collectiveai-team/speaker-diarization-3 🖼️🔢 → ❓

▶️ 4.9K runs 📅 Oct 2023 ⚙️ Cog 0.8.3 🔗 GitHub ⚖️ License
audio-embedding speaker-diarization

About

Segments an audio recording based on who is speaking

Example Output

Output

{"segments":[{"stop":"0:00:06.629881","start":"0:00:00.008489","speaker":"A"},{"stop":"0:00:08.276740","start":"0:00:07.122241","speaker":"A"},{"stop":"0:00:09.787776","start":"0:00:08.616299","speaker":"A"},{"stop":"0:00:13.658744","start":"0:00:09.906621","speaker":"A"},{"stop":"0:00:18.582343","start":"0:00:13.675722","speaker":"A"},{"stop":"0:00:26.052632","start":"0:00:18.989813","speaker":"A"},{"stop":"0:00:22.555178","start":"0:00:22.300509","speaker":"B"},{"stop":"0:00:32.555178","start":"0:00:26.324278","speaker":"A"},{"stop":"0:00:32.691002","start":"0:00:32.589134","speaker":"A"},{"stop":"0:00:44.100170","start":"0:00:32.724958","speaker":"A"},{"stop":"0:00:47.292020","start":"0:00:44.371817","speaker":"A"},{"stop":"0:00:59.261460","start":"0:00:47.648557","speaker":"A"},{"stop":"0:00:56.884550","start":"0:00:56.561969","speaker":"B"},{"stop":"0:01:08.497453","start":"0:01:00.059423","speaker":"A"},{"stop":"0:01:13.539898","start":"0:01:08.887946","speaker":"A"},{"stop":"0:01:49.023769","start":"0:01:13.998302","speaker":"A"},{"stop":"0:02:12.640068","start":"0:01:49.346350","speaker":"A"},{"stop":"0:02:45.679117","start":"0:02:12.911715","speaker":"A"},{"stop":"0:02:13.302207","start":"0:02:13.064516","speaker":"B"},{"stop":"0:03:12.351443","start":"0:02:46.273345","speaker":"A"},{"stop":"0:02:55.424448","start":"0:02:54.949066","speaker":"B"},{"stop":"0:03:02.911715","start":"0:03:02.724958","speaker":"B"},{"stop":"0:03:34.881154","start":"0:03:12.962649","speaker":"A"}],"speakers":{"count":2,"labels":["A","B"],"embeddings":{"A":[-0.2980277958241376,-0.19159927533625007,-0.2675081236989467,-0.25381432860702663,0.09958059384257763,-0.09743198539529528,0.4132504979898403,0.2032775030314148,0.01562528210607442,-0.6177756972127146,0.07577934418502566,0.077455000068944,-0.42971207220833024,0.143487013489395,0.04374769898494343,-0.1741128261987265,0.052689338707691664,-0.10136796780801438,-0.02375249339678845,0.26002338644746065,-0.3924751459778129,-0.41776453597205027,0.42611784710512535,0.03243526141461614,0.3725283621967613,0.12168989166036828,-0.5446009047619709,-0.06255066316187768,0.16032569468408436,0.24098822314824378,-0.19773885567805596,0.15155758430528177,0.08128198661974498,-0.022670983977906116,0.48185896563839603,-0.29806817690660425,-0.05942703619018778,-0.07483277019935769,0.38329678773880005,-0.08116064692375721,-0.16691496760233657,-0.42538210130357124,0.411977027530794,0.8507556992691833,0.23823742723310148,0.4496179528824695,0.10730816622252588,-0.22765118604550114,-0.2253746965585591,0.22255700260594294,-0.011031272639701892,-0.33252304869812804,0.0882140866650099,-0.10681848276358147,-0.29219809426115706,0.00936510863822776,-0.22848142219054235,0.11640579674949313,-0.13048594787281442,-0.18411347891699958,0.3619395898921149,-0.6014321190970284,0.11484903825277631,0.4214380840202431,0.028998981858906033,-0.09855928494558706,-0.024741925069360765,-0.14838007895590424,0.07313753858015135,0.0616028198803013,-0.22130442420383553,-0.0486562324615268,0.012167474557343242,0.11412440937060814,-0.1500650424171578,-0.31762206128665377,0.03374973084632452,0.07254524845871832,-0.3653383216300568,0.28723999974015474,-0.06534733992771476,0.07936668623383943,0.30377362358879734,-0.0313888629172723,-0.05317511940495921,-0.007353778214907491,-0.21232955731064468,0.02324318266534186,-0.05557481255140397,-0.36463111813192245,-0.29444163447463667,-0.14647939109376498,0.1298446642694535,0.5466475808001184,0.30658132815128797,-0.17523605652250251,-0.07153023406863213,0.04778134583362511,-0.2236534280629901,-0.046524424686447366,0.2998360505738816,-0.037915714774522685,-0.19151858370993044,0.11666154106716