{"created":"2026-10-27T13:36:18.129278+00:00","scope":"Paired real CPU event / GPU caption tests, pinned public and authored sounds.","worker":{"ready":true,"busy":false,"model":"EfficientAT mn04_as","parameters":983599,"device":"cpu","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","recordings_saved":false},"fixtures":{"dog-1":{"filename":"1-100032-A-0.wav","fold":"1","target":"0","category":"dog","esc10":"True","src_file":"100032","take":"A","url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/audio/1-100032-A-0.wav","sha256":"f40a849a2375c8c63312a73dd2dd6c74007301fcc21b4be2ece29a642831e3d8","credit":"- [1-100032-A.ogg]: clip derived from rose_bark.wav (http://www.freesound.org/people/nfrae/sounds/100032/) by nfrae [CC0]","source_license_url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/LICENSE","audio_redistributed":false},"dog-2":{"filename":"1-110389-A-0.wav","fold":"1","target":"0","category":"dog","esc10":"True","src_file":"110389","take":"A","url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/audio/1-110389-A-0.wav","sha256":"4a18f3f834eb184b9f02595ac74c7de37ef8048a3da92f58f27018fec580b36a","credit":"- [1-110389-A.ogg]: clip derived from animals_dog_bark_springer_spaniel_001.wav (http://www.freesound.org/people/soundscalpel.com/sounds/110389/) by soundscalpel.com [CC-BY]","source_license_url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/LICENSE","audio_redistributed":false},"cat-1":{"filename":"1-34094-A-5.wav","fold":"1","target":"5","category":"cat","esc10":"False","src_file":"34094","take":"A","url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/audio/1-34094-A-5.wav","sha256":"ceddf296bcdda3996d35d3f4c292c338050bcb4c5a05a96ca22a69d33e33e4de","credit":"- [1-34094-A.ogg]: clip derived from 070422-cats-sample.wav (http://www.freesound.org/people/sazman/sounds/34094/) by sazman [CC-BY]","source_license_url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/LICENSE","audio_redistributed":false},"cat-2":{"filename":"1-34094-B-5.wav","fold":"1","target":"5","category":"cat","esc10":"False","src_file":"34094","take":"B","url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/audio/1-34094-B-5.wav","sha256":"43814c96e62a5c2fbf14b84828cc929e381e53c0add7c1e8211d212e1da97734","credit":"- [1-34094-B.ogg]: clip derived from 070422-cats-sample.wav (http://www.freesound.org/people/sazman/sounds/34094/) by sazman [CC-BY]","source_license_url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/LICENSE","audio_redistributed":false},"glass_breaking-1":{"filename":"1-20133-A-39.wav","fold":"1","target":"39","category":"glass_breaking","esc10":"False","src_file":"20133","take":"A","url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/audio/1-20133-A-39.wav","sha256":"db6946133c37fbd4513fe932dbb71e0b077bf7d240beaed339eb6c88e48c903b","credit":"- [1-20133-A.ogg]: clip derived from breaking_glass.wav (http://www.freesound.org/people/gezortenplotz/sounds/20133/) by gezortenplotz [CC-BY]","source_license_url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/LICENSE","audio_redistributed":false},"glass_breaking-2":{"filename":"1-84536-A-39.wav","fold":"1","target":"39","category":"glass_breaking","esc10":"False","src_file":"84536","take":"A","url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/audio/1-84536-A-39.wav","sha256":"79efba4c0c54acadc88783e83b428fc9c430db94515b25339a6b5598e2ade0c0","credit":"- [1-84536-A.ogg]: clip derived from glass.wav (http://www.freesound.org/people/cmusounddesign/sounds/84536/) by cmusounddesign [CC-BY]","source_license_url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/LICENSE","audio_redistributed":false},"car_horn-1":{"filename":"1-17124-A-43.wav","fold":"1","target":"43","category":"car_horn","esc10":"False","src_file":"17124","take":"A","url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/audio/1-17124-A-43.wav","sha256":"9d5e01e07a386ee36c2e73f40817d132a54d91c936eccc01414280abca5a4209","credit":"- [1-17124-A.ogg]: clip derived from car sharp horn.wav (http://www.freesound.org/people/cognito%20perceptu/sounds/17124/) by cognito perceptu [CC0]","source_license_url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/LICENSE","audio_redistributed":false},"car_horn-2":{"filename":"1-19026-A-43.wav","fold":"1","target":"43","category":"car_horn","esc10":"False","src_file":"19026","take":"A","url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/audio/1-19026-A-43.wav","sha256":"67bb2fe5cf138930eb6a6a84bedeb7284093076738cd47ef73cc8b3b8393ff40","credit":"- [1-19026-A.ogg]: clip derived from claxon.wav (http://www.freesound.org/people/han1/sounds/19026/) by han1 [CC-BY]","source_license_url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/LICENSE","audio_redistributed":false},"engine-1":{"filename":"1-18527-A-44.wav","fold":"1","target":"44","category":"engine","esc10":"False","src_file":"18527","take":"A","url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/audio/1-18527-A-44.wav","sha256":"83eb3e6065246fd87d1acbbe414aa5bfb7c2081a57c188713cdc017819ffc38f","credit":"- [1-18527-A.ogg]: clip derived from garbage_truck.wav (http://www.freesound.org/people/Corsica_S/sounds/18527/) by Corsica_S [CC-BY]","source_license_url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/LICENSE","audio_redistributed":false},"engine-2":{"filename":"1-18527-B-44.wav","fold":"1","target":"44","category":"engine","esc10":"False","src_file":"18527","take":"B","url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/audio/1-18527-B-44.wav","sha256":"40f0ab8a2fa68cbdf814f10fc8b2c26916b3dc54c1b0e719d4697ba58c0bdb81","credit":"- [1-18527-B.ogg]: clip derived from garbage_truck.wav (http://www.freesound.org/people/Corsica_S/sounds/18527/) by Corsica_S [CC-BY]","source_license_url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/LICENSE","audio_redistributed":false},"rain-1":{"filename":"1-17367-A-10.wav","fold":"1","target":"10","category":"rain","esc10":"True","src_file":"17367","take":"A","url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/audio/1-17367-A-10.wav","sha256":"d732acd2e0c7c40405968010f49f250740c86998fc416eff2ed5330fc8c89dea","credit":"- [1-17367-A.ogg]: clip derived from unlocki door to mod rain.wav (http://www.freesound.org/people/cognito%20perceptu/sounds/17367/) by cognito perceptu [CC0]","source_license_url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/LICENSE","audio_redistributed":false},"rain-2":{"filename":"1-21189-A-10.wav","fold":"1","target":"10","category":"rain","esc10":"True","src_file":"21189","take":"A","url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/audio/1-21189-A-10.wav","sha256":"5f15ab2d8f6ef9932909b1b75c8ac254cbea46c93b4b2f0f3542abdf09b9abc0","credit":"- [1-21189-A.ogg]: clip derived from Louisiana Rain 1.wav (http://www.freesound.org/people/uberhuberman/sounds/21189/) by uberhuberman [CC0]","source_license_url":"https://raw.githubusercontent.com/karolpiczak/ESC-50/33c8ce9eb2cf0b1c2f8bcf322eb349b6be34dbb6/LICENSE","audio_redistributed":false},"authored_music":{"license":"CC0 authored deterministic melody, environment_fixtures.py"},"authored_impacts":{"license":"CC0 procedural impacts"}},"rows":[{"fixture":"dog-1","tags":{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":50.57,"window_s":5.0,"candidates":[{"label":"Bark","score":0.7576},{"label":"Dog","score":0.7574},{"label":"Animal","score":0.7333},{"label":"Domestic animals, pets","score":0.6429},{"label":"Silence","score":0.4257},{"label":"Bow-wow","score":0.2688}],"music_score":0.0931,"speech_score":0.0305,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Bark","score":0.7481},{"label":"Dog","score":0.6245},{"label":"Animal","score":0.5757}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Bark","score":0.7576},{"label":"Dog","score":0.7574},{"label":"Animal","score":0.6967}]},{"start_s":2.56,"end_s":3.84,"candidates":[{"label":"Silence","score":0.4227},{"label":"Music","score":0.0876},{"label":"Sound effect","score":0.02}]},{"start_s":3.2,"end_s":4.48,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":3.72,"end_s":5.0,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":54.29},"caption":{"status":"available","caption":"The audio contains a single, distinct dog bark. The bark is relatively short and sharp, with a medium pitch.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":5.0,"tokens":24,"preprocess_ms":10.92,"encoder_gpu_ms":15.9,"decoder_gpu_ms":192.05,"inference_ms":208.22,"total_ms":219.13,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":222.04},"parallel_wall_ms":222.43},{"fixture":"dog-2","tags":{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":36.37,"window_s":5.0,"candidates":[{"label":"Animal","score":0.7345},{"label":"Dog","score":0.6525},{"label":"Bark","score":0.6112},{"label":"Domestic animals, pets","score":0.5464},{"label":"Silence","score":0.4257},{"label":"Bow-wow","score":0.2783}],"music_score":0.0931,"speech_score":0.018,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Dog","score":0.6108},{"label":"Animal","score":0.5832},{"label":"Bark","score":0.5359}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":2.56,"end_s":3.84,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":3.2,"end_s":4.48,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":3.72,"end_s":5.0,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":40.24},"caption":{"status":"available","caption":"A single, sharp, and distinct percussive sound is heard. It has a dry, crisp quality, resembling a quick, forceful impact or a single strike.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":5.0,"tokens":36,"preprocess_ms":8.63,"encoder_gpu_ms":8.09,"decoder_gpu_ms":387.75,"inference_ms":396.09,"total_ms":404.72,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":407.53},"parallel_wall_ms":408.19},{"fixture":"cat-1","tags":{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":38.14,"window_s":5.0,"candidates":[{"label":"Cat","score":0.8499},{"label":"Animal","score":0.8237},{"label":"Domestic animals, pets","score":0.7773},{"label":"Siren","score":0.771},{"label":"Meow","score":0.709},{"label":"Civil defense siren","score":0.3953}],"music_score":0.1418,"speech_score":0.1031,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Siren","score":0.771},{"label":"Civil defense siren","score":0.3953},{"label":"Emergency vehicle","score":0.3571}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Animal","score":0.3506},{"label":"Domestic animals, pets","score":0.3048},{"label":"Cat","score":0.2585}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Music","score":0.1418},{"label":"Animal","score":0.0853},{"label":"Theremin","score":0.0448}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Cat","score":0.2075},{"label":"Meow","score":0.1825},{"label":"Animal","score":0.1767}]},{"start_s":2.56,"end_s":3.84,"candidates":[{"label":"Animal","score":0.1595},{"label":"Siren","score":0.1369},{"label":"Cat","score":0.126}]},{"start_s":3.2,"end_s":4.48,"candidates":[{"label":"Cat","score":0.597},{"label":"Animal","score":0.526},{"label":"Domestic animals, pets","score":0.4975}]},{"start_s":3.72,"end_s":5.0,"candidates":[{"label":"Music","score":0.0597},{"label":"Animal","score":0.0594},{"label":"Cat","score":0.0317}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":41.91},"caption":{"status":"available","caption":"The audio features a distinct, high-pitched meow sound. The meow is short and clear, with a slight wavering in pitch.