RSNuts commited on
Commit
7557af0
1 Parent(s): 5141a65

Upload 6 files

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ uss_material/harry_potter.flac filter=lfs diff=lfs merge=lfs -text
uss_material/class_labels_indices.csv ADDED
@@ -0,0 +1,528 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ index,mid,display_name
2
+ 0,/m/09x0r,"Speech"
3
+ 1,/m/05zppz,"Male speech, man speaking"
4
+ 2,/m/02zsn,"Female speech, woman speaking"
5
+ 3,/m/0ytgt,"Child speech, kid speaking"
6
+ 4,/m/01h8n0,"Conversation"
7
+ 5,/m/02qldy,"Narration, monologue"
8
+ 6,/m/0261r1,"Babbling"
9
+ 7,/m/0brhx,"Speech synthesizer"
10
+ 8,/m/07p6fty,"Shout"
11
+ 9,/m/07q4ntr,"Bellow"
12
+ 10,/m/07rwj3x,"Whoop"
13
+ 11,/m/07sr1lc,"Yell"
14
+ 12,/m/04gy_2,"Battle cry"
15
+ 13,/t/dd00135,"Children shouting"
16
+ 14,/m/03qc9zr,"Screaming"
17
+ 15,/m/02rtxlg,"Whispering"
18
+ 16,/m/01j3sz,"Laughter"
19
+ 17,/t/dd00001,"Baby laughter"
20
+ 18,/m/07r660_,"Giggle"
21
+ 19,/m/07s04w4,"Snicker"
22
+ 20,/m/07sq110,"Belly laugh"
23
+ 21,/m/07rgt08,"Chuckle, chortle"
24
+ 22,/m/0463cq4,"Crying, sobbing"
25
+ 23,/t/dd00002,"Baby cry, infant cry"
26
+ 24,/m/07qz6j3,"Whimper"
27
+ 25,/m/07qw_06,"Wail, moan"
28
+ 26,/m/07plz5l,"Sigh"
29
+ 27,/m/015lz1,"Singing"
30
+ 28,/m/0l14jd,"Choir"
31
+ 29,/m/01swy6,"Yodeling"
32
+ 30,/m/02bk07,"Chant"
33
+ 31,/m/01c194,"Mantra"
34
+ 32,/t/dd00003,"Male singing"
35
+ 33,/t/dd00004,"Female singing"
36
+ 34,/t/dd00005,"Child singing"
37
+ 35,/t/dd00006,"Synthetic singing"
38
+ 36,/m/06bxc,"Rapping"
39
+ 37,/m/02fxyj,"Humming"
40
+ 38,/m/07s2xch,"Groan"
41
+ 39,/m/07r4k75,"Grunt"
42
+ 40,/m/01w250,"Whistling"
43
+ 41,/m/0lyf6,"Breathing"
44
+ 42,/m/07mzm6,"Wheeze"
45
+ 43,/m/01d3sd,"Snoring"
46
+ 44,/m/07s0dtb,"Gasp"
47
+ 45,/m/07pyy8b,"Pant"
48
+ 46,/m/07q0yl5,"Snort"
49
+ 47,/m/01b_21,"Cough"
50
+ 48,/m/0dl9sf8,"Throat clearing"
51
+ 49,/m/01hsr_,"Sneeze"
52
+ 50,/m/07ppn3j,"Sniff"
53
+ 51,/m/06h7j,"Run"
54
+ 52,/m/07qv_x_,"Shuffle"
55
+ 53,/m/07pbtc8,"Walk, footsteps"
56
+ 54,/m/03cczk,"Chewing, mastication"
57
+ 55,/m/07pdhp0,"Biting"
58
+ 56,/m/0939n_,"Gargling"
59
+ 57,/m/01g90h,"Stomach rumble"
60
+ 58,/m/03q5_w,"Burping, eructation"
61
+ 59,/m/02p3nc,"Hiccup"
62
+ 60,/m/02_nn,"Fart"
63
