{ "id": "LK-SP-HIN-002", "slug": "hindi-general-conversation", "title": "Hindi general conversation", "modality": "speech", "speechType": "conversational", "kind": "conversations", "unit": "conversations", "collection": "general-conversation", "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": "Open topic", "scripted": false, "parties": null, "hours": 81.1, "transcribed": true, "channels": "mono", "source": "Recorded for the dataset", "review": "Every recording has a complete, segment-level transcript", "personalData": "Redacted", "licence": "Custom", "sheetRows": [ 14 ], "sample": { "key": "conversations-hi-gc-78", "slug": "hindi-general-conversation", "dual": false, "audio": { "sampleRateHz": 16000, "bitDepth": 16, "codec": "pcm_s16le", "container": "flac", "filesPerConversation": 1, "measured": true }, "metrics": { "durationS": 1475.4, "conversations": 6, "turns": 359, "words": 3631, "talkTimeS": { "1": 599.7, "2": 650.3 }, "speechShare": 0.835, "overlapShare": 0.012, "silenceShare": 0.165, "wordsPerMinute": 176.8, "turnDurationS": { "median": 1.77, "p90": 9.69 }, "floorTransfer": { "count": 151, "medianS": 0.666, "p10S": 0.099, "p90S": 2.282, "overlappedShare": 0.013, "histogram": { "edgesS": [ -2, -1, -0.5, -0.2, 0, 0.2, 0.5, 1, 2, 4 ], "counts": [ 0, 1, 0, 1, 0, 22, 43, 26, 36, 14, 8 ] } }, "backchannels": { "count": 110, "perMinute": 4.47 }, "codeMix": { "latinTokens": 515, "nativeTokens": 3114, "latinShare": 0.142 }, "events": { "[filler]": 63, "[unintelligible]": 40, "[silence]": 48, "[suppressed]": 1, "[non_primary_speaker]": 9 }, "overlapEvents": 1 }, "quality": { "snrDb": { "median": 53, "min": 36.2, "max": 107.2 }, "noiseFloorDb": -75.7, "speechLevelDb": -15.3, "bandwidthHz": 8000, "clippingShare": 0.00015, "label": "some background", "dnsmos": { "sig": 3.29, "bak": 3.75, "ovrl": 2.88 }, "method": "Frame RMS at 20 ms on the channels mixed to mono. Noise floor is the 10th percentile, speech level the 90th; SNR is their difference. Bandwidth is the highest frequency at which speech still rises 6 dB above the recording's own noise spectrum." }, "speakers": [ { "role": "Speaker 1", "id": "hi-gc-78-s0025", "gender": "male", "ageBand": null }, { "role": "Speaker 2", "id": "hi-gc-78-s0026", "gender": "male", "ageBand": null } ], "speakerSummary": { "distinctIds": 11, "genders": { "male": 4, "female": 7 }, "ageBands": null }, "conversations": [ { "index": 1, "sourceId": "conv-db0cd9ba63", "title": "Open conversation", "durationS": 248.9, "turns": 81, "words": 756, "speakers": [ { "role": "Speaker 1", "id": "hi-gc-78-s0025", "gender": "male", "ageBand": null }, { "role": "Speaker 2", "id": "hi-gc-78-s0026", "gender": "male", "ageBand": null } ], "flagged": 0, "silenceShare": 0.112, "overlapShare": 0.012, "latinShare": 0.116, "wordsPerMinute": 205.3, "specimen": { "id": "hindi-general-conversation--3", "windowS": 44.647, "offsetS": 163.622, "segments": 16, "bytes": 288462, "sha256": "ecef7d15224b80abb042bdd64f947e68f3d5bab024585e915104d8040c374c3e", "dnsmos": { "sig": 3.55, "bak": 3.91, "ovrl": 3.2 } }, "quality": { "noiseFloorDb": -76.7, "speechLevelDb": -23.1, "snrDb": 53.7, "clippingShare": 0, "bandwidthHz": 7900 }, "qualityLabel": "clean", "excerptSnrDb": 51.8 }, { "index": 2, "sourceId": "conv-6319dfae0b", "title": "Open conversation", "durationS": 248.4, "turns": 39, "words": 427, "speakers": [ { "role": "Speaker 1", "id": "hi-gc-78-s0047", "gender": "male", "ageBand": null }, { "role": "Speaker 2", "id": "hi-gc-78-s0046", "gender": "female", "ageBand": null } ], "flagged": 0, "silenceShare": 0.163, "overlapShare": 0.028, "latinShare": 0.171, "wordsPerMinute": 123.3, "specimen": null, "quality": { "noiseFloorDb": -120, "speechLevelDb": -12.8, "snrDb": 107.2, "clippingShare": 0, "bandwidthHz": 8000 }, "qualityLabel": "clean", "excerptSnrDb": 106.9 }, { "index": 3, "sourceId": "conv-5418a189bc", "title": "Open conversation", "durationS": 241.3, "turns": 49, "words": 670, "speakers": [ { "role": "Speaker 1", "id": "hi-gc-78-s0079", "gender": "female", "ageBand": null }, { "role": "Speaker 