{
  "id": "LK-SP-TAM-004",
  "slug": "tamil-speech-recognition-utterances",
  "title": "Tamil speech recognition utterances",
  "modality": "speech",
  "speechType": "conversational",
  "kind": "asr",
  "unit": "utterances",
  "collection": "mixed",
  "language": {
    "name": "Tamil",
    "native": "தமிழ்",
    "iso": "tam",
    "bcp47": "ta-IN",
    "script": "Tamil"
  },
  "languages": [
    {
      "name": "Tamil",
      "native": "தமிழ்",
      "iso": "tam",
      "bcp47": "ta-IN",
      "script": "Tamil"
    }
  ],
  "region": "India",
  "domain": "consumer surveys, customer service calls, general conversation",
  "scripted": null,
  "parties": null,
  "hours": 201.1,
  "transcribed": true,
  "channels": "mono",
  "source": "Recorded for the dataset",
  "review": "Every recording has a complete, segment-level transcript",
  "personalData": "Redacted",
  "licence": "Custom",
  "sheetRows": [
    3,
    4,
    6
  ],
  "sample": null,
  "gaps": [],
  "bundleId": "asr-ta",
  "relatedSlugs": [
    "tamil-call-centre-customer-service",
    "tamil-general-conversation",
    "tamil-call-centre-banking-and-retail"
  ],
  "measured": {
    "id": "asr-ta",
    "files": 157231,
    "conversations": 1308,
    "utterances": 157231,
    "turns": null,
    "speakers": 1236,
    "speakerGender": {
      "male": 316,
      "female": 784
    },
    "channels": null,
    "transcripts": 0,
    "segments": 157231,
    "words": 1748023,
    "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": "2026-09-29T00:15",
    "profile": null,
    "provisional": false
  },
  "utterances": {
    "measured": 151,
    "distinctSpeakers": 118,
    "genders": {
      "female": 101,
      "male": 35
    },
    "quality": {
      "snrDb": 25.6,
      "bandwidthHz": 7900,
      "label": "some background"
    },
    "clips": [
      {
        "id": "tamil-speech-recognition-utterances--u1",
        "sourceId": "utt-22ea250aa3",
        "text": "ஆ, சொல்லுங்க, அங்கேருந்து தான் call பண்றீங்களா?",
        "durationS": 3.29,
        "gender": "female",
        "speakerId": "ta-gc-99-s0042",
        "snrDb": 69.5,
        "audio": {
          "url": "/lokah-samples/tamil-speech-recognition-utterances--u1.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 30036,
          "sha256": "b753f997174af931898a4b8da942ec03557af850854805991bfa083d3daafdc4"
        }
      },
      {
        "id": "tamil-speech-recognition-utterances--u2",
        "sourceId": "utt-b6e45e3758",
        "text": "OK hair வந்து சிக்கு இல்லாம easy ஆ சீவரதுக்கு அப்படி பாக்கும்போது",
        "durationS": 4.78,
        "gender": "male",
        "speakerId": "ta-cc-100-s0426",
        "snrDb": 62.9,
        "audio": {
          "url": "/lokah-samples/tamil-speech-recognition-utterances--u2.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 35044,
          "sha256": "6285af29f3787ad43b9b076feebed5d92b8c64e0f88c11fceccabffe713183b5"
        }
      },
      {
        "id": "tamil-speech-recognition-utterances--u3",
        "sourceId": "utt-b84d8be713",
        "text": "OK mam. வேற எதாச்சும் facilities இருக்குதா?",
        "durationS": 3.91,
        "gender": "female",
        "speakerId": "ta-gc-99-s0241",
        "snrDb": 61.1,
        "audio": {
          "url": "/lokah-samples/tamil-speech-recognition-utterances--u3.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 30768,
          "sha256": "95698fe71b119efb641d1f90872ecc5d386a3ef00761f4a37df3038d74927291"
        }
      },
      {
        "id": "tamil-speech-recognition-utterances--u4",
        "sourceId": "utt-a2a20e3e31",
        "text": "OK OK குடுப்பாங்க நா சொல்ற நா சொல்ற நீங்க கேட்டுகோங்கோ அவங்க குடுப்பாங்க.",
        "durationS": 3.71,
        "gender": "male",
        "speakerId": "ta-gc-99-s0058",
        "snrDb": 57.8,
        "audio": {
          "url": "/lokah-samples/tamil-speech-recognition-utterances--u4.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 32208,
          "sha256": "ffdd6e49e9dc346de13d34c92c0821a3b2bc5dbc1062e3c5ab94c4409d0ecfa5"
        }
      },
      {
        "id": "tamil-speech-recognition-utterances--u5",
        "sourceId": "utt-a29ee8fe46",
        "text": "that means, for example, some people stay OK, we give you ten to peace discount but that is like ten days rupees discount on the next product device. So that is the corruption",
        "durationS": 11.51,
        "gender": "male",
        "speakerId": "ta-cc-100-s0542",
        "snrDb": 57,
        "audio": {
          "url": "/lokah-samples/tamil-speech-recognition-utterances--u5.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 94846,
          "sha256": "46e64becb4f61a36d631eea816f594eedde497ef9c825f76e7eb9e13d9724f46"
        }
      },
      {
        "id": "tamil-speech-recognition-utterances--u6",
        "sourceId": "utt-a321e84bf6",
        "text": "ஆ, அந்த மாதிரி model ன்னா sudden mam. actual லா sudden ஆ வந்துட்டு நீங்க வந்து இந்த long days க்கு போகும்போது இந்த luggage எல்லாம் கொண்டு போறதுக்கு நிறைய lossage இருக்குமா? இல்லை உங்களுக்கு? இல்லை இப்படி.",
        "durationS": 10.67,
        "gender": "male",
        "speakerId": "ta-gc-99-s0048",
        "snrDb": 55.9,
        "audio": {
          "url": "/lokah-samples/tamil-speech-recognition-utterances--u6.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 82473,
          "sha256": "914f2f0923d5efa1cb04090deeaf43fab50afe9a76e7d76d476affec88b50df9"
        }
      }
    ]
  },
  "url": "https://kenpathlabs.com/lokah/datasets/tamil-speech-recognition-utterances"
}