+ 61,/m/0k65p,"Hands"
64
+ 62,/m/025_jnm,"Finger snapping"
65
+ 63,/m/0l15bq,"Clapping"
66
+ 64,/m/01jg02,"Heart sounds, heartbeat"
67
+ 65,/m/01jg1z,"Heart murmur"
68
+ 66,/m/053hz1,"Cheering"
69
+ 67,/m/028ght,"Applause"
70
+ 68,/m/07rkbfh,"Chatter"
71
+ 69,/m/03qtwd,"Crowd"
72
+ 70,/m/07qfr4h,"Hubbub, speech noise, speech babble"
73
+ 71,/t/dd00013,"Children playing"
74
+ 72,/m/0jbk,"Animal"
75
+ 73,/m/068hy,"Domestic animals, pets"
76
+ 74,/m/0bt9lr,"Dog"
77
+ 75,/m/05tny_,"Bark"
78
+ 76,/m/07r_k2n,"Yip"
79
+ 77,/m/07qf0zm,"Howl"
80
+ 78,/m/07rc7d9,"Bow-wow"
81
+ 79,/m/0ghcn6,"Growling"
82
+ 80,/t/dd00136,"Whimper (dog)"
83
+ 81,/m/01yrx,"Cat"
84
+ 82,/m/02yds9,"Purr"
85
+ 83,/m/07qrkrw,"Meow"
86
+ 84,/m/07rjwbb,"Hiss"
87
+ 85,/m/07r81j2,"Caterwaul"
88
+ 86,/m/0ch8v,"Livestock, farm animals, working animals"
89
+ 87,/m/03k3r,"Horse"
90
+ 88,/m/07rv9rh,"Clip-clop"
91
+ 89,/m/07q5rw0,"Neigh, whinny"
92
+ 90,/m/01xq0k1,"Cattle, bovinae"
93
+ 91,/m/07rpkh9,"Moo"
94
+ 92,/m/0239kh,"Cowbell"
95
+ 93,/m/068zj,"Pig"
96
+ 94,/t/dd00018,"Oink"
97
+ 95,/m/03fwl,"Goat"
98
+ 96,/m/07q0h5t,"Bleat"
99
+ 97,/m/07bgp,"Sheep"
100
+ 98,/m/025rv6n,"Fowl"
101
+ 99,/m/09b5t,"Chicken, rooster"
102
+ 100,/m/07st89h,"Cluck"
103
+ 101,/m/07qn5dc,"Crowing, cock-a-doodle-doo"
104
+ 102,/m/01rd7k,"Turkey"
105
+ 103,/m/07svc2k,"Gobble"
106
+ 104,/m/09ddx,"Duck"
107
+ 105,/m/07qdb04,"Quack"
108
+ 106,/m/0dbvp,"Goose"
109
+ 107,/m/07qwf61,"Honk"
110
+ 108,/m/01280g,"Wild animals"
111
+ 109,/m/0cdnk,"Roaring cats (lions, tigers)"
112
+ 110,/m/04cvmfc,"Roar"
113
+ 111,/m/015p6,"Bird"
114
+ 112,/m/020bb7,"Bird vocalization, bird call, bird song"
115
+ 113,/m/07pggtn,"Chirp, tweet"
116
+ 114,/m/07sx8x_,"Squawk"
117
+ 115,/m/0h0rv,"Pigeon, dove"
118
+ 116,/m/07r_25d,"Coo"
119
+ 117,/m/04s8yn,"Crow"
120
+ 118,/m/07r5c2p,"Caw"
121
+ 119,/m/09d5_,"Owl"
122
+ 120,/m/07r_80w,"Hoot"
123
+ 121,/m/05_wcq,"Bird flight, flapping wings"
124
+ 122,/m/01z5f,"Canidae, dogs, wolves"
125
+ 123,/m/06hps,"Rodents, rats, mice"
126
+ 124,/m/04rmv,"Mouse"
127
+ 125,/m/07r4gkf,"Patter"
128
+ 126,/m/03vt0,"Insect"
129
+ 127,/m/09xqv,"Cricket"
130
+ 128,/m/09f96,"Mosquito"
131
+ 129,/m/0h2mp,"Fly, housefly"
132
+ 130,/m/07pjwq1,"Buzz"
133
+ 131,/m/01h3n,"Bee, wasp, etc."