056,0.39011356350663423,-0.3191354412150073,0.044048880831665034,0.14075470517401573,-0.041643699558524344,-0.16565525249953006,0.028705820949240166,-0.21070052218901647,0.4992749884531095,0.14883781959871192,-0.4119358577511527,-0.5384860921215702,-0.1578043360843674,0.1715867846913926,-0.05601542578502135,-0.181090600014507,-0.004767911853389694,0.36159427367247543,-0.6207205931861679,0.16143732430872978,-0.2347321788986008,0.02273632080427238,0.055050118403001266,-0.24649299690862755,-0.21079601337770362,-0.09435739073079902,-0.08087513749427222,-0.12570423705430775,0.054864239286292686,0.2445069279570084,-0.3486694542618541,-0.4622815357787268,-0.18829677839364325,0.10042502855664337,0.256172057192821,0.25681665462332887,0.012307212748504305,0.4981143075924415,0.08744535314572321,0.19451923716764946,-0.272460309328971,-0.12226968038488518,-0.1705902868083545,-0.2491248824766704,0.11083746145104433,-0.04127803712466417,0.26021204985581436,-0.11932596629606439,-0.24519814463791909,-0.02791117617933007,-0.28244354604900657,0.15853182332856314,0.4105076242189903,-0.06333677049774628,0.3073548703611671,-0.000280045722792675,0.14617977460676973,0.12411557157318313,-0.05663811833924287,-0.2579154026779262,0.2646378246075534,-0.08221379174040509,0.19624638291341917,-0.0843930971361213,-0.1377280969898422,-0.032491969694564866,-0.13732083574808263,-0.008927843235614527,0.19387406647785918,-0.156196792162471,-0.007981663303715842,-0.04979786847705965,-0.1279741834075033,0.2477875669281204,0.2247705768261637,0.27278280325911264,0.29017828840326954,-0.10455101024504605,-0.004279102259255075,-0.40712080025053643,-0.11401444538073106,-0.08654718788026215,-0.26493524334260393,0.16893563661482427,-0.2326994313822164,0.37047250897853407,0.008457627486098896,-0.10205523319566598,-0.11571106793625015,0.055834398471883366,0.2878503557536509,0.18265529146248644,-0.020800547686393386,0.14096574524006286,-0.03788623276662517,-0.0743287546294076,0.1259401597856701,-0.10667986877401686,0.21194476094822606,-0.3093454746843933,0.2447658060239507,-0.31693133305419574,0.01592029882715894,0.17525215579995088,0.09279285385817676,-0.09228506655275047,0.07441991091669574,0.1557216060819564,0.19363100664665947,-0.12881685082208028,-0.3358800041598159,0.015616602990050594,-0.31054633313959296,0.19975015927444806,0.0874475831432002,0.09344918660626009,0.2395071971484206,0.19913564876399256,0.6006629726329407,0.1309550589845552,0.0729240306241849,-0.013779515424719104,0.13759209768387018,-0.21896729806994464,-0.09213411970088234,-0.5560763033179493,-0.23635780221069014,-0.43267011487638796,-0.12215130321391217,0.03636081589313297,0.2627331919290803,0.31121962735211695,-0.13332596469622154,-0.398363497350123,-0.21667043869565059,-0.5754971268115106,-0.10026832313167972,0.010454692140028074,-0.17342204542516113,-0.1105685666832444,-0.2382642917044751,0.1831290785513528,0.19652475426336388,0.050046242114350006,0.15041765251329967,-0.18117927555478625,0.050221169585144367,0.08144111413653794,0.21002425403370487,-0.5958981200472101,-0.20697989953415735,-0.03530745213101437],"B":[]}}}

Performance Metrics

131.23s Prediction Time
227.26s Total Time
Input Parameters
audio Type: stringDefault: https://replicate.delivery/pbxt/IZjTvet2ZGiyiYaMEEPrzn0xY1UDNsh0NfcO9qeTlpwCo7ig/lex-levin-4min.mp3
Audio file or url
max_speakers Type: integerRange: 1 - ∞
Maximum number of speakers to diarize. Default: None
min_speakers Type: integerRange: 1 - ∞
Minimum number of speakers to diarize. Default: None
num_speakers Type: integerRange: 1 - ∞
Number of speakers to diarize. Default: infer
Output Schema
segments Type: array
Segments
speakers
Example Execution Logs
pre-processing audio file...
diarizing audio file...
post-processing diarization...
Version Details
Version ID
6e29843b8c1b751ec384ad96d3566af2392046465152fef3cc22ad701090b64c
Version Created
February 23, 2024
Run on Replicate →