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":5.0,"tokens":30,"preprocess_ms":7.6,"encoder_gpu_ms":15.79,"decoder_gpu_ms":343.87,"inference_ms":359.88,"total_ms":367.48,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":370.25},"parallel_wall_ms":370.91},{"fixture":"cat-2","tags":{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":37.84,"window_s":5.0,"candidates":[{"label":"Cat","score":0.907},{"label":"Animal","score":0.8743},{"label":"Domestic animals, pets","score":0.8457},{"label":"Meow","score":0.7785},{"label":"Caterwaul","score":0.4261},{"label":"Siren","score":0.3925}],"music_score":0.0879,"speech_score":0.0794,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Cat","score":0.5593},{"label":"Animal","score":0.4588},{"label":"Domestic animals, pets","score":0.3431}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Siren","score":0.3925},{"label":"Emergency vehicle","score":0.3109},{"label":"Cat","score":0.129}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Siren","score":0.2825},{"label":"Emergency vehicle","score":0.1634},{"label":"Fire engine, fire truck (siren)","score":0.1291}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Animal","score":0.2819},{"label":"Baby cry, infant cry","score":0.2063},{"label":"Domestic animals, pets","score":0.1559}]},{"start_s":2.56,"end_s":3.84,"candidates":[{"label":"Cat","score":0.907},{"label":"Animal","score":0.8743},{"label":"Domestic animals, pets","score":0.8457}]},{"start_s":3.2,"end_s":4.48,"candidates":[{"label":"Cat","score":0.8461},{"label":"Animal","score":0.7656},{"label":"Domestic animals, pets","score":0.7383}]},{"start_s":3.72,"end_s":5.0,"candidates":[{"label":"Cat","score":0.7669},{"label":"Meow","score":0.5956},{"label":"Domestic animals, pets","score":0.5511}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":41.99},"caption":{"status":"available","caption":"The audio contains a loud, sustained siren sound. The siren has a rising and falling pitch, characteristic of emergency vehicles.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":5.0,"tokens":27,"preprocess_ms":6.95,"encoder_gpu_ms":15.19,"decoder_gpu_ms":307.57,"inference_ms":322.94,"total_ms":329.89,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":332.72},"parallel_wall_ms":333.42},{"fixture":"glass_breaking-1","tags":{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":39.34,"window_s":5.0,"candidates":[{"label":"Breaking","score":0.6896},{"label":"Machine gun","score":0.4884},{"label":"Glass","score":0.4862},{"label":"Silence","score":0.4257},{"label":"Gunshot, gunfire","score":0.2117},{"label":"Shatter","score":0.1869}],"music_score":0.0931,"speech_score":0.0198,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Shatter","score":0.1039},{"label":"Glass","score":0.0862},{"label":"Breaking","score":0.0812}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Chink, clink","score":0.1215},{"label":"Dishes, pots, and pans","score":0.0302},{"label":"Vehicle","score":0.0248}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Machine gun","score":0.4884},{"label":"Gunshot, gunfire","score":0.2117},{"label":"Music","score":0.0292}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Machine gun","score":0.1568},{"label":"Gunshot, gunfire","score":0.0631},{"label":"Sound effect","score":0.0195}]},{"start_s":2.56,"end_s":3.84,"candidates":[{"label":"Writing","score":0.0488},{"label":"Walk, footsteps","score":0.048},{"label":"Silence","score":0.045}]},{"start_s":3.2,"end_s":4.48,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":3.72,"end_s":5.0,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":43.39},"caption":{"status":"available","caption":"The audio contains a single, sharp, percussive sound. It sounds like a single, forceful strike, possibly a drum hit or a similar impact.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":5.0,"tokens":33,"preprocess_ms":8.43,"encoder_gpu_ms":16.7,"decoder_gpu_ms":367.73,"inference_ms":384.64,"total_ms":393.07,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":396.05},"parallel_wall_ms":396.73},{"fixture":"glass_breaking-2","tags":{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":38.04,"window_s":5.0,"candidates":[{"label":"Breaking","score":0.8607},{"label":"Coin (dropping)","score":0.7279},{"label":"Glass","score":0.6588},{"label":"Silence","score":0.4257},{"label":"Shatter","score":0.2371},{"label":"Chink, clink","score":0.1099}],"music_score":0.0931,"speech_score":0.0221,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Glass","score":0.5323},{"label":"Breaking","score":0.2999},{"label":"Chink, clink","score":0.0903}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Glass","score":0.6588},{"label":"Breaking","score":0.6361},{"label":"Shatter","score":0.2371}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Coin (dropping)","score":0.7279},{"label":"Mechanisms","score":0.0411},{"label":"Chink, clink","score":0.0236}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Boat, Water vehicle","score":0.1032},{"label":"Animal","score":0.0815},{"label":"Rustling leaves","score":0.0634}]},{"start_s":2.56,"end_s":3.84,"candidates":[{"label":"Silence","score":0.1398},{"label":"Music","score":0.0438},{"label":"Sound effect","score":0.0328}]},{"start_s":3.2,"end_s":4.48,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":3.72,"end_s":5.0,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":41.64},"caption":{"status":"available","caption":"The audio contains a single, sharp, and loud gunshot sound. The sound is brief and impactful, with a clear attack and decay.