134
+ 132,/m/09ld4,"Frog"
135
+ 133,/m/07st88b,"Croak"
136
+ 134,/m/078jl,"Snake"
137
+ 135,/m/07qn4z3,"Rattle"
138
+ 136,/m/032n05,"Whale vocalization"
139
+ 137,/m/04rlf,"Music"
140
+ 138,/m/04szw,"Musical instrument"
141
+ 139,/m/0fx80y,"Plucked string instrument"
142
+ 140,/m/0342h,"Guitar"
143
+ 141,/m/02sgy,"Electric guitar"
144
+ 142,/m/018vs,"Bass guitar"
145
+ 143,/m/042v_gx,"Acoustic guitar"
146
+ 144,/m/06w87,"Steel guitar, slide guitar"
147
+ 145,/m/01glhc,"Tapping (guitar technique)"
148
+ 146,/m/07s0s5r,"Strum"
149
+ 147,/m/018j2,"Banjo"
150
+ 148,/m/0jtg0,"Sitar"
151
+ 149,/m/04rzd,"Mandolin"
152
+ 150,/m/01bns_,"Zither"
153
+ 151,/m/07xzm,"Ukulele"
154
+ 152,/m/05148p4,"Keyboard (musical)"
155
+ 153,/m/05r5c,"Piano"
156
+ 154,/m/01s0ps,"Electric piano"
157
+ 155,/m/013y1f,"Organ"
158
+ 156,/m/03xq_f,"Electronic organ"
159
+ 157,/m/03gvt,"Hammond organ"
160
+ 158,/m/0l14qv,"Synthesizer"
161
+ 159,/m/01v1d8,"Sampler"
162
+ 160,/m/03q5t,"Harpsichord"
163
+ 161,/m/0l14md,"Percussion"
164
+ 162,/m/02hnl,"Drum kit"
165
+ 163,/m/0cfdd,"Drum machine"
166
+ 164,/m/026t6,"Drum"
167
+ 165,/m/06rvn,"Snare drum"
168
+ 166,/m/03t3fj,"Rimshot"
169
+ 167,/m/02k_mr,"Drum roll"
170
+ 168,/m/0bm02,"Bass drum"
171
+ 169,/m/011k_j,"Timpani"
172
+ 170,/m/01p970,"Tabla"
173
+ 171,/m/01qbl,"Cymbal"
174
+ 172,/m/03qtq,"Hi-hat"
175
+ 173,/m/01sm1g,"Wood block"
176
+ 174,/m/07brj,"Tambourine"
177
+ 175,/m/05r5wn,"Rattle (instrument)"
178
+ 176,/m/0xzly,"Maraca"
179
+ 177,/m/0mbct,"Gong"
180
+ 178,/m/016622,"Tubular bells"
181
+ 179,/m/0j45pbj,"Mallet percussion"
182
+ 180,/m/0dwsp,"Marimba, xylophone"
183
+ 181,/m/0dwtp,"Glockenspiel"
184
+ 182,/m/0dwt5,"Vibraphone"
185
+ 183,/m/0l156b,"Steelpan"
186
+ 184,/m/05pd6,"Orchestra"
187
+ 185,/m/01kcd,"Brass instrument"
188
+ 186,/m/0319l,"French horn"
189
+ 187,/m/07gql,"Trumpet"
190
+ 188,/m/07c6l,"Trombone"
191
+ 189,/m/0l14_3,"Bowed string instrument"
192
+ 190,/m/02qmj0d,"String section"
193
+ 191,/m/07y_7,"Violin, fiddle"
194
+ 192,/m/0d8_n,"Pizzicato"
195
+ 193,/m/01xqw,"Cello"
196
+ 194,/m/02fsn,"Double bass"
197
+ 195,/m/085jw,"Wind instrument, woodwind instrument"
198
+ 196,/m/0l14j_,"Flute"
199
+ 197,/m/06ncr,"Saxophone"
200
+ 198,/m/01wy6,"Clarinet"
201
+ 199,/m/03m5k,"Harp"
202
+ 200,/m/0395lw,"Bell"
203
+ 201,/m/03w41f,"Church bell"
204
+ 202,/m/027m70_,"Jingle bell"
205
+ 203,/m/0gy1t2s,"Bicycle bell"
206
+ 204,/m/07n_g,"Tuning fork"
207
+ 205,/m/0f8s22,"Chime"
208
+ 206,/m/026fgl,"Wind chime"
209
+ 207,/m/0150b9,"Change ringing (campanology)"
210
+ 208,/m/03qjg,"Harmonica"
211
+ 209,/m/0mkg,"Accordion"
212
+ 210,/m/0192l,"Bagpipes"
213
+ 211,/m/02bxd,"Didgeridoo"
