mispeech/ced-mini
44k
1{2 "architectures": [3 "CedForAudioClassification"4 ],5 "auto_map": {6 "AutoConfig": "configuration_ced.CedConfig",7 "AutoModel": "modeling_ced.CedModel",8 "AutoModelForAudioClassification": "modeling_ced.CedForAudioClassification"9 },10 "attn_drop_rate": 0.0,11 "center": true,12 "depth": 12,13 "drop_path_rate": 0.0,14 "drop_rate": 0.0,15 "embed_dim": 256,16 "eval_avg": "mean",17 "f_max": 8000,18 "f_min": 0,19 "hop_size": 160,20 "id2label": {21 "0": "Speech",22 "1": "Male speech",23 "2": "Female speech",24 "3": "Child speech",25 "4": "Conversation",26 "5": "Narration",27 "6": "Babbling",28 "7": "Speech synthesizer",29 "8": "Shout",30 "9": "Bellow",31 "10": "Whoop",32 "11": "Yell",33 "12": "Battle cry",34 "13": "Children shouting",35 "14": "Screaming",36 "15": "Whispering",37 "16": "Laughter",38 "17": "Baby laughter",39 "18": "Giggle",40 "19": "Snicker",41 "20": "Belly laugh",42 "21": "Chuckle",43 "22": "Crying",44 "23": "Baby cry",45 "24": "Whimper",46 "25": "Wail",47 "26": "Sigh",48 "27": "Singing",49 "28": "Choir",50 "29": "Yodeling",51 "30": "Chant",52 "31": "Mantra",53 "32": "Male singing",54 "33": "Female singing",55 "34": "Child singing",56 "35": "Synthetic singing",57 "36": "Rapping",58 "37": "Humming",59 "38": "Groan",60 "39": "Grunt",61 "40": "Whistling",62 "41": "Breathing",63 "42": "Wheeze",64 "43": "Snoring",65 "44": "Gasp",66 "45": "Pant",67 "46": "Snort",68 "47": "Cough",69 "48": "Throat clearing",70 "49": "Sneeze",71 "50": "Sniff",72 "51": "Run",73 "52": "Shuffle",74 "53": "Walk",75 "54": "Chewing",76 "55": "Biting",77 "56": "Gargling",78 "57": "Stomach rumble",79 "58": "Burping",80 "59": "Hiccup",81 "60": "Fart",82 "61": "Hands",83 "62": "Finger snapping",84 "63": "Clapping",85 "64": "Heart sounds",86 "65": "Heart murmur",87 "66": "Cheering",88 "67": "Applause",89 "68": "Chatter",90 "69": "Crowd",91 "70": "Hubbub",92 "71": "Children playing",93 "72": "Animal",94 "73": "Domestic animals",95 "74": "Dog",96 "75": "Bark",97 "76": "Yip",98 "77": "Howl",99 "78": "Bow-wow",100 "79": "Growling",101 "80": "Whimper (dog)",102 "81": "Cat",103 "82": "Purr",104 "83": "Meow",105 "84": "Hiss",106 "85": "Caterwaul",107 "86": "Livestock",108 "87": "Horse",109 "88": "Clip-clop",110 "89": "Neigh",111 "90": "Cattle",112 "91": "Moo",113 "92": "Cowbell",114 "93": "Pig",115 "94": "Oink",116 "95": "Goat",117 "96": "Bleat",118 "97": "Sheep",119 "98": "Fowl",120 "99": "Chicken",121 "100": "Cluck",122 "101": "Crowing",123 "102": "Turkey",124 "103": "Gobble",125 "104": "Duck",126 "105": "Quack",127 "106": "Goose",128 "107": "Honk",129 "108": "Wild animals",130 "109": "Roaring cats (lions",131 "110": "Roar",132 "111": "Bird",133 "112": "Bird vocalization",134 "113": "Chirp",135 "114": "Squawk",136 "115": "Pigeon",137 "116": "Coo",138 "117": "Crow",139 "118": "Caw",140 "119": "Owl",141 "120": "Hoot",142 "121": "Bird flight",143 "122": "Canidae",144 "123": "Rodents",145 "124": "Mouse",146 "125": "Patter",147 "126": "Insect",148 "127": "Cricket",149 "128": "Mosquito",150 "129": "Fly",151 "130": "Buzz",152 "131": "Bee",153 "132": "Frog",154 "133": "Croak",155 "134": "Snake",156 "135": "Rattle",157 "136": "Whale vocalization",158 "137": "Music",159 "138": "Musical instrument",160 "139": "Plucked string instrument",161 "140": "Guitar",162 "141": "Electric guitar",163 "142": "Bass guitar",164 "143": "Acoustic guitar",165 "144": "Steel guitar",166 "145": "Tapping (guitar technique)",167 "146": "Strum",168 "147": "Banjo",169 "148": "Sitar",170 "149": "Mandolin",171 "150": "Zither",172 "151": "Ukulele",173 "152": "Keyboard (musical)",174 "153": "Piano",175 "154": "Electric piano",176 "155": "Organ",177 "156": "Electronic organ",178 "157": "Hammond organ",179 "158": "Synthesizer",180 "159": "Sampler",181 "160": "Harpsichord",182 "161": "Percussion",183 "162": "Drum kit",184 "163": "Drum machine",185 "164": "Drum",186 "165": "Snare drum",187 "166": "Rimshot",188 "167": "Drum roll",189 "168": "Bass drum",190 "169": "Timpani",191 "170": "Tabla",192 "171": "Cymbal",193 "172": "Hi-hat",194 "173": "Wood block",195 "174": "Tambourine",196 "175": "Rattle (instrument)",197 "176": "Maraca",198 "177": "Gong",199 "178": "Tubular bells",200 "179": "Mallet percussion",201 "180": "Marimba",202 "181": "Glockenspiel",203 "182": "Vibraphone",204 "183": "Steelpan",205 "184": "Orchestra",206 "185": "Brass instrument",207 "186": "French horn",208 "187": "Trumpet",209 "188": "Trombone",210 "189": "Bowed string instrument",211 "190": "String section",212 "191": "Violin",213 "192": "Pizzicato",214 "193": "Cello",215 "194": "Double bass",216 "195": "Wind instrument",217 "196": "Flute",218 "197": "Saxophone",219 "198": "Clarinet",220 "199": "Harp",221 "200": "Bell",222 "201": "Church bell",223 "202": "Jingle bell",224 "203": "Bicycle bell",225 "204": "Tuning fork",226 "205": "Chime",227 "206": "Wind chime",228 "207": "Change ringing (campanology)",229 "208": "Harmonica",230 "209": "Accordion",231 "210": "Bagpipes",232 "211": "Didgeridoo",233 "212": "Shofar",234 "213": "Theremin",235 "214": "Singing bowl",236 "215": "Scratching (performance technique)",237 "216": "Pop music",238 "217": "Hip hop music",239 "218": "Beatboxing",240 "219": "Rock music",241 "220": "Heavy metal",242 "221": "Punk rock",243 "222": "Grunge",244 "223": "Progressive rock",245 "224": "Rock and roll",246 "225": "Psychedelic rock",247 "226": "Rhythm and blues",248 "227": "Soul music",249 "228": "Reggae",250 "229": "Country",251 "230": "Swing music",252 "231": "Bluegrass",253 "232": "Funk",254 "233": "Folk music",255 "234": "Middle Eastern music",256 "235": "Jazz",257 "236": "Disco",258 "237": "Classical music",259 "238": "Opera",260 "239": "Electronic music",261 "240": "House music",262 "241": "Techno",263 "242": "Dubstep",264 "243": "Drum and bass",265 "244": "Electronica",266 "245": "Electronic dance music",267 "246": "Ambient music",268 "247": "Trance music",269 "248": "Music of Latin America",270 "249": "Salsa music",271 "250": "Flamenco",272 "251": "Blues",273 "252": "Music for children",274 "253": "New-age music",275 "254": "Vocal music",276 "255": "A capella",277 "256": "Music of Africa",278 "257": "Afrobeat",279 "258": "Christian music",280 "259": "Gospel music",281 "260": "Music of Asia",282 "261": "Carnatic music",283 "262": "Music of Bollywood",284 "263": "Ska",285 "264": "Traditional music",286 "265": "Independent music",287 "266": "Song",288 "267": "Background music",289 "268": "Theme music",290 "269": "Jingle (music)",291 "270": "Soundtrack music",292 "271": "Lullaby",293 "272": "Video game music",294 "273": "Christmas music",295 "274": "Dance music",296 "275": "Wedding music",297 "276": "Happy music",298 "277": "Funny music",299 "278": "Sad music",300 "279": "Tender music",301 "280": "Exciting music",302 "281": "Angry music",303 "282": "Scary music",304 "283": "Wind",305 "284": "Rustling leaves",306 "285": "Wind noise (microphone)",307 "286": "Thunderstorm",308 "287": "Thunder",309 "288": "Water",310 "289": "Rain",311 "290": "Raindrop",312 "291": "Rain on surface",313 "292": "Stream",314 "293": "Waterfall",315 "294": "Ocean",316 "295": "Waves",317 "296": "Steam",318 "297": "Gurgling",319 "298": "Fire",320 "299": "Crackle",321 "300": "Vehicle",322 "301": "Boat",323 "302": "Sailboat",324 "303": "Rowboat",325 "304": "Motorboat",326 "305": "Ship",327 "306": "Motor vehicle (road)",328 "307": "Car",329 "308": "Vehicle horn",330 "309": "Toot",331 "310": "Car alarm",332 "311": "Power windows",333 "312": "Skidding",334 "313": "Tire squeal",335 "314": "Car passing by",336 "315": "Race car",337 "316": "Truck",338 "317": "Air brake",339 "318": "Air horn",340 "319": "Reversing beeps",341 "320": "Ice cream truck",342 "321": "Bus",343 "322": "Emergency vehicle",344 "323": "Police car (siren)",345 "324": "Ambulance (siren)",346 "325": "Fire engine",347 "326": "Motorcycle",348 "327": "Traffic noise",349 "328": "Rail transport",350 "329": "Train",351 "330": "Train whistle",352 "331": "Train horn",353 "332": "Railroad car",354 "333": "Train wheels squealing",355 "334": "Subway",356 "335": "Aircraft",357 "336": "Aircraft engine",358 "337": "Jet engine",359 "338": "Propeller",360 "339": "Helicopter",361 "340": "Fixed-wing aircraft",362 "341": "Bicycle",363 "342": "Skateboard",364 "343": "Engine",365 "344": "Light engine (high frequency)",366 "345": "Dental drill",367 "346": "Lawn mower",368 "347": "Chainsaw",369 "348": "Medium engine (mid frequency)",370 "349": "Heavy engine (low frequency)",371 "350": "Engine knocking",372 "351": "Engine starting",373 "352": "Idling",374 "353": "Accelerating",375 "354": "Door",376 "355": "Doorbell",377 "356": "Ding-dong",378 "357": "Sliding door",379 "358": "Slam",380 "359": "Knock",381 "360": "Tap",382 "361": "Squeak",383 "362": "Cupboard open or close",384 "363": "Drawer open or close",385 "364": "Dishes",386 "365": "Cutlery",387 "366": "Chopping (food)",388 "367": "Frying (food)",389 "368": "Microwave oven",390 "369": "Blender",391 "370": "Water tap",392 "371": "Sink (filling