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":5.0,"tokens":29,"preprocess_ms":8.24,"encoder_gpu_ms":15.87,"decoder_gpu_ms":311.95,"inference_ms":328.03,"total_ms":336.27,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":339.0},"parallel_wall_ms":339.57},{"fixture":"car_horn-1","tags":{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":39.18,"window_s":5.0,"candidates":[{"label":"Vehicle horn, car horn, honking","score":0.5791},{"label":"Vehicle","score":0.5662},{"label":"Silence","score":0.4257},{"label":"Car","score":0.3283},{"label":"Outside, urban or manmade","score":0.2147},{"label":"Toot","score":0.1322}],"music_score":0.0931,"speech_score":0.0345,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Vehicle","score":0.4262},{"label":"Vehicle horn, car horn, honking","score":0.2686},{"label":"Car","score":0.1521}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Silence","score":0.3223},{"label":"Music","score":0.0665},{"label":"Sound effect","score":0.0182}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":2.56,"end_s":3.84,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":3.2,"end_s":4.48,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":3.72,"end_s":5.0,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":42.73},"caption":{"status":"available","caption":"The audio features a single, distinct, and sharp metallic clang. The sound is brief and has a clear, resonant quality.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":5.0,"tokens":28,"preprocess_ms":8.57,"encoder_gpu_ms":8.3,"decoder_gpu_ms":205.58,"inference_ms":214.09,"total_ms":222.66,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":225.27},"parallel_wall_ms":225.83},{"fixture":"car_horn-2","tags":{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":36.76,"window_s":5.0,"candidates":[{"label":"Vehicle horn, car horn, honking","score":0.8448},{"label":"Music","score":0.6307},{"label":"Silence","score":0.4296},{"label":"Musical instrument","score":0.2982},{"label":"Air horn, truck horn","score":0.2651},{"label":"Vehicle","score":0.2076}],"music_score":0.6307,"speech_score":0.0231,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Vehicle horn, car horn, honking","score":0.4439},{"label":"Air horn, truck horn","score":0.2651},{"label":"Siren","score":0.1421}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Music","score":0.4068},{"label":"Musical instrument","score":0.2982},{"label":"Vehicle horn, car horn, honking","score":0.2224}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Music","score":0.6307},{"label":"Musical instrument","score":0.0626},{"label":"Silence","score":0.0276}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Silence","score":0.4296},{"label":"Music","score":0.0919},{"label":"Sound effect","score":0.0193}]},{"start_s":2.56,"end_s":3.84,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":3.2,"end_s":4.48,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":3.72,"end_s":5.0,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":40.33},"caption":{"status":"available","caption":"The audio features a short, sharp sound, similar to a gunshot or a gunshot. The sound is abrupt and percussive, with a quick decay.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":5.0,"tokens":34,"preprocess_ms":8.15,"encoder_gpu_ms":8.1,"decoder_gpu_ms":255.4,"inference_ms":263.69,"total_ms":271.85,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":273.99},"parallel_wall_ms":274.45},{"fixture":"engine-1","tags":{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":38.11,"window_s":5.0,"candidates":[{"label":"Vehicle","score":0.6851},{"label":"Truck","score":0.291},{"label":"Engine","score":0.2404},{"label":"Heavy engine (low frequency)","score":0.2321},{"label":"Idling","score":0.2272},{"label":"Bus","score":0.1827}],"music_score":0.0411,"speech_score":0.0222,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Vehicle","score":0.6546},{"label":"Truck","score":0.2261},{"label":"Engine","score":0.2069}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Vehicle","score":0.6851},{"label":"Engine","score":0.2382},{"label":"Idling","score":0.2272}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Vehicle","score":0.6156},{"label":"Truck","score":0.2317},{"label":"Idling","score":0.2072}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Vehicle","score":0.592},{"label":"Truck","score":0.232},{"label":"Idling","score":0.1834}]},{"start_s":2.56,"end_s":3.84,"candidates":[{"label":"Vehicle","score":0.6644},{"label":"Truck","score":0.2393},{"label":"Engine","score":0.1775}]},{"start_s":3.2,"end_s":4.48,"candidates":[{"label":"Vehicle","score":0.6669},{"label":"Truck","score":0.291},{"label":"Engine","score":0.2404}]},{"start_s":3.72,"end_s":5.0,"candidates":[{"label":"Vehicle","score":0.6178},{"label":"Engine","score":0.2067},{"label":"Truck","score":0.1809}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":41.95},"caption":{"status":"available","caption":"The audio features a distinct, low-frequency rumble, accompanied by a higher-pitched whine. The sounds are consistent and do not vary significantly in intensity.