214
+ 212,/m/0l14l2,"Shofar"
215
+ 213,/m/07kc_,"Theremin"
216
+ 214,/m/0l14t7,"Singing bowl"
217
+ 215,/m/01hgjl,"Scratching (performance technique)"
218
+ 216,/m/064t9,"Pop music"
219
+ 217,/m/0glt670,"Hip hop music"
220
+ 218,/m/02cz_7,"Beatboxing"
221
+ 219,/m/06by7,"Rock music"
222
+ 220,/m/03lty,"Heavy metal"
223
+ 221,/m/05r6t,"Punk rock"
224
+ 222,/m/0dls3,"Grunge"
225
+ 223,/m/0dl5d,"Progressive rock"
226
+ 224,/m/07sbbz2,"Rock and roll"
227
+ 225,/m/05w3f,"Psychedelic rock"
228
+ 226,/m/06j6l,"Rhythm and blues"
229
+ 227,/m/0gywn,"Soul music"
230
+ 228,/m/06cqb,"Reggae"
231
+ 229,/m/01lyv,"Country"
232
+ 230,/m/015y_n,"Swing music"
233
+ 231,/m/0gg8l,"Bluegrass"
234
+ 232,/m/02x8m,"Funk"
235
+ 233,/m/02w4v,"Folk music"
236
+ 234,/m/06j64v,"Middle Eastern music"
237
+ 235,/m/03_d0,"Jazz"
238
+ 236,/m/026z9,"Disco"
239
+ 237,/m/0ggq0m,"Classical music"
240
+ 238,/m/05lls,"Opera"
241
+ 239,/m/02lkt,"Electronic music"
242
+ 240,/m/03mb9,"House music"
243
+ 241,/m/07gxw,"Techno"
244
+ 242,/m/07s72n,"Dubstep"
245
+ 243,/m/0283d,"Drum and bass"
246
+ 244,/m/0m0jc,"Electronica"
247
+ 245,/m/08cyft,"Electronic dance music"
248
+ 246,/m/0fd3y,"Ambient music"
249
+ 247,/m/07lnk,"Trance music"
250
+ 248,/m/0g293,"Music of Latin America"
251
+ 249,/m/0ln16,"Salsa music"
252
+ 250,/m/0326g,"Flamenco"
253
+ 251,/m/0155w,"Blues"
254
+ 252,/m/05fw6t,"Music for children"
255
+ 253,/m/02v2lh,"New-age music"
256
+ 254,/m/0y4f8,"Vocal music"
257
+ 255,/m/0z9c,"A capella"
258
+ 256,/m/0164x2,"Music of Africa"
259
+ 257,/m/0145m,"Afrobeat"
260
+ 258,/m/02mscn,"Christian music"
261
+ 259,/m/016cjb,"Gospel music"
262
+ 260,/m/028sqc,"Music of Asia"
263
+ 261,/m/015vgc,"Carnatic music"
264
+ 262,/m/0dq0md,"Music of Bollywood"
265
+ 263,/m/06rqw,"Ska"
266
+ 264,/m/02p0sh1,"Traditional music"
267
+ 265,/m/05rwpb,"Independent music"
268
+ 266,/m/074ft,"Song"
269
+ 267,/m/025td0t,"Background music"
270
+ 268,/m/02cjck,"Theme music"
271
+ 269,/m/03r5q_,"Jingle (music)"
272
+ 270,/m/0l14gg,"Soundtrack music"
273
+ 271,/m/07pkxdp,"Lullaby"
274
+ 272,/m/01z7dr,"Video game music"
275
+ 273,/m/0140xf,"Christmas music"
276
+ 274,/m/0ggx5q,"Dance music"
277
+ 275,/m/04wptg,"Wedding music"
278
+ 276,/t/dd00031,"Happy music"
279
+ 277,/t/dd00032,"Funny music"
280
+ 278,/t/dd00033,"Sad music"
281
+ 279,/t/dd00034,"Tender music"
282
+ 280,/t/dd00035,"Exciting music"
283
+ 281,/t/dd00036,"Angry music"
284
+ 282,/t/dd00037,"Scary music"
285
+ 283,/m/03m9d0z,"Wind"
286
+ 284,/m/09t49,"Rustling leaves"
287
+ 285,/t/dd00092,"Wind noise (microphone)"
288
+ 286,/m/0jb2l,"Thunderstorm"
289
+ 287,/m/0ngt1,"Thunder"
290
+ 288,/m/0838f,"Water"
