Hugging Face's logo

objects76
/
full-ja4-2.25sec-big-rf-250513_1713

Transformers
Safetensors
pyannet
speaker-diarization
speaker-segmentation
Generated from Trainer
Model card Files
xet
 Community
objects76 commited on
Commit
41288f5
·
verified ·
1 Parent(s): 1155e6d

End of training

Browse files
Files changed (4) hide show
  1. README.md +147 -0
  2. config.json +22 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: pyannote/segmentation-3.0
5
+ tags:
6
+ - speaker-diarization
7
+ - speaker-segmentation
8
+ - generated_from_trainer
9
+ datasets:
10
+ - objects76/synthetic-ja4-speaker-overlap-6400
11
+ model-index:
12
+ - name: full-ja4-2.25sec-big-rf
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # full-ja4-2.25sec-big-rf
20
+
21
+ This model is a fine-tuned version of [pyannote/segmentation-3.0](https://huggingface.co/pyannote/segmentation-3.0) on the objects76/synthetic-ja4-speaker-overlap-6400 dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.4183
24
+ - Der: 0.1253
25
+ - False Alarm: 0.0559
26
+ - Missed Detection: 0.0520
27
+ - Confusion: 0.0175
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 0.001
47
+ - train_batch_size: 2048
48
+ - eval_batch_size: 2048
49
+ - seed: 42
50
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
+ - lr_scheduler_type: cosine
52
+ - num_epochs: 200
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Confusion | Der | False Alarm | Validation Loss | Missed Detection |
57
+ |:-------------:|:-----:|:----:|:---------:|:------:|:-----------:|:---------------:|:----------------:|
58
+ | No log | 1.0 | 7 | 0.0594 | 0.2999 | 0.1200 | 0.9837 | 0.1206 |
59
+ | No log | 2.0 | 14 | 0.0651 | 0.2710 | 0.0724 | 0.8711 | 0.1335 |
60
+ | No log | 3.0 | 21 | 0.0775 | 0.2659 | 0.0140 | 0.8192 | 0.1744 |
61
+ | 0.9138 | 4.0 | 28 | 0.0714 | 0.2422 | 0.0283 | 0.7813 | 0.1425 |
62
+ | 0.9138 | 5.0 | 35 | 0.0569 | 0.2231 | 0.0685 | 0.7536 | 0.0977 |
63
+ | 0.9138 | 6.0 | 42 | 0.0564 | 0.2136 | 0.0681 | 0.7049 | 0.0891 |
64
+ | 0.9138 | 7.0 | 49 | 0.0509 | 0.2050 | 0.0815 | 0.6687 | 0.0726 |
65
+ | 0.7407 | 8.0 | 56 | 0.0470 | 0.2004 | 0.0872 | 0.6428 | 0.0661 |
66
+ | 0.7407 | 9.0 | 63 | 0.0459 | 0.1950 | 0.0827 | 0.6224 | 0.0664 |
67
+ | 0.7407 | 10.0 | 70 | 0.0430 | 0.1915 | 0.0874 | 0.6045 | 0.0611 |
68
+ | 0.6308 | 11.0 | 77 | 0.0418 | 0.1877 | 0.0839 | 0.5877 | 0.0620 |
69
+ | 0.6308 | 12.0 | 84 | 0.0391 | 0.1828 | 0.0812 | 0.5714 | 0.0625 |
70
+ | 0.6308 | 13.0 | 91 | 0.0356 | 0.1771 | 0.0820 | 0.5571 | 0.0595 |
71
+ | 0.6308 | 14.0 | 98 | 0.0335 | 0.1698 | 0.0755 | 0.5410 | 0.0608 |
72
+ | 0.5637 | 15.0 | 105 | 0.0310 | 0.1642 | 0.0753 | 0.5294 | 0.0579 |
73
+ | 0.5637 | 16.0 | 112 | 0.0293 | 0.1588 | 0.0691 | 0.5173 | 0.0604 |
74
+ | 0.5637 | 17.0 | 119 | 0.0278 | 0.1551 | 0.0687 | 0.5070 | 0.0586 |
75
+ | 0.5103 | 18.0 | 126 | 0.0279 | 0.1517 | 0.0634 | 0.4972 | 0.0604 |