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":5.0,"tokens":36,"preprocess_ms":8.42,"encoder_gpu_ms":17.16,"decoder_gpu_ms":248.96,"inference_ms":266.33,"total_ms":274.75,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":277.27},"parallel_wall_ms":277.83},{"fixture":"engine-2","tags":{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":35.61,"window_s":5.0,"candidates":[{"label":"Vehicle","score":0.7695},{"label":"Truck","score":0.4732},{"label":"Bus","score":0.3085},{"label":"Car","score":0.1793},{"label":"Heavy engine (low frequency)","score":0.1688},{"label":"Idling","score":0.1486}],"music_score":0.0726,"speech_score":0.0184,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Vehicle","score":0.5242},{"label":"Truck","score":0.2209},{"label":"Bus","score":0.1532}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Vehicle","score":0.6337},{"label":"Truck","score":0.2456},{"label":"Bus","score":0.1772}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Vehicle","score":0.7656},{"label":"Truck","score":0.3014},{"label":"Bus","score":0.2833}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Vehicle","score":0.7695},{"label":"Truck","score":0.4732},{"label":"Bus","score":0.2382}]},{"start_s":2.56,"end_s":3.84,"candidates":[{"label":"Vehicle","score":0.7279},{"label":"Bus","score":0.2834},{"label":"Truck","score":0.2748}]},{"start_s":3.2,"end_s":4.48,"candidates":[{"label":"Vehicle","score":0.6606},{"label":"Bus","score":0.2029},{"label":"Truck","score":0.1977}]},{"start_s":3.72,"end_s":5.0,"candidates":[{"label":"Vehicle","score":0.5789},{"label":"Bus","score":0.3085},{"label":"Truck","score":0.2987}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":39.6},"caption":{"status":"available","caption":"The audio features a continuous, low-frequency hum, consistent with the sound of a large engine or machinery. The sound is steady and has a deep, resonant quality.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":5.0,"tokens":37,"preprocess_ms":8.2,"encoder_gpu_ms":8.33,"decoder_gpu_ms":270.23,"inference_ms":278.78,"total_ms":286.97,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":289.55},"parallel_wall_ms":290.21},{"fixture":"rain-1","tags":{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":38.14,"window_s":5.0,"candidates":[{"label":"Rain","score":0.6023},{"label":"Rain on surface","score":0.4806},{"label":"Raindrop","score":0.4542},{"label":"Stream","score":0.3459},{"label":"Waterfall","score":0.2317},{"label":"Vehicle","score":0.1453}],"music_score":0.0644,"speech_score":0.0454,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Rain","score":0.1113},{"label":"Rain on surface","score":0.0953},{"label":"Vehicle","score":0.0872}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Stream","score":0.3459},{"label":"Waterfall","score":0.2317},{"label":"Water","score":0.1245}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Stream","score":0.1808},{"label":"Vehicle","score":0.1453},{"label":"Waterfall","score":0.1221}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Vehicle","score":0.1241},{"label":"Rain","score":0.0835},{"label":"Waterfall","score":0.0826}]},{"start_s":2.56,"end_s":3.84,"candidates":[{"label":"Rain","score":0.154},{"label":"Rain on surface","score":0.1199},{"label":"Raindrop","score":0.0832}]},{"start_s":3.2,"end_s":4.48,"candidates":[{"label":"Rain","score":0.457},{"label":"Rain on surface","score":0.358},{"label":"Raindrop","score":0.2218}]},{"start_s":3.72,"end_s":5.0,"candidates":[{"label":"Rain","score":0.2887},{"label":"Rain on surface","score":0.2026},{"label":"Raindrop","score":0.1636}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":42.11},"caption":{"status":"available","caption":"The audio contains the sound of liquid being poured. The sound is continuous and consistent, with a moderate volume.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":5.0,"tokens":23,"preprocess_ms":8.19,"encoder_gpu_ms":8.09,"decoder_gpu_ms":171.96,"inference_ms":180.23,"total_ms":188.42,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":190.96},"parallel_wall_ms":191.6},{"fixture":"rain-2","tags":{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":36.49,"window_s":5.0,"candidates":[{"label":"Rain on surface","score":0.6967},{"label":"Rain","score":0.626},{"label":"Raindrop","score":0.4056},{"label":"Static","score":0.1264},{"label":"Music","score":0.0795},{"label":"Waterfall","score":0.0527}],"music_score":0.0795,"speech_score":0.0312,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Rain on surface","score":0.6361},{"label":"Rain","score":0.626},{"label":"Raindrop","score":0.4056}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Rain on surface","score":0.6297},{"label":"Rain","score":0.5288},{"label":"Raindrop","score":0.2666}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Rain on surface","score":0.4041},{"label":"Rain","score":0.2913},{"label":"Raindrop","score":0.1757}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Rain on surface","score":0.6967},{"label":"Rain","score":0.5997},{"label":"Raindrop","score":0.363}]},{"start_s":2.56,"end_s":3.84,"candidates":[{"label":"Rain on surface","score":0.3202},{"label":"Rain","score":0.2207},{"label":"Raindrop","score":0.0714}]},{"start_s":3.2,"end_s":4.48,"candidates":[{"label":"Rain on surface","score":0.6099},{"label":"Rain","score":0.4882},{"label":"Raindrop","score":0.2619}]},{"start_s":3.72,"end_s":5.0,"candidates":[{"label":"Rain on surface","score":0.6241},{"label":"Rain","score":0.4927},{"label":"Raindrop","score":0.2874}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":40.65},"caption":{"status":"available","caption":"The audio features the sound of a vehicle. The sound is a low rumble, possibly from an engine, and a distinct whooshing sound, possibly from the vehicle moving at a moderate speed.