291
+ 289,/m/06mb1,"Rain"
292
+ 290,/m/07r10fb,"Raindrop"
293
+ 291,/t/dd00038,"Rain on surface"
294
+ 292,/m/0j6m2,"Stream"
295
+ 293,/m/0j2kx,"Waterfall"
296
+ 294,/m/05kq4,"Ocean"
297
+ 295,/m/034srq,"Waves, surf"
298
+ 296,/m/06wzb,"Steam"
299
+ 297,/m/07swgks,"Gurgling"
300
+ 298,/m/02_41,"Fire"
301
+ 299,/m/07pzfmf,"Crackle"
302
+ 300,/m/07yv9,"Vehicle"
303
+ 301,/m/019jd,"Boat, Water vehicle"
304
+ 302,/m/0hsrw,"Sailboat, sailing ship"
305
+ 303,/m/056ks2,"Rowboat, canoe, kayak"
306
+ 304,/m/02rlv9,"Motorboat, speedboat"
307
+ 305,/m/06q74,"Ship"
308
+ 306,/m/012f08,"Motor vehicle (road)"
309
+ 307,/m/0k4j,"Car"
310
+ 308,/m/0912c9,"Vehicle horn, car horn, honking"
311
+ 309,/m/07qv_d5,"Toot"
312
+ 310,/m/02mfyn,"Car alarm"
313
+ 311,/m/04gxbd,"Power windows, electric windows"
314
+ 312,/m/07rknqz,"Skidding"
315
+ 313,/m/0h9mv,"Tire squeal"
316
+ 314,/t/dd00134,"Car passing by"
317
+ 315,/m/0ltv,"Race car, auto racing"
318
+ 316,/m/07r04,"Truck"
319
+ 317,/m/0gvgw0,"Air brake"
320
+ 318,/m/05x_td,"Air horn, truck horn"
321
+ 319,/m/02rhddq,"Reversing beeps"
322
+ 320,/m/03cl9h,"Ice cream truck, ice cream van"
323
+ 321,/m/01bjv,"Bus"
324
+ 322,/m/03j1ly,"Emergency vehicle"
325
+ 323,/m/04qvtq,"Police car (siren)"
326
+ 324,/m/012n7d,"Ambulance (siren)"
327
+ 325,/m/012ndj,"Fire engine, fire truck (siren)"
328
+ 326,/m/04_sv,"Motorcycle"
329
+ 327,/m/0btp2,"Traffic noise, roadway noise"
330
+ 328,/m/06d_3,"Rail transport"
331
+ 329,/m/07jdr,"Train"
332
+ 330,/m/04zmvq,"Train whistle"
333
+ 331,/m/0284vy3,"Train horn"
334
+ 332,/m/01g50p,"Railroad car, train wagon"
335
+ 333,/t/dd00048,"Train wheels squealing"
336
+ 334,/m/0195fx,"Subway, metro, underground"
337
+ 335,/m/0k5j,"Aircraft"
338
+ 336,/m/014yck,"Aircraft engine"
339
+ 337,/m/04229,"Jet engine"
340
+ 338,/m/02l6bg,"Propeller, airscrew"
341
+ 339,/m/09ct_,"Helicopter"
342
+ 340,/m/0cmf2,"Fixed-wing aircraft, airplane"
343
+ 341,/m/0199g,"Bicycle"
344
+ 342,/m/06_fw,"Skateboard"
345
+ 343,/m/02mk9,"Engine"
346
+ 344,/t/dd00065,"Light engine (high frequency)"
347
+ 345,/m/08j51y,"Dental drill, dentist's drill"
348
+ 346,/m/01yg9g,"Lawn mower"
349
+ 347,/m/01j4z9,"Chainsaw"
350
+ 348,/t/dd00066,"Medium engine (mid frequency)"
351
+ 349,/t/dd00067,"Heavy engine (low frequency)"
352
+ 350,/m/01h82_,"Engine knocking"
353
+ 351,/t/dd00130,"Engine starting"
354
+ 352,/m/07pb8fc,"Idling"
355
+ 353,/m/07q2z82,"Accelerating, revving, vroom"
356
+ 354,/m/02dgv,"Door"
357
+ 355,/m/03wwcy,"Doorbell"
358
+ 356,/m/07r67yg,"Ding-dong"
359
+ 357,/m/02y_763,"Sliding door"
360
+ 358,/m/07rjzl8,"Slam"
361
+ 359,/m/07r4wb8,"Knock"
362
+ 360,/m/07qcpgn,"Tap"