2", "id": "hi-gc-78-s0066", "gender": "female", "ageBand": null } ], "flagged": 0, "silenceShare": 0.051, "overlapShare": 0.012, "latinShare": 0.158, "wordsPerMinute": 175.5, "specimen": null, "quality": { "noiseFloorDb": -43.7, "speechLevelDb": -7.5, "snrDb": 36.2, "clippingShare": 0.00015, "bandwidthHz": 8000 }, "qualityLabel": "some background", "excerptSnrDb": 39.2 }, { "index": 4, "sourceId": "conv-02d8606c9b", "title": "Open conversation", "durationS": 249.3, "turns": 57, "words": 570, "speakers": [ { "role": "Speaker 1", "id": "hi-gc-78-s0027", "gender": "female", "ageBand": null }, { "role": "Speaker 2", "id": "hi-gc-78-s0028", "gender": "female", "ageBand": null } ], "flagged": 0, "silenceShare": 0.224, "overlapShare": 0.005, "latinShare": 0.063, "wordsPerMinute": 176.7, "specimen": { "id": "hindi-general-conversation--4", "windowS": 40.465, "offsetS": 3.094, "segments": 10, "bytes": 254951, "sha256": "2f5787e1eb0359d3918a3d53957da788f85bd923bfca3e41b8ae848b7603e5a9", "dnsmos": { "sig": 3.32, "bak": 3.64, "ovrl": 2.84 } }, "quality": { "noiseFloorDb": -68.6, "speechLevelDb": -16.8, "snrDb": 51.8, "clippingShare": 0, "bandwidthHz": 8000 }, "qualityLabel": "clean", "excerptSnrDb": 52.3 }, { "index": 5, "sourceId": "conv-eefee135c3", "title": "Open conversation", "durationS": 248.1, "turns": 79, "words": 701, "speakers": [ { "role": "Speaker 1", "id": "hi-gc-78-s0017", "gender": "male", "ageBand": null }, { "role": "Speaker 2", "id": "hi-gc-78-s0026", "gender": "male", "ageBand": null } ], "flagged": 0, "silenceShare": 0.165, "overlapShare": 0.005, "latinShare": 0.146, "wordsPerMinute": 203, "specimen": { "id": "hindi-general-conversation--1", "windowS": 44.161, "offsetS": 20.284, "segments": 23, "bytes": 283300, "sha256": "0909ab3c1e2cf776a2610409d611e09665f7ab34304210efbf3aa6b05b5b8542", "dnsmos": { "sig": 3.45, "bak": 3.77, "ovrl": 3.02 } }, "quality": { "noiseFloorDb": -80.7, "speechLevelDb": -28.5, "snrDb": 52.2, "clippingShare": 0, "bandwidthHz": 7800 }, "qualityLabel": "clean", "excerptSnrDb": 47.2 }, { "index": 6, "sourceId": "conv-06b26554b2", "title": "Open conversation", "durationS": 239.4, "turns": 54, "words": 507, "speakers": [ { "role": "Speaker 1", "id": "hi-gc-78-s0021", "gender": "female", "ageBand": null }, { "role": "Speaker 2", "id": "hi-gc-78-s0022", "gender": "female", "ageBand": null } ], "flagged": 0, "silenceShare": 0.275, "overlapShare": 0.01, "latinShare": 0.217, "wordsPerMinute": 175.2, "specimen": { "id": "hindi-general-conversation--2", "windowS": 41.443, "offsetS": 1.391, "segments": 18, "bytes": 257786, "sha256": "9691ec8c9adff53bcd5634b53b32323374d63d837e599ec2f36a88b0451442ab", "dnsmos": { "sig": 2.83, "bak": 3.68, "ovrl": 2.48 } }, "quality": { "noiseFloorDb": -74.7, "speechLevelDb": -13.8, "snrDb": 60.9, "clippingShare": 0, "bandwidthHz": 8000 }, "qualityLabel": "clean", "excerptSnrDb": 59.1 } ], "specimens": [ "hindi-general-conversation--1", "hindi-general-conversation--2", "hindi-general-conversation--3", "hindi-general-conversation--4" ], "transcriptFormat": "json", "piiFlaggedSegments": 0, "withheld": false }, "utterances": null, "gaps": [], "bundleId": "conversations-hi-gc-78", "relatedSlugs": [ "hindi-speech-recognition-utterances", "hindi-speaker-diarization" ], "measured": { "id": "hi-gc-78", "files": 259, "conversations": 259, "channels": "259 mono conversation", "bandwidth": "wideband (8 kHz)", "bandwidthCounts": { "wideband (8 kHz)": 259 }, "telephoneBandFiles": 0, "utterances": null, "turns": null, "speakers": 177, "speakerGender": { "female": 85, "male": 82 }, "transcripts": 259, "segments": 53495, "words": 718981, "snrMedianDb": 36.8, "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": "2026-09-28T23:32", "profile": { "conversations": 259, "medianConversationMin": 19.84, "talkShareByRank": [ 0.681, 0.319 ], "silenceShare": 0.268, "overlapShare": 0.013, "turnsPerMin": 8.63, "wordsPerMin": 147.6, "codeMixShare": 0.139, "twoChannel": null }, "provisional": false }, "url": "https://kenpathlabs.com/lokah/datasets/hindi-general-conversation" }