or washing)",393 "372": "Bathtub (filling or washing)",394 "373": "Hair dryer",395 "374": "Toilet flush",396 "375": "Toothbrush",397 "376": "Electric toothbrush",398 "377": "Vacuum cleaner",399 "378": "Zipper (clothing)",400 "379": "Keys jangling",401 "380": "Coin (dropping)",402 "381": "Scissors",403 "382": "Electric shaver",404 "383": "Shuffling cards",405 "384": "Typing",406 "385": "Typewriter",407 "386": "Computer keyboard",408 "387": "Writing",409 "388": "Alarm",410 "389": "Telephone",411 "390": "Telephone bell ringing",412 "391": "Ringtone",413 "392": "Telephone dialing",414 "393": "Dial tone",415 "394": "Busy signal",416 "395": "Alarm clock",417 "396": "Siren",418 "397": "Civil defense siren",419 "398": "Buzzer",420 "399": "Smoke detector",421 "400": "Fire alarm",422 "401": "Foghorn",423 "402": "Whistle",424 "403": "Steam whistle",425 "404": "Mechanisms",426 "405": "Ratchet",427 "406": "Clock",428 "407": "Tick",429 "408": "Tick-tock",430 "409": "Gears",431 "410": "Pulleys",432 "411": "Sewing machine",433 "412": "Mechanical fan",434 "413": "Air conditioning",435 "414": "Cash register",436 "415": "Printer",437 "416": "Camera",438 "417": "Single-lens reflex camera",439 "418": "Tools",440 "419": "Hammer",441 "420": "Jackhammer",442 "421": "Sawing",443 "422": "Filing (rasp)",444 "423": "Sanding",445 "424": "Power tool",446 "425": "Drill",447 "426": "Explosion",448 "427": "Gunshot",449 "428": "Machine gun",450 "429": "Fusillade",451 "430": "Artillery fire",452 "431": "Cap gun",453 "432": "Fireworks",454 "433": "Firecracker",455 "434": "Burst",456 "435": "Eruption",457 "436": "Boom",458 "437": "Wood",459 "438": "Chop",460 "439": "Splinter",461 "440": "Crack",462 "441": "Glass",463 "442": "Chink",464 "443": "Shatter",465 "444": "Liquid",466 "445": "Splash",467 "446": "Slosh",468 "447": "Squish",469 "448": "Drip",470 "449": "Pour",471 "450": "Trickle",472 "451": "Gush",473 "452": "Fill (with liquid)",474 "453": "Spray",475 "454": "Pump (liquid)",476 "455": "Stir",477 "456": "Boiling",478 "457": "Sonar",479 "458": "Arrow",480 "459": "Whoosh",481 "460": "Thump",482 "461": "Thunk",483 "462": "Electronic tuner",484 "463": "Effects unit",485 "464": "Chorus effect",486 "465": "Basketball bounce",487 "466": "Bang",488 "467": "Slap",489 "468": "Whack",490 "469": "Smash",491 "470": "Breaking",492 "471": "Bouncing",493 "472": "Whip",494 "473": "Flap",495 "474": "Scratch",496 "475": "Scrape",497 "476": "Rub",498 "477": "Roll",499 "478": "Crushing",500 "479": "Crumpling",501 "480": "Tearing",502 "481": "Beep",503 "482": "Ping",504 "483": "Ding",505 "484": "Clang",506 "485": "Squeal",507 "486": "Creak",508 "487": "Rustle",509 "488": "Whir",510 "489": "Clatter",511 "490": "Sizzle",512 "491": "Clicking",513 "492": "Clickety-clack",514 "493": "Rumble",515 "494": "Plop",516 "495": "Jingle",517 "496": "Hum",518 "497": "Zing",519 "498": "Boing",520 "499": "Crunch",521 "500": "Silence",522 "501": "Sine wave",523 "502": "Harmonic",524 "503": "Chirp tone",525 "504": "Sound