363
+ 361,/m/07q6cd_,"Squeak"
364
+ 362,/m/0642b4,"Cupboard open or close"
365
+ 363,/m/0fqfqc,"Drawer open or close"
366
+ 364,/m/04brg2,"Dishes, pots, and pans"
367
+ 365,/m/023pjk,"Cutlery, silverware"
368
+ 366,/m/07pn_8q,"Chopping (food)"
369
+ 367,/m/0dxrf,"Frying (food)"
370
+ 368,/m/0fx9l,"Microwave oven"
371
+ 369,/m/02pjr4,"Blender"
372
+ 370,/m/02jz0l,"Water tap, faucet"
373
+ 371,/m/0130jx,"Sink (filling or washing)"
374
+ 372,/m/03dnzn,"Bathtub (filling or washing)"
375
+ 373,/m/03wvsk,"Hair dryer"
376
+ 374,/m/01jt3m,"Toilet flush"
377
+ 375,/m/012xff,"Toothbrush"
378
+ 376,/m/04fgwm,"Electric toothbrush"
379
+ 377,/m/0d31p,"Vacuum cleaner"
380
+ 378,/m/01s0vc,"Zipper (clothing)"
381
+ 379,/m/03v3yw,"Keys jangling"
382
+ 380,/m/0242l,"Coin (dropping)"
383
+ 381,/m/01lsmm,"Scissors"
384
+ 382,/m/02g901,"Electric shaver, electric razor"
385
+ 383,/m/05rj2,"Shuffling cards"
386
+ 384,/m/0316dw,"Typing"
387
+ 385,/m/0c2wf,"Typewriter"
388
+ 386,/m/01m2v,"Computer keyboard"
389
+ 387,/m/081rb,"Writing"
390
+ 388,/m/07pp_mv,"Alarm"
391
+ 389,/m/07cx4,"Telephone"
392
+ 390,/m/07pp8cl,"Telephone bell ringing"
393
+ 391,/m/01hnzm,"Ringtone"
394
+ 392,/m/02c8p,"Telephone dialing, DTMF"
395
+ 393,/m/015jpf,"Dial tone"
396
+ 394,/m/01z47d,"Busy signal"
397
+ 395,/m/046dlr,"Alarm clock"
398
+ 396,/m/03kmc9,"Siren"
399
+ 397,/m/0dgbq,"Civil defense siren"
400
+ 398,/m/030rvx,"Buzzer"
401
+ 399,/m/01y3hg,"Smoke detector, smoke alarm"
402
+ 400,/m/0c3f7m,"Fire alarm"
403
+ 401,/m/04fq5q,"Foghorn"
404
+ 402,/m/0l156k,"Whistle"
405
+ 403,/m/06hck5,"Steam whistle"
406
+ 404,/t/dd00077,"Mechanisms"
407
+ 405,/m/02bm9n,"Ratchet, pawl"
408
+ 406,/m/01x3z,"Clock"
409
+ 407,/m/07qjznt,"Tick"
410
+ 408,/m/07qjznl,"Tick-tock"
411
+ 409,/m/0l7xg,"Gears"
412
+ 410,/m/05zc1,"Pulleys"
413
+ 411,/m/0llzx,"Sewing machine"
414
+ 412,/m/02x984l,"Mechanical fan"
415
+ 413,/m/025wky1,"Air conditioning"
416
+ 414,/m/024dl,"Cash register"
417
+ 415,/m/01m4t,"Printer"
418
+ 416,/m/0dv5r,"Camera"
419
+ 417,/m/07bjf,"Single-lens reflex camera"
420
+ 418,/m/07k1x,"Tools"
421
+ 419,/m/03l9g,"Hammer"
422
+ 420,/m/03p19w,"Jackhammer"
423
+ 421,/m/01b82r,"Sawing"
424
+ 422,/m/02p01q,"Filing (rasp)"
425
+ 423,/m/023vsd,"Sanding"
426
+ 424,/m/0_ksk,"Power tool"
427
+ 425,/m/01d380,"Drill"
428
+ 426,/m/014zdl,"Explosion"
429
+ 427,/m/032s66,"Gunshot, gunfire"
430
+ 428,/m/04zjc,"Machine gun"
431
+ 429,/m/02z32qm,"Fusillade"
432
+ 430,/m/0_1c,"Artillery fire"
433
+ 431,/m/073cg4,"Cap gun"
434
+ 432,/m/0g6b5,"Fireworks"
435
+ 433,/g/122z_qxw,"Firecracker"
436
+ 434,/m/07qsvvw,"Burst, pop"
437
+ 435,/m/07pxg6y,"Eruption"
438