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":5.0,"tokens":39,"preprocess_ms":8.49,"encoder_gpu_ms":8.32,"decoder_gpu_ms":302.74,"inference_ms":311.28,"total_ms":319.77,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":322.55},"parallel_wall_ms":323.21},{"fixture":"authored_music","tags":{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":36.89,"window_s":5.0,"candidates":[{"label":"Music","score":0.9098},{"label":"Musical instrument","score":0.1429},{"label":"Electric piano","score":0.1264},{"label":"Keyboard (musical)","score":0.1175},{"label":"Piano","score":0.1134},{"label":"Synthesizer","score":0.0971}],"music_score":0.9098,"speech_score":0.0145,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Music","score":0.8757},{"label":"Musical instrument","score":0.1429},{"label":"Electric piano","score":0.1264}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Music","score":0.9098},{"label":"Musical instrument","score":0.1015},{"label":"Synthesizer","score":0.0703}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Music","score":0.8656},{"label":"Musical instrument","score":0.1131},{"label":"Synthesizer","score":0.0971}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Music","score":0.8796},{"label":"Musical instrument","score":0.1231},{"label":"Electric piano","score":0.0878}]},{"start_s":2.56,"end_s":3.84,"candidates":[{"label":"Music","score":0.8769},{"label":"Musical instrument","score":0.0691},{"label":"Electric piano","score":0.069}]},{"start_s":3.2,"end_s":4.48,"candidates":[{"label":"Music","score":0.8063},{"label":"Musical instrument","score":0.0899},{"label":"Electric piano","score":0.058}]},{"start_s":3.72,"end_s":5.0,"candidates":[{"label":"Music","score":0.8487},{"label":"Keyboard (musical)","score":0.1175},{"label":"Musical instrument","score":0.1174}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":40.58},"caption":{"status":"available","caption":"The audio features a repetitive, rhythmic electronic beat. A synthesized bassline is prominent, along with a simple, repeating melody.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":5.0,"tokens":27,"preprocess_ms":7.21,"encoder_gpu_ms":8.11,"decoder_gpu_ms":186.41,"inference_ms":194.72,"total_ms":201.93,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":204.4},"parallel_wall_ms":204.95},{"fixture":"authored_impacts","tags":{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":35.05,"window_s":5.0,"candidates":[{"label":"Music","score":0.779},{"label":"Drum machine","score":0.6572},{"label":"Silence","score":0.4257},{"label":"Drum","score":0.1841},{"label":"Sampler","score":0.1602},{"label":"Musical instrument","score":0.1468}],"music_score":0.779,"speech_score":0.0137,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Music","score":0.7485},{"label":"Drum machine","score":0.6572},{"label":"Sampler","score":0.1602}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Music","score":0.779},{"label":"Drum machine","score":0.5494},{"label":"Sampler","score":0.131}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":2.56,"end_s":3.84,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":3.2,"end_s":4.48,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]},{"start_s":3.72,"end_s":5.0,"candidates":[{"label":"Silence","score":0.4257},{"label":"Music","score":0.0931},{"label":"Sound effect","score":0.0186}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":38.75},"caption":{"status":"available","caption":"The audio contains a single, distinct percussive sound. It is a sharp, dry, and short sound with a quick decay.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":5.0,"tokens":28,"preprocess_ms":8.64,"encoder_gpu_ms":8.1,"decoder_gpu_ms":213.23,"inference_ms":221.52,"total_ms":230.16,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":232.65},"parallel_wall_ms":233.2}],"timings":[{"repeat":0,"mode":"caption_only","wall_ms":301.01,"jobs":[{"status":"available","caption":"The audio features a fast-paced electronic track with a prominent, repetitive synth melody. A driving beat is present, with a strong bassline and a consistent rhythmic pulse.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":3.2,"tokens":35,"preprocess_ms":9.14,"encoder_gpu_ms":16.6,"decoder_gpu_ms":273.23,"inference_ms":290.06,"total_ms":299.2,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":301.01}]},{"repeat":0,"mode":"parallel","wall_ms":268.49,"jobs":[{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":35.43,"window_s":3.2,"candidates":[{"label":"Music","score":0.9098},{"label":"Musical instrument","score":0.1429},{"label":"Electric piano","score":0.1264},{"label":"Piano","score":0.1134},{"label":"Keyboard (musical)","score":0.1133},{"label":"Synthesizer","score":0.0971}],"music_score":0.9098,"speech_score":0.0125,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Music","score":0.8757},{"label":"Musical instrument","score":0.1429},{"label":"Electric piano","score":0.1264}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Music","score":0.9098},{"label":"Musical instrument","score":0.1015},{"label":"Synthesizer","score":0.0703}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Music","score":0.8656},{"label":"Musical instrument","score":0.1131},{"label":"Synthesizer","score":0.0971}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Music","score":0.8796},{"label":"Musical instrument","score":0.1234},{"label":"Electric piano","score":0.0876}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":38.22},{"status":"available","caption":"The audio features a fast-paced electronic track with a prominent, repetitive synth melody. A driving beat is present, with a strong bassline and a consistent rhythmic pulse.