effect",526 "505": "Pulse",527 "506": "Inside",528 "507": "Inside",529 "508": "Inside",530 "509": "Outside",531 "510": "Outside",532 "511": "Reverberation",533 "512": "Echo",534 "513": "Noise",535 "514": "Environmental noise",536 "515": "Static",537 "516": "Mains hum",538 "517": "Distortion",539 "518": "Sidetone",540 "519": "Cacophony",541 "520": "White noise",542 "521": "Pink noise",543 "522": "Throbbing",544 "523": "Vibration",545 "524": "Television",546 "525": "Radio",547 "526": "Field recording"548 },549 "label2id": {550 "A capella": 255,551 "Accelerating": 353,552 "Accordion": 209,553 "Acoustic guitar": 143,554 "Afrobeat": 257,555 "Air brake": 317,556 "Air conditioning": 413,557 "Air horn": 318,558 "Aircraft": 335,559 "Aircraft engine": 336,560 "Alarm": 388,561 "Alarm clock": 395,562 "Ambient music": 246,563 "Ambulance (siren)": 324,564 "Angry music": 281,565 "Animal": 72,566 "Applause": 67,567 "Arrow": 458,568 "Artillery fire": 430,569 "Babbling": 6,570 "Baby cry": 23,571 "Baby laughter": 17,572 "Background music": 267,573 "Bagpipes": 210,574 "Bang": 466,575 "Banjo": 147,576 "Bark": 75,577 "Basketball bounce": 465,578 "Bass drum": 168,579 "Bass guitar": 142,580 "Bathtub (filling or washing)": 372,581 "Battle cry": 12,582 "Beatboxing": 218,583 "Bee": 131,584 "Beep": 481,585 "Bell": 200,586 "Bellow": 9,587 "Belly laugh": 20,588 "Bicycle": 341,589 "Bicycle bell": 203,590 "Bird": 111,591 "Bird flight": 121,592 "Bird vocalization": 112,593 "Biting": 55,594 "Bleat": 96,595 "Blender": 369,596 "Bluegrass": 231,597 "Blues": 251,598 "Boat": 301,599 "Boiling": 456,600 "Boing": 498,601 "Boom": 436,602 "Bouncing": 471,603 "Bow-wow": 78,604 "Bowed string instrument": 189,605 "Brass instrument": 185,606 "Breaking": 470,607 "Breathing": 41,608 "Burping": 58,609 "Burst": 434,610 "Bus": 321,611 "Busy signal": 394,612 "Buzz": 130,613 "Buzzer": 398,614 "Cacophony": 519,615 "Camera": 416,616 "Canidae": 122,617 "Cap gun": 431,618 "Car": 307,619 "Car alarm": 310,620 "Car passing by": 314,621 "Carnatic music": 261,622 "Cash register": 414,623 "Cat": 81,624 "Caterwaul": 85,625 "Cattle": 90,626 "Caw": 118,627 "Cello": 193,628 "Chainsaw": 347,629 "Change ringing (campanology)": 207,630 "Chant": 30,631 "Chatter": 68,632 "Cheering": 66,633 "Chewing": 54,634 "Chicken": 99,635 "Child singing": 34,636 "Child speech": 3,637 "Children playing": 71,638 "Children shouting": 13,639 "Chime": 205,640 "Chink": 442,641 "Chirp": 113,642 "Chirp tone": 503,643 "Choir": 28,644 "Chop": 438,645 "Chopping (food)": 366,646 "Chorus effect": 464,647 "Christian music": 258,648 "Christmas music": 273,649 "Chuckle": 21,650 "Church bell": 201,651 "Civil defense siren": 397,652 "Clang": 484,653 "Clapping": 63,654 "Clarinet": 198,655 "Classical music": 237,656 "Clatter": 489,657 "Clickety-clack": 492,658 "Clicking": 491,659 "Clip-clop": 88,660 "Clock": 406,661 "Cluck": 100,662 "Coin (dropping)": 380,663 "Computer keyboard": 386,664 "Conversation": 4,665 "Coo": 116,666 "Cough": 47,667 "Country": 229,668 "Cowbell": 92,669 "Crack": 440,670 "Crackle": 299,671 "Creak": 486,672 "Cricket": 127,673 "Croak": 133,674 "Crow": 117,675 "Crowd": 69,676 "Crowing": 101,677 "Crumpling": 479,678 "Crunch": 499,679 "Crushing": 478,680 "Crying": 22,681 "Cupboard open or close": 362,682 "Cutlery": 365,683 "Cymbal": 171,684 "Dance music": 274,685 "Dental drill": 345,686 "Dial tone": 393,687 "Didgeridoo": 211,688 "Ding": 483,689 "Ding-dong": 356,690 "Disco": 236,691 "Dishes": 364,692 "Distortion": 517,693 "Dog": 74,694 "Domestic animals": 73,695 "Door": 354,696 "Doorbell": 355,697 "Double bass": 194,698 "Drawer open or close": 363,699 "Drill": 425,700 "Drip": 448,701 "Drum": 164,702 "Drum and bass": 243,703 "Drum kit": 162,704 "Drum machine": 163,705 "Drum roll": 167,706 "Dubstep": 242,707 "Duck": 104,708 "Echo": 512,709 "Effects unit": 463,710 "Electric guitar": 141,711 "Electric piano": 154,712 "Electric shaver": 382,713 "Electric toothbrush": 376,714 "Electronic dance music": 245,715 "Electronic music": 239,716 "Electronic organ": 156,717 "Electronic tuner": 462,718 "Electronica": 244,719 "Emergency vehicle": 322,720 "Engine": 343,721 "Engine knocking": 350,722 "Engine starting": 351,723 "Environmental noise": 514,724 "Eruption": 435,725 "Exciting music": 280,726 "Explosion": 426,727 "Fart": 60,728 "Female singing": 33,729 "Female speech": 2,730 "Field recording": 526,731 "Filing (rasp)": 422,732 "Fill (with liquid)": 452,733 "Finger snapping": 62,734 "Fire": 298,735 "Fire alarm": 400,736 "Fire engine": 325,737 "Firecracker": 433,738 "Fireworks": 432,739 "Fixed-wing aircraft": 340,740 "Flamenco": 250,741 "Flap": 473,742 "Flute": 196,743 "Fly": 129,744 "Foghorn": 401,745 "Folk music": 233,746 "Fowl": 98,747 "French horn": 186,748 "Frog": 132,749 "Frying (food)": 367,750 "Funk": 232,751 "Funny music": 277,752 "Fusillade": 429,753 "Gargling": 56,754 "Gasp": 44,755 "Gears": 409,756 "Giggle": 18,757 "Glass": 441,758 "Glockenspiel": 181,759 "Goat": 95,760 "Gobble": 103,761 "Gong": 177,762 "Goose": 106,763 "Gospel music": 259,764 "Groan": 38,765 "Growling": 79,766 "Grunge": 222,767 "Grunt": 39,768 "Guitar": 140,769 "Gunshot": 427,770 "Gurgling": 297,771 "Gush": 451,772 "Hair dryer": 373,773 "Hammer": 419,774 "Hammond organ": 157,775 "Hands": 61,776 "Happy music": 276,777 "Harmonic": 502,778 "Harmonica": 208,779 "Harp": 199,780 "Harpsichord": 160,781 "Heart murmur": 65,782 "Heart sounds": 64,783 "Heavy engine (low frequency)": 349,784 "Heavy metal": 220,785 "Helicopter": 339,786 "Hi-hat": 172,787 "Hiccup": 59,788 "Hip hop music": 217,789 "Hiss": 84,790 "Honk": 107,791 "Hoot": 120,792 "Horse": 87,793 "House music": 240,794 "Howl": 77,795 "Hubbub": 70,796 "Hum": 496,797 "Humming": 37,798 "Ice cream truck": 320,799 "Idling": 352,800 "Independent music": 265,801 "Insect": 126,802 "Inside": 508,803 "Jackhammer": 420,804 "Jazz": 235,805 "Jet engine": 337,806 "Jingle": 495,807 "Jingle (music)": 269,808 "Jingle bell": 202,809 "Keyboard (musical)": 152,810 "Keys jangling": 379,811 "Knock": 