+ 436,/m/07qqyl4,"Boom"
439
+ 437,/m/083vt,"Wood"
440
+ 438,/m/07pczhz,"Chop"
441
+ 439,/m/07pl1bw,"Splinter"
442
+ 440,/m/07qs1cx,"Crack"
443
+ 441,/m/039jq,"Glass"
444
+ 442,/m/07q7njn,"Chink, clink"
445
+ 443,/m/07rn7sz,"Shatter"
446
+ 444,/m/04k94,"Liquid"
447
+ 445,/m/07rrlb6,"Splash, splatter"
448
+ 446,/m/07p6mqd,"Slosh"
449
+ 447,/m/07qlwh6,"Squish"
450
+ 448,/m/07r5v4s,"Drip"
451
+ 449,/m/07prgkl,"Pour"
452
+ 450,/m/07pqc89,"Trickle, dribble"
453
+ 451,/t/dd00088,"Gush"
454
+ 452,/m/07p7b8y,"Fill (with liquid)"
455
+ 453,/m/07qlf79,"Spray"
456
+ 454,/m/07ptzwd,"Pump (liquid)"
457
+ 455,/m/07ptfmf,"Stir"
458
+ 456,/m/0dv3j,"Boiling"
459
+ 457,/m/0790c,"Sonar"
460
+ 458,/m/0dl83,"Arrow"
461
+ 459,/m/07rqsjt,"Whoosh, swoosh, swish"
462
+ 460,/m/07qnq_y,"Thump, thud"
463
+ 461,/m/07rrh0c,"Thunk"
464
+ 462,/m/0b_fwt,"Electronic tuner"
465
+ 463,/m/02rr_,"Effects unit"
466
+ 464,/m/07m2kt,"Chorus effect"
467
+ 465,/m/018w8,"Basketball bounce"
468
+ 466,/m/07pws3f,"Bang"
469
+ 467,/m/07ryjzk,"Slap, smack"
470
+ 468,/m/07rdhzs,"Whack, thwack"
471
+ 469,/m/07pjjrj,"Smash, crash"
472
+ 470,/m/07pc8lb,"Breaking"
473
+ 471,/m/07pqn27,"Bouncing"
474
+ 472,/m/07rbp7_,"Whip"
475
+ 473,/m/07pyf11,"Flap"
476
+ 474,/m/07qb_dv,"Scratch"
477
+ 475,/m/07qv4k0,"Scrape"
478
+ 476,/m/07pdjhy,"Rub"
479
+ 477,/m/07s8j8t,"Roll"
480
+ 478,/m/07plct2,"Crushing"
481
+ 479,/t/dd00112,"Crumpling, crinkling"
482
+ 480,/m/07qcx4z,"Tearing"
483
+ 481,/m/02fs_r,"Beep, bleep"
484
+ 482,/m/07qwdck,"Ping"
485
+ 483,/m/07phxs1,"Ding"
486
+ 484,/m/07rv4dm,"Clang"
487
+ 485,/m/07s02z0,"Squeal"
488
+ 486,/m/07qh7jl,"Creak"
489
+ 487,/m/07qwyj0,"Rustle"
490
+ 488,/m/07s34ls,"Whir"
491
+ 489,/m/07qmpdm,"Clatter"
492
+ 490,/m/07p9k1k,"Sizzle"
493
+ 491,/m/07qc9xj,"Clicking"
494
+ 492,/m/07rwm0c,"Clickety-clack"
495
+ 493,/m/07phhsh,"Rumble"
496
+ 494,/m/07qyrcz,"Plop"
497
+ 495,/m/07qfgpx,"Jingle, tinkle"
498
+ 496,/m/07rcgpl,"Hum"
499
+ 497,/m/07p78v5,"Zing"
500
+ 498,/t/dd00121,"Boing"
501
+ 499,/m/07s12q4,"Crunch"
502
+ 500,/m/028v0c,"Silence"
503
+ 501,/m/01v_m0,"Sine wave"
504
+ 502,/m/0b9m1,"Harmonic"
505
+ 503,/m/0hdsk,"Chirp tone"
506
+ 504,/m/0c1dj,"Sound effect"
507
+ 505,/m/07pt_g0,"Pulse"
508
+ 506,/t/dd00125,"Inside, small room"
509
+ 507,/t/dd00126,"Inside, large room or hall"
510
+ 508,/t/dd00127,"Inside, public space"
511
+ 509,/t/dd00128,"Outside, urban or manmade"
512
+ 510,/t/dd00129,"Outside, rural or natural"
513
+ 511,/m/01b9nn,"Reverberation"
514
+ 512,/m/01jnbd,"Echo"
515
+ 513,/m/096m7z,"Noise"
516
+ 514,/m/06_y0by,"Environmental noise"
517
+ 515,/m/07rgkc5,"Static"
518
+ 516,/m/06xkwv,"Mains hum"
519
+ 517,/m/0g12c5,"Distortion"
