{
  "id": "LK-SP-HIN-003",
  "slug": "hindi-speech-recognition-utterances",
  "title": "Hindi speech recognition utterances",
  "modality": "speech",
  "speechType": "conversational",
  "kind": "asr",
  "unit": "utterances",
  "collection": "mixed",
  "language": {
    "name": "Hindi",
    "native": "हिन्दी",
    "iso": "hin",
    "bcp47": "hi-IN",
    "script": "Devanagari"
  },
  "languages": [
    {
      "name": "Hindi",
      "native": "हिन्दी",
      "iso": "hin",
      "bcp47": "hi-IN",
      "script": "Devanagari"
    }
  ],
  "region": "India",
  "domain": "insurance calls, general conversation",
  "scripted": null,
  "parties": null,
  "hours": 350.3,
  "transcribed": true,
  "channels": "mono",
  "source": "Recorded for the dataset",
  "review": "Every recording has a complete, segment-level transcript",
  "personalData": "Redacted",
  "licence": "Custom",
  "sheetRows": [
    5,
    14
  ],
  "sample": null,
  "gaps": [],
  "bundleId": "asr-hi",
  "relatedSlugs": [
    "hindi-call-centre-insurance",
    "hindi-general-conversation"
  ],
  "status": "released",
  "planned": null,
  "flagship": false,
  "aiAgent": false,
  "customCollection": false,
  "measured": {
    "id": "asr-hi",
    "files": 218428,
    "conversations": 2104,
    "utterances": 218428,
    "turns": null,
    "speakers": 667,
    "speakerGender": {
      "female": 325,
      "male": 330
    },
    "channels": null,
    "transcripts": 0,
    "segments": 218428,
    "words": 3377105,
    "bandwidth": null,
    "bandwidthCounts": null,
    "telephoneBandFiles": null,
    "snrMedianDb": null,
    "container": "flac",
    "sampleRateHz": 16000,
    "bitDepth": 16,
    "pii": "Numbers of 4 or more digits, digit strings spoken as words, and email addresses are masked as [pii] in text and replaced by a tone in audio. First names are not masked.",
    "release": "v1.0",
    "updatedAt": "2026-09-29T00:21",
    "profile": null,
    "provisional": false
  },
  "utterances": {
    "measured": 142,
    "distinctSpeakers": 111,
    "genders": {
      "male": 81,
      "female": 59
    },
    "quality": {
      "snrDb": 37.1,
      "bandwidthHz": 8000,
      "label": "some background"
    },
    "clips": [
      {
        "id": "hindi-speech-recognition-utterances--u1",
        "sourceId": "utt-06a680d968",
        "text": "जी जी ma'am ये एक साल के लिए होगा आपका insurance और ma'am",
        "durationS": 8.94,
        "gender": "male",
        "speakerId": "hi-cc-insurance-s0325",
        "snrDb": 64.2,
        "audio": {
          "url": "/lokah-samples/hindi-speech-recognition-utterances--u1.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 72764,
          "sha256": "d4104e6420e21eeea7dd55ec0e7d57363d577657db27f48a58c12c7b87ad78f3"
        }
      },
      {
        "id": "hindi-speech-recognition-utterances--u2",
        "sourceId": "utt-3183474dab",
        "text": "ma'am उनका नाम अजित होंगा. नंबर मे आपको नहीं दे सकता ma'am.",
        "durationS": 3.3,
        "gender": "male",
        "speakerId": "hi-cc-insurance-s0330",
        "snrDb": 63.8,
        "audio": {
          "url": "/lokah-samples/hindi-speech-recognition-utterances--u2.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 32144,
          "sha256": "89fe3e4cbe6f7819ce4a84ff20c8b7eccd9730666a3468945f756d39953f7754"
        }
      },
      {
        "id": "hindi-speech-recognition-utterances--u3",
        "sourceId": "utt-ee91549785",
        "text": "जी जी जी जी तो अपने बचने केलिए अपने कार को मोड़ा बो जेक पोल पे टकरा गए यही कहना चाहतेहो आप",
        "durationS": 11.86,
        "gender": "male",
        "speakerId": "hi-cc-insurance-s0312",
        "snrDb": 62.4,
        "audio": {
          "url": "/lokah-samples/hindi-speech-recognition-utterances--u3.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 103851,
          "sha256": "506bc999ebd3b3d695447a428f25ab8177a65ba6fadd1e04189010df2a2f39a1"
        }
      },
      {
        "id": "hindi-speech-recognition-utterances--u4",
        "sourceId": "utt-ae8e6494e1",
        "text": "जी जी दरअसल उनकी क्या उमर हे?",
        "durationS": 4.13,
        "gender": "male",
        "speakerId": "hi-cc-insurance-s0310",
        "snrDb": 61.2,
        "audio": {
          "url": "/lokah-samples/hindi-speech-recognition-utterances--u4.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 37501,
          "sha256": "345051f3ab5ff2189665ab3f3b5b76c2011031851fd07ebf1b8b28155f092c22"
        }
      },
      {
        "id": "hindi-speech-recognition-utterances--u5",
        "sourceId": "utt-ffc7cd4122",
        "text": "नयी सड़क से बात कर रही हैं आप तो ये जो आपके पिता के साथ दिक्कत है कितने ये साल से है",
        "durationS": 6.06,
        "gender": "male",
        "speakerId": "hi-cc-insurance-s0328",
        "snrDb": 60.5,
        "audio": {
          "url": "/lokah-samples/hindi-speech-recognition-utterances--u5.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 56091,
          "sha256": "696b94ecfa344ac769186f4b4edfb0afcddfaf55ba082772b0b0acfd22efe4ea"
        }
      },
      {
        "id": "hindi-speech-recognition-utterances--u6",
        "sourceId": "utt-ebe2b5b5f2",
        "text": "जी तो मैं जानना चाहता हूं कि दादी की death कितने दिन पहले हुई थी?",
        "durationS": 5.36,
        "gender": "male",
        "speakerId": "hi-cc-insurance-s0319",
        "snrDb": 60,
        "audio": {
          "url": "/lokah-samples/hindi-speech-recognition-utterances--u6.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 48687,
          "sha256": "8b4faf230a8d5251bfcdea58e7e186a74ffcf31f10a27fc4673e04e3f061bc9f"
        }
      }
    ]
  },
  "url": "https://kenpathlabs.com/lokah/datasets/hindi-speech-recognition-utterances"
}