76
+ | 0.5103 | 19.0 | 133 | 0.0272 | 0.1493 | 0.0625 | 0.4876 | 0.0596 |
77
+ | 0.5103 | 20.0 | 140 | 0.0264 | 0.1490 | 0.0643 | 0.4819 | 0.0583 |
78
+ | 0.5103 | 21.0 | 147 | 0.0260 | 0.1471 | 0.0605 | 0.4732 | 0.0606 |
79
+ | 0.4692 | 22.0 | 154 | 0.0251 | 0.1453 | 0.0607 | 0.4689 | 0.0595 |
80
+ | 0.4692 | 23.0 | 161 | 0.0250 | 0.1435 | 0.0601 | 0.4639 | 0.0584 |
81
+ | 0.4692 | 24.0 | 168 | 0.0238 | 0.1417 | 0.0622 | 0.4591 | 0.0556 |
82
+ | 0.4454 | 25.0 | 175 | 0.0241 | 0.1406 | 0.0571 | 0.4529 | 0.0594 |
83
+ | 0.4454 | 26.0 | 182 | 0.0234 | 0.1404 | 0.0612 | 0.4527 | 0.0558 |
84
+ | 0.4454 | 27.0 | 189 | 0.0229 | 0.1392 | 0.0560 | 0.4459 | 0.0602 |
85
+ | 0.4454 | 28.0 | 196 | 0.0217 | 0.1388 | 0.0634 | 0.4473 | 0.0536 |
86
+ | 0.423 | 29.0 | 203 | 0.0223 | 0.1375 | 0.0580 | 0.4434 | 0.0572 |
87
+ | 0.423 | 30.0 | 210 | 0.0225 | 0.1368 | 0.0564 | 0.4398 | 0.0579 |
88
+ | 0.423 | 31.0 | 217 | 0.0215 | 0.1361 | 0.0599 | 0.4379 | 0.0547 |
89
+ | 0.423 | 32.0 | 224 | 0.0220 | 0.1350 | 0.0553 | 0.4340 | 0.0578 |
90
+ | 0.3906 | 33.0 | 231 | 0.0216 | 0.1352 | 0.0561 | 0.4334 | 0.0575 |
91
+ | 0.3906 | 34.0 | 238 | 0.0211 | 0.1353 | 0.0602 | 0.4348 | 0.0541 |
92
+ | 0.3906 | 35.0 | 245 | 0.0211 | 0.1326 | 0.0551 | 0.4274 | 0.0565 |
93
+ | 0.3918 | 36.0 | 252 | 0.0214 | 0.1336 | 0.0577 | 0.4280 | 0.0545 |
94
+ | 0.3918 | 37.0 | 259 | 0.0220 | 0.1328 | 0.0545 | 0.4297 | 0.0562 |
95
+ | 0.3918 | 38.0 | 266 | 0.0220 | 0.1333 | 0.0572 | 0.4315 | 0.0541 |
96
+ | 0.3918 | 39.0 | 273 | 0.0220 | 0.1324 | 0.0533 | 0.4287 | 0.0571 |
97
+ | 0.3811 | 40.0 | 280 | 0.0202 | 0.1310 | 0.0577 | 0.4222 | 0.0531 |
98
+ | 0.3811 | 41.0 | 287 | 0.0202 | 0.1298 | 0.0540 | 0.4178 | 0.0556 |
99
+ | 0.3811 | 42.0 | 294 | 0.0201 | 0.1296 | 0.0545 | 0.4218 | 0.0549 |
100
+ | 0.3707 | 43.0 | 301 | 0.0189 | 0.1280 | 0.0535 | 0.4176 | 0.0556 |
101
+ | 0.3707 | 44.0 | 308 | 0.0189 | 0.1287 | 0.0556 | 0.4156 | 0.0542 |
102
+ | 0.3707 | 45.0 | 315 | 0.0192 | 0.1267 | 0.0524 | 0.4142 | 0.0551 |
103
+ | 0.3707 | 46.0 | 322 | 0.0188 | 0.1269 | 0.0529 | 0.4141 | 0.0552 |
104
+ | 0.3636 | 47.0 | 329 | 0.0190 | 0.1283 | 0.0571 | 0.4188 | 0.0522 |
105
+ | 0.3636 | 48.0 | 336 | 0.0191 | 0.1264 | 0.0503 | 0.4129 | 0.0569 |
106
+ | 0.3636 | 49.0 | 343 | 0.0182 | 0.1276 | 0.0574 | 0.4167 | 0.0520 |
107
+ | 0.354 | 50.0 | 350 | 0.0191 | 0.1264 | 0.0511 | 0.4141 | 0.0562 |
108
+ | 0.354 | 51.0 | 357 | 0.0184 | 0.1264 | 0.0555 | 0.4132 | 0.0526 |
109
+ | 0.354 | 52.0 | 364 | 0.0193 | 0.1265 | 0.0510 | 0.4137 | 0.0562 |
110
+ | 0.354 | 53.0 | 371 | 0.0187 | 0.1267 | 0.0560 | 0.4153 | 0.0520 |
111
+ | 0.3411 | 54.0 | 378 | 0.0182 | 0.1255 | 0.0540 | 0.4133 | 0.0534 |
112
+ | 0.3411 | 55.0 | 385 | 0.0187 | 0.1251 | 0.0515 | 0.4143 | 0.0549 |
113
+ | 0.3411 | 56.0 | 392 | 0.0186 | 0.1254 | 0.0544 | 0.4136 | 0.0524 |