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":3.2,"tokens":35,"preprocess_ms":8.26,"encoder_gpu_ms":8.1,"decoder_gpu_ms":249.79,"inference_ms":258.08,"total_ms":266.34,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":268.17}]},{"repeat":1,"mode":"parallel","wall_ms":278.01,"jobs":[{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":28.12,"window_s":3.2,"candidates":[{"label":"Music","score":0.9098},{"label":"Musical instrument","score":0.1429},{"label":"Electric piano","score":0.1264},{"label":"Piano","score":0.1134},{"label":"Keyboard (musical)","score":0.1133},{"label":"Synthesizer","score":0.0971}],"music_score":0.9098,"speech_score":0.0125,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Music","score":0.8757},{"label":"Musical instrument","score":0.1429},{"label":"Electric piano","score":0.1264}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Music","score":0.9098},{"label":"Musical instrument","score":0.1015},{"label":"Synthesizer","score":0.0703}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Music","score":0.8656},{"label":"Musical instrument","score":0.1131},{"label":"Synthesizer","score":0.0971}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Music","score":0.8796},{"label":"Musical instrument","score":0.1234},{"label":"Electric piano","score":0.0876}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":30.85},{"status":"available","caption":"The audio features a fast-paced electronic track with a prominent, repetitive synth melody. A driving beat is present, with a strong bassline and a consistent rhythmic pulse.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":3.2,"tokens":35,"preprocess_ms":6.32,"encoder_gpu_ms":14.17,"decoder_gpu_ms":255.17,"inference_ms":269.53,"total_ms":275.85,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":277.68}]},{"repeat":1,"mode":"caption_only","wall_ms":320.74,"jobs":[{"status":"available","caption":"The audio features a fast-paced electronic track with a prominent, repetitive synth melody. A driving beat is present, with a strong bassline and a consistent rhythmic pulse.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":3.2,"tokens":35,"preprocess_ms":8.4,"encoder_gpu_ms":15.25,"decoder_gpu_ms":294.86,"inference_ms":310.3,"total_ms":318.7,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":320.74}]},{"repeat":2,"mode":"caption_only","wall_ms":392.94,"jobs":[{"status":"available","caption":"The audio features a fast-paced electronic track with a prominent, repetitive synth melody. A driving beat is present, with a strong bassline and a consistent rhythmic pulse.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":3.2,"tokens":35,"preprocess_ms":8.68,"encoder_gpu_ms":8.08,"decoder_gpu_ms":373.89,"inference_ms":382.16,"total_ms":390.84,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":392.94}]},{"repeat":2,"mode":"parallel","wall_ms":420.57,"jobs":[{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":27.84,"window_s":3.2,"candidates":[{"label":"Music","score":0.9098},{"label":"Musical instrument","score":0.1429},{"label":"Electric piano","score":0.1264},{"label":"Piano","score":0.1134},{"label":"Keyboard (musical)","score":0.1133},{"label":"Synthesizer","score":0.0971}],"music_score":0.9098,"speech_score":0.0125,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Music","score":0.8757},{"label":"Musical instrument","score":0.1429},{"label":"Electric piano","score":0.1264}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Music","score":0.9098},{"label":"Musical instrument","score":0.1015},{"label":"Synthesizer","score":0.0703}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Music","score":0.8656},{"label":"Musical instrument","score":0.1131},{"label":"Synthesizer","score":0.0971}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Music","score":0.8796},{"label":"Musical instrument","score":0.1234},{"label":"Electric piano","score":0.0876}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":30.41},{"status":"available","caption":"The audio features a fast-paced electronic track with a prominent, repetitive synth melody. A driving beat is present, with a strong bassline and a consistent rhythmic pulse.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":3.2,"tokens":35,"preprocess_ms":9.09,"encoder_gpu_ms":16.89,"decoder_gpu_ms":391.99,"inference_ms":409.13,"total_ms":418.21,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":420.24}]},{"repeat":3,"mode":"parallel","wall_ms":261.69,"jobs":[{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":29.96,"window_s":3.2,"candidates":[{"label":"Music","score":0.9098},{"label":"Musical instrument","score":0.1429},{"label":"Electric piano","score":0.1264},{"label":"Piano","score":0.1134},{"label":"Keyboard (musical)","score":0.1133},{"label":"Synthesizer","score":0.0971}],"music_score":0.9098,"speech_score":0.0125,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Music","score":0.8757},{"label":"Musical instrument","score":0.1429},{"label":"Electric piano","score":0.1264}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Music","score":0.9098},{"label":"Musical instrument","score":0.1015},{"label":"Synthesizer","score":0.0703}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Music","score":0.8656},{"label":"Musical instrument","score":0.1131},{"label":"Synthesizer","score":0.0971}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Music","score":0.8796},{"label":"Musical instrument","score":0.1234},{"label":"Electric piano","score":0.0876}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":32.97},{"status":"available","caption":"The audio features a fast-paced electronic track with a prominent, repetitive synth melody. A driving beat is present, with a strong bassline and a consistent rhythmic pulse.