359,812 "Laughter": 16,813 "Lawn mower": 346,814 "Light engine (high frequency)": 344,815 "Liquid": 444,816 "Livestock": 86,817 "Lullaby": 271,818 "Machine gun": 428,819 "Mains hum": 516,820 "Male singing": 32,821 "Male speech": 1,822 "Mallet percussion": 179,823 "Mandolin": 149,824 "Mantra": 31,825 "Maraca": 176,826 "Marimba": 180,827 "Mechanical fan": 412,828 "Mechanisms": 404,829 "Medium engine (mid frequency)": 348,830 "Meow": 83,831 "Microwave oven": 368,832 "Middle Eastern music": 234,833 "Moo": 91,834 "Mosquito": 128,835 "Motor vehicle (road)": 306,836 "Motorboat": 304,837 "Motorcycle": 326,838 "Mouse": 124,839 "Music": 137,840 "Music for children": 252,841 "Music of Africa": 256,842 "Music of Asia": 260,843 "Music of Bollywood": 262,844 "Music of Latin America": 248,845 "Musical instrument": 138,846 "Narration": 5,847 "Neigh": 89,848 "New-age music": 253,849 "Noise": 513,850 "Ocean": 294,851 "Oink": 94,852 "Opera": 238,853 "Orchestra": 184,854 "Organ": 155,855 "Outside": 510,856 "Owl": 119,857 "Pant": 45,858 "Patter": 125,859 "Percussion": 161,860 "Piano": 153,861 "Pig": 93,862 "Pigeon": 115,863 "Ping": 482,864 "Pink noise": 521,865 "Pizzicato": 192,866 "Plop": 494,867 "Plucked string instrument": 139,868 "Police car (siren)": 323,869 "Pop music": 216,870 "Pour": 449,871 "Power tool": 424,872 "Power windows": 311,873 "Printer": 415,874 "Progressive rock": 223,875 "Propeller": 338,876 "Psychedelic rock": 225,877 "Pulleys": 410,878 "Pulse": 505,879 "Pump (liquid)": 454,880 "Punk rock": 221,881 "Purr": 82,882 "Quack": 105,883 "Race car": 315,884 "Radio": 525,885 "Rail transport": 328,886 "Railroad car": 332,887 "Rain": 289,888 "Rain on surface": 291,889 "Raindrop": 290,890 "Rapping": 36,891 "Ratchet": 405,892 "Rattle": 135,893 "Rattle (instrument)": 175,894 "Reggae": 228,895 "Reverberation": 511,896 "Reversing beeps": 319,897 "Rhythm and blues": 226,898 "Rimshot": 166,899 "Ringtone": 391,900 "Roar": 110,901 "Roaring cats (lions": 109,902 "Rock and roll": 224,903 "Rock music": 219,904 "Rodents": 123,905 "Roll": 477,906 "Rowboat": 303,907 "Rub": 476,908 "Rumble": 493,909 "Run": 51,910 "Rustle": 487,911 "Rustling leaves": 284,912 "Sad music": 278,913 "Sailboat": 302,914 "Salsa music": 249,915 "Sampler": 159,916 "Sanding": 423,917 "Sawing": 421,918 "Saxophone": 197,919 "Scary music": 282,920 "Scissors": 381,921 "Scrape": 475,922 "Scratch": 474,923 "Scratching (performance technique)": 215,924 "Screaming": 14,925 "Sewing machine": 411,926 "Shatter": 443,927 "Sheep": 97,928 "Ship": 305,929 "Shofar": 212,930 "Shout": 8,931 "Shuffle": 52,932 "Shuffling cards": 383,933 "Sidetone": 518,934 "Sigh": 26,935 "Silence": 500,936 "Sine wave": 501,937 "Singing": 27,938 "Singing bowl": 214,939 "Single-lens reflex camera": 417,940 "Sink (filling or washing)": 371,941 "Siren": 396,942 "Sitar": 148,943 "Sizzle": 490,944 "Ska": 263,945 "Skateboard": 342,946 "Skidding": 312,947 "Slam": 358,948 "Slap": 467,949 "Sliding door": 357,950 "Slosh": 446,951 "Smash": 469,952 "Smoke detector": 399,953 "Snake": 134,954 "Snare drum": 165,955 "Sneeze": 49,956 "Snicker": 19,957 "Sniff": 50,958 "Snoring": 43,959 "Snort": 46,960 "Sonar": 457,961 "Song": 266,962 "Soul music": 227,963 "Sound effect": 504,964 "Soundtrack music": 270,965 "Speech": 0,966 "Speech synthesizer": 7,967 "Splash": 445,968 "Splinter": 439,969 "Spray": 453,970 "Squawk": 114,971 "Squeak": 361,972 "Squeal": 485,973 "Squish": 447,974 "Static": 515,975 "Steam": 296,976 "Steam whistle": 403,977 "Steel guitar": 144,978 "Steelpan": 183,979 "Stir": 455,980 "Stomach rumble": 57,981 "Stream": 292,982 "String section": 190,983 "Strum": 146,984 "Subway": 334,985 "Swing music": 230,986 "Synthesizer": 158,987 "Synthetic singing": 35,988 "Tabla": 170,989 "Tambourine": 174,990 "Tap": 360,991 "Tapping (guitar technique)": 145,992 "Tearing": 480,993 "Techno": 241,994 "Telephone": 389,995 "Telephone bell ringing": 390,996 "Telephone dialing": 392,997 "Television": 524,998 "Tender music": 279,999 "Theme music": 268,1000 "Theremin": 213,1001 "Throat clearing": 48,1002 "Throbbing": 522,1003 "Thump": 460,1004 "Thunder": 287,1005 "Thunderstorm": 286,1006 "Thunk": 461,1007 "Tick": 407,1008 "Tick-tock": 408,1009 "Timpani": 169,1010 "Tire squeal": 313,1011 "Toilet flush": 374,1012 "Tools": 418,1013 "Toot": 309,1014 "Toothbrush": 375,1015 "Traditional music": 264,1016 "Traffic noise": 327,1017 "Train": 329,1018 "Train horn": 331,1019 "Train wheels squealing": 333,1020 "Train whistle": 330,1021 "Trance music": 247,1022 "Trickle": 450,1023 "Trombone": 188,1024 "Truck": 316,1025 "Trumpet": 187,1026 "Tubular bells": 178,1027 "Tuning fork": 204,1028 "Turkey": 102,1029 "Typewriter": 385,1030 "Typing": 384,1031 "Ukulele": 151,1032 "Vacuum cleaner": 377,1033 "Vehicle": 300,1034 "Vehicle horn": 308,1035 "Vibraphone": 182,1036 "Vibration": 523,1037 "Video game music": 272,1038 "Violin": 191,1039 "Vocal music": 254,1040 "Wail": 25,1041 "Walk": 53,1042 "Water": 288,1043 "Water tap": 370,1044 "Waterfall": 293,1045 "Waves": 295,1046 "Wedding music": 275,1047 "Whack": 468,1048 "Whale vocalization": 136,1049 "Wheeze": 42,1050 "Whimper": 24,1051 "Whimper (dog)": 80,1052 "Whip": 472,1053 "Whir": 488,1054 "Whispering": 15,1055 "Whistle": 402,1056 "Whistling": 40,1057 "White noise": 520,1058 "Whoop": 10,1059 "Whoosh": 459,1060 "Wild animals": 108,1061 "Wind": 283,1062 "Wind chime": 206,1063 "Wind instrument": 195,1064 "Wind noise (microphone)": 285,1065 "Wood": 437,1066 "Wood block": 173,1067 "Writing": 387,1068 "Yell": 11,1069 "Yip": 76,1070 "Yodeling": 29,1071 "Zing": 497,1072 "Zipper (clothing)": 378,1073 "Zither": 1501074 },1075 "mlp_ratio": 4.0,1076 "model_type": "ced",1077 "n_fft": 512,1078 "n_mels": 64,1079 "name": "ced-mini",1080 "num_heads": 4,1081 "outputdim": 527,1082 "pad_last": true,1083 "patch_size": 16,1084 "patch_stride": 16,1085 "pooling": "mean",1086 "qkv_bias": true,1087 "target_length": 1012,1088 "torch_dtype": "float32",1089 "transformers_version": "4.35.2",1090 "win_size": 5121091}1092 