114
+ | 0.3411 | 57.0 | 399 | 0.0189 | 0.1253 | 0.0526 | 0.4118 | 0.0538 |
115
+ | 0.3413 | 58.0 | 406 | 0.0187 | 0.1259 | 0.0532 | 0.4134 | 0.0541 |
116
+ | 0.3413 | 59.0 | 413 | 0.0184 | 0.1255 | 0.0529 | 0.4137 | 0.0542 |
117
+ | 0.3413 | 60.0 | 420 | 0.0186 | 0.1243 | 0.0509 | 0.4119 | 0.0547 |
118
+ | 0.3381 | 61.0 | 427 | 0.0183 | 0.1249 | 0.0532 | 0.4117 | 0.0534 |
119
+ | 0.3381 | 62.0 | 434 | 0.0184 | 0.1258 | 0.0504 | 0.4092 | 0.0570 |
120
+ | 0.3381 | 63.0 | 441 | 0.0177 | 0.1254 | 0.0548 | 0.4122 | 0.0529 |
121
+ | 0.3381 | 64.0 | 448 | 0.0190 | 0.1253 | 0.0502 | 0.4121 | 0.0560 |
122
+ | 0.3351 | 65.0 | 455 | 0.0172 | 0.1255 | 0.0572 | 0.4131 | 0.0511 |
123
+ | 0.3351 | 66.0 | 462 | 0.0173 | 0.1241 | 0.0516 | 0.4094 | 0.0551 |
124
+ | 0.3351 | 67.0 | 469 | 0.0172 | 0.1246 | 0.0549 | 0.4123 | 0.0525 |
125
+ | 0.3296 | 68.0 | 476 | 0.0173 | 0.1243 | 0.0533 | 0.4107 | 0.0536 |
126
+ | 0.3296 | 69.0 | 483 | 0.0177 | 0.1233 | 0.0504 | 0.4096 | 0.0552 |
127
+ | 0.3296 | 70.0 | 490 | 0.0181 | 0.1250 | 0.0518 | 0.4126 | 0.0552 |
128
+ | 0.3296 | 71.0 | 497 | 0.0181 | 0.1248 | 0.0509 | 0.4127 | 0.0558 |
129
+ | 0.3242 | 72.0 | 504 | 0.0177 | 0.1244 | 0.0536 | 0.4142 | 0.0531 |
130
+ | 0.3242 | 73.0 | 511 | 0.4129 | 0.1250 | 0.0512 | 0.0555 | 0.0183 |
131
+ | 0.3242 | 74.0 | 518 | 0.4162 | 0.1264 | 0.0552 | 0.0528 | 0.0184 |
132
+ | 0.3197 | 75.0 | 525 | 0.4124 | 0.1248 | 0.0505 | 0.0553 | 0.0190 |
133
+ | 0.3197 | 76.0 | 532 | 0.4137 | 0.1245 | 0.0551 | 0.0517 | 0.0177 |
134
+ | 0.3197 | 77.0 | 539 | 0.4107 | 0.1232 | 0.0517 | 0.0547 | 0.0168 |
135
+ | 0.3197 | 78.0 | 546 | 0.4109 | 0.1240 | 0.0527 | 0.0541 | 0.0172 |
136
+ | 0.314 | 79.0 | 553 | 0.4105 | 0.1230 | 0.0529 | 0.0539 | 0.0162 |
137
+ | 0.314 | 80.0 | 560 | 0.4115 | 0.1242 | 0.0527 | 0.0539 | 0.0176 |
138
+ | 0.314 | 81.0 | 567 | 0.4133 | 0.1237 | 0.0503 | 0.0563 | 0.0172 |
139
+ | 0.314 | 82.0 | 574 | 0.4183 | 0.1253 | 0.0559 | 0.0520 | 0.0175 |
140
+
141
+
142
+ ### Framework versions
143
+
144
+ - Transformers 4.51.3
145
+ - Pytorch 2.6.0+cu124
146
+ - Datasets 3.5.0
147
+ - Tokenizers 0.21.1
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SegmentationModel"
4
+ ],
5
+ "chunk_duration": 2.25,
6
+ "max_speakers_per_chunk": 2,
7
+ "max_speakers_per_frame": 2,
8
+ "min_duration": null,
9
+ "model_type": "pyannet",
10
+ "sample_rate": 16000,
11
+ "sincnet": {
12
+ "ksize": 321,
13
+ "stride": 56
14
+ },
15
+ "torch_dtype": "float32",
16
+ "transformers_version": "4.51.3",
17
+ "warm_up": [
18
+ 0.0,
19
+ 0.0
20
+ ],
21
+ "weigh_by_cardinality": false
22
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf244cec937a8477d9aaf0ba7d6aa82063c1ee24c5e1c18b67cf8f3eaaa9a191
3
+ size 5898016
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55b8abb3da494eb075476bb672598b795dd79937575402610b96798268b31bb3
3
+ size 5368