{
  "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"
  ],
  "status": "released",
  "planned": null,
  "flagship": false,
  "aiAgent": false,
  "customCollection": false,
  "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": {
      "male": 35,
      "female": 101
    },
    "quality": {
      "snrDb": 25.1,
      "bandwidthHz": 7900,
      "label": "some background"
    },
    "clips": [
      {
        "id": "tamil-speech-recognition-utterances--u1",
        "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--u1.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 32208,
          "sha256": "ffdd6e49e9dc346de13d34c92c0821a3b2bc5dbc1062e3c5ab94c4409d0ecfa5"
        }
      },
      {
        "id": "tamil-speech-recognition-utterances--u2",
        "sourceId": "utt-8a09ca2994",
        "text": "ஒழுங்கான preserve பண்ணி கொண்டு போகல அப்படி நான் நினைக்கிறேன்.",
        "durationS": 3.24,
        "gender": "male",
        "speakerId": "ta-gc-99-s0122",
        "snrDb": 53.7,
        "audio": {
          "url": "/lokah-samples/tamil-speech-recognition-utterances--u2.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 28792,
          "sha256": "046267976e50b417e29def3d916c89c734eb8b7717d08cfbb19819eb0ebc4381"
        }
      },
      {
        "id": "tamil-speech-recognition-utterances--u3",
        "sourceId": "utt-44b045370a",
        "text": "five OK. color க்கு madam?",
        "durationS": 4.41,
        "gender": "male",
        "speakerId": "ta-cc-100-s0377",
        "snrDb": 52.8,
        "audio": {
          "url": "/lokah-samples/tamil-speech-recognition-utterances--u3.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 32870,
          "sha256": "fafb14d4acb94f9cfd94ad88a52dc7a4404b68869628e7fa8a0294a36006007d"
        }
      },
      {
        "id": "tamil-speech-recognition-utterances--u4",
        "sourceId": "utt-4951f4103f",
        "text": "but நீங்க வந்துட்டு அவங்க அப்பா அம்மா இருக்காங்கனு ஒரு தெரிஞ்சுக்கலாம்",
        "durationS": 4.23,
        "gender": "female",
        "speakerId": "ta-cc-dual-s0019",
        "snrDb": 51.2,
        "audio": {
          "url": "/lokah-samples/tamil-speech-recognition-utterances--u4.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 39733,
          "sha256": "0ba5a831ff6ffdc010e8a62aa49f4aedb4239161c86473237690e8bb76c471ef"
        }
      },
      {
        "id": "tamil-speech-recognition-utterances--u5",
        "sourceId": "utt-22ea250aa3",
        "text": "ஆ, சொல்லுங்க, அங்கேருந்து தான் call பண்றீங்களா?",
        "durationS": 3.29,
        "gender": "female",
        "speakerId": "ta-gc-99-s0042",
        "snrDb": 48.2,
        "audio": {
          "url": "/lokah-samples/tamil-speech-recognition-utterances--u5.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 30036,
          "sha256": "b753f997174af931898a4b8da942ec03557af850854805991bfa083d3daafdc4"
        }
      },
      {
        "id": "tamil-speech-recognition-utterances--u6",
        "sourceId": "utt-5a0e33bdbb",
        "text": "sir அந்த product அது நீங்க use பண்ணிங்களா sir?",
        "durationS": 3.64,
        "gender": "male",
        "speakerId": "ta-cc-100-s0467",
        "snrDb": 46.1,
        "audio": {
          "url": "/lokah-samples/tamil-speech-recognition-utterances--u6.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 28620,
          "sha256": "f449c28cb0b0acd46025933a5fe154710eec69c1c1a43fcb8606e189d5550444"
        }
      }
    ]
  },
  "url": "https://kenpathlabs.com/lokah/datasets/tamil-speech-recognition-utterances"
}