from the AMI word reference. This has not been adjudicated by listening.",
      "DirectShow and the phrase “two cards, one for audio and one for video” are present in the model output.",
      "One model speaker label is used throughout, matching the one annotated source speaker B."
    ],
    "method": "Reference-based comparison against the AMI manual word annotations v1.6.2, including speaker IDs and original source times. Not a listening audit.",
    "reviewedAt": "2026-10-15T07:45:32.761043+00:00",
    "notManuallyListened": true,
    "measured": {
      "durationSec": 62.01,
      "modelSegments": 5,
      "modelWordEntries": 100,
      "wordEntriesWithTiming": 100,
      "missingWordTiming": 0,
      "modelSpeakerCount": 1,
      "referenceSpeakerCount": 1,
      "referenceSpeakerIds": [
        "B"
      ],
      "referenceLexicalEntries": 110,
      "timingStatusCounts": {
        "unknown": 100
      }
    },
    "limitations": [
      "These are two short, selected excerpts from real non-scenario multi-person meetings, using the official mixed headset recording. They are not privately recorded one-person/two-person sessions.",
      "The reference contains false starts, fillers and overlapping speech. Word-count differences are not an error rate, and no WER/DER or general accuracy claim is made.",
      "Timestamps are model output, not independently listened-to alignment measurements. All normalized timing statuses remain unknown, even where numeric times exist.",
      "No output text, speaker label or timestamp was manually corrected. Original provider output and normalized original exports are preserved.",
      "This direct-provider test uses the unchanged production input adapter, pinned model, normalizer and exporters. It does not test application login, credits, job database, webhook handling or browser processing."
    ]
  },
  "reviewUrl": "/samples/whisperx/human-solo/review.json",
  "notesUrl": "/samples/whisperx/human-solo/review.md",
  "detectedSpeakerCount": 1,
  "wordCount": 100,
  "segmentCount": 5,
  "sourceLabel": "Human speech · AMI non-scenario meeting · CC BY 4.0"
}