520
+ 518,/m/08p9q4,"Sidetone"
521
+ 519,/m/07szfh9,"Cacophony"
522
+ 520,/m/0chx_,"White noise"
523
+ 521,/m/0cj0r,"Pink noise"
524
+ 522,/m/07p_0gm,"Throbbing"
525
+ 523,/m/01jwx6,"Vibration"
526
+ 524,/m/07c52,"Television"
527
+ 525,/m/06bz3,"Radio"
528
+ 526,/m/07hvw1,"Field recording"
uss_material/harry_potter.flac ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b99948e3fd08fa887b734460601f01350961e1e9678f61d28214da098b443e0
3
+ size 23580774
uss_material/ontology.json ADDED
The diff for this file is too large to render. See raw diff
 
uss_material/queries.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a811dbc8e69de5239ecffec3f3e33e913ead693a676a4381d9503e7fb0dffc9
3
+ size 87844
uss_material/ss_model=resunet30,querynet=at_soft,data=full,devices=8,step=1000000.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ef6b4fddd3c06f7b01693a503a3ca786290b24d48337e649e2163ba43f0ae5
3
+ size 1121024828
uss_material/ss_model=resunet30,querynet=at_soft,data=full.yaml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ task_name: audioset
3
+
4
+ data:
5
+ indexes_dict: "hdf5s/indexes/full_train.h5"
6
+ sampler_type: balanced_sampler
7
+ anchor_segment_detect_mode: max_area # "max_area" | "random"
8
+ sample_rate: 32000
9
+ frames_per_second: 100
10
+ segment_seconds: 2.0
11
+ classes_num: 527
12
+ augmentation:
13
+ match_energy: True
14
+ mix_num: 2
15
+
16
+ sound_event_detection:
17
+ model_type: Cnn14_DecisionLevelMax
18
+ freeze: True
19
+
20
+ query_net:
21
+ model_type: Cnn14_Wrapper # "Cnn14_Wrapper" | "AdaptiveCnn14_Wrapper"
22
+ base_checkpoint_type: "Cnn14"
23
+ freeze_base: True
24
+ freeze_adaptor: False
25
+ bottleneck_type: at_soft # "embedding" | "at_soft"
26
+ outputs_num: 527
27
+
28
+ ss_model:
29
+ model_type: ResUNet30
30
+ input_channels: 1
31
+ output_channels: 1
32
+
33
+ train:
34
+ num_workers: 16
35
+ loss_type: l1_wav
36
+ optimizer:
37
+ optimizer_type: AdamW
38
+ learning_rate: 1e-3
39
+ lr_lambda_type: constant_warm_up # "constant_warm_up" | "linear_warm_up"
40
+ warm_up_steps: 10000
41
+ reduce_lr_steps: 1000000
42
+ batch_size_per_device: 16
43
+ precision: 32
44
+ steps_per_epoch: 10000 # Every 10000 steps is called an epoch
45
+ evaluate_step_frequency: 20000 # Evaluate every #evaluate_step_frequency steps
46
+ save_step_frequency: 100000 # Save every #save_step_frequency steps
47
+ early_stop_steps: 10000001
48
+ random_seed: 1234
49
+ resume_checkpoint_path: ""
50
+
51
+ evaluate:
52
+ balanced_train_eval_dir: "evaluation/audioset/2s_segments_balanced_train"
53
+ test_eval_dir: "evaluation/audioset/2s_segments_test"
54
+ max_eval_per_class: 10
55
+