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":3.2,"tokens":35,"preprocess_ms":8.77,"encoder_gpu_ms":8.1,"decoder_gpu_ms":242.16,"inference_ms":250.45,"total_ms":259.23,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":261.36}]},{"repeat":3,"mode":"caption_only","wall_ms":360.88,"jobs":[{"status":"available","caption":"The audio features a fast-paced electronic track with a prominent, repetitive synth melody. A driving beat is present, with a strong bassline and a consistent rhythmic pulse.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":3.2,"tokens":35,"preprocess_ms":9.3,"encoder_gpu_ms":8.82,"decoder_gpu_ms":340.62,"inference_ms":349.69,"total_ms":358.99,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":360.88}]},{"repeat":4,"mode":"caption_only","wall_ms":413.12,"jobs":[{"status":"available","caption":"The audio features a fast-paced electronic track with a prominent, repetitive synth melody. A driving beat is present, with a strong bassline and a consistent rhythmic pulse.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":3.2,"tokens":35,"preprocess_ms":8.65,"encoder_gpu_ms":11.77,"decoder_gpu_ms":390.58,"inference_ms":402.59,"total_ms":411.24,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":413.12}]},{"repeat":4,"mode":"parallel","wall_ms":283.14,"jobs":[{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":28.18,"window_s":3.2,"candidates":[{"label":"Music","score":0.9098},{"label":"Musical instrument","score":0.1429},{"label":"Electric piano","score":0.1264},{"label":"Piano","score":0.1134},{"label":"Keyboard (musical)","score":0.1133},{"label":"Synthesizer","score":0.0971}],"music_score":0.9098,"speech_score":0.0125,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Music","score":0.8757},{"label":"Musical instrument","score":0.1429},{"label":"Electric piano","score":0.1264}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Music","score":0.9098},{"label":"Musical instrument","score":0.1015},{"label":"Synthesizer","score":0.0703}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Music","score":0.8656},{"label":"Musical instrument","score":0.1131},{"label":"Synthesizer","score":0.0971}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Music","score":0.8796},{"label":"Musical instrument","score":0.1234},{"label":"Electric piano","score":0.0876}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":30.88},{"status":"available","caption":"The audio features a fast-paced electronic track with a prominent, repetitive synth melody. A driving beat is present, with a strong bassline and a consistent rhythmic pulse.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":3.2,"tokens":35,"preprocess_ms":6.93,"encoder_gpu_ms":8.45,"decoder_gpu_ms":265.2,"inference_ms":273.87,"total_ms":280.8,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":282.74}]},{"repeat":5,"mode":"parallel","wall_ms":267.78,"jobs":[{"status":"available","model":"EfficientAT mn04_as","revision":"a425fdce92572e602a1d5634799bd9f1f2efa806","weight_sha256":"899a8c6217063f6941793102a2780b3dd788ab11fce468d9cf5f0577c453321c","device":"cpu","parameters":983599,"total_ms":27.55,"window_s":3.2,"candidates":[{"label":"Music","score":0.9098},{"label":"Musical instrument","score":0.1429},{"label":"Electric piano","score":0.1264},{"label":"Piano","score":0.1134},{"label":"Keyboard (musical)","score":0.1133},{"label":"Synthesizer","score":0.0971}],"music_score":0.9098,"speech_score":0.0125,"frames":[{"start_s":0.0,"end_s":1.28,"candidates":[{"label":"Music","score":0.8757},{"label":"Musical instrument","score":0.1429},{"label":"Electric piano","score":0.1264}]},{"start_s":0.64,"end_s":1.92,"candidates":[{"label":"Music","score":0.9098},{"label":"Musical instrument","score":0.1015},{"label":"Synthesizer","score":0.0703}]},{"start_s":1.28,"end_s":2.56,"candidates":[{"label":"Music","score":0.8656},{"label":"Musical instrument","score":0.1131},{"label":"Synthesizer","score":0.0971}]},{"start_s":1.92,"end_s":3.2,"candidates":[{"label":"Music","score":0.8796},{"label":"Musical instrument","score":0.1234},{"label":"Electric piano","score":0.0876}]}],"temporal_resolution_note":"Overlapping 1.28-second classification windows, 0.64-second stride; not precise event boundaries or spatial direction.","uncertainty":"Multilabel model scores, not calibrated event probabilities.","http_ms":29.8},{"status":"available","caption":"The audio features a fast-paced electronic track with a prominent, repetitive synth melody. A driving beat is present, with a strong bassline and a consistent rhythmic pulse.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":3.2,"tokens":35,"preprocess_ms":8.87,"encoder_gpu_ms":8.32,"decoder_gpu_ms":248.28,"inference_ms":256.82,"total_ms":265.69,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":267.46}]},{"repeat":5,"mode":"caption_only","wall_ms":265.99,"jobs":[{"status":"available","caption":"The audio features a fast-paced electronic track with a prominent, repetitive synth melody. A driving beat is present, with a strong bassline and a consistent rhythmic pulse.","uncertainty":"Fallible sound hypothesis, not a transcript or confirmed event.","window_s":3.2,"tokens":35,"preprocess_ms":9.08,"encoder_gpu_ms":8.11,"decoder_gpu_ms":246.98,"inference_ms":255.31,"total_ms":264.39,"model":"laion/sound-effect-captioning-whisper","revision":"bb36f9c6534037a8d1d78cff97d119dd37da478a","device":"cuda:0","precision":"float16","http_ms":265.99}]}],"notes":["No spatial localization with a mono microphone.","AudioSet scores are not calibrated probabilities.","The 1.28-second sliding windows are approximate temporal localization, not event boundary ground truth.","These few examples are diagnostic, not a representative accuracy estimate."]}