Hugging Face's logo

aongwachi
/
amity-diarization-v00

Transformers
TensorBoard
Safetensors
pyannet
speaker-diarization
speaker-segmentation
Generated from Trainer
Model card Files
xet
Metrics Community
aongwachi commited on
Commit
090e454
·
verified ·
1 Parent(s): 2cfe2ca

End of training

Browse files
Files changed (2) hide show
  1. README.md +31 -31
  2. model.safetensors +1 -1
README.md CHANGED
@@ -20,12 +20,12 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [pyannote/segmentation-3.0](https://huggingface.co/pyannote/segmentation-3.0) on the amitysolution/sample-voice-dataset dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.3149
24
- - Model Preparation Time: 0.0044
25
- - Der: 0.1367
26
- - False Alarm: 0.0655
27
- - Missed Detection: 0.0627
28
- - Confusion: 0.0085
29
 
30
  ## Model description
31
 
@@ -44,7 +44,7 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 0.001
48
  - train_batch_size: 32
49
  - eval_batch_size: 32
50
  - seed: 42
@@ -56,30 +56,30 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der | False Alarm | Missed Detection | Confusion |
58
  |:-------------:|:-------:|:----:|:---------------:|:----------------------:|:------:|:-----------:|:----------------:|:---------:|
59
- | 0.4401 | 0.6173 | 300 | 0.3711 | 0.0044 | 0.1735 | 0.0887 | 0.0689 | 0.0159 |
60
- | 0.314 | 1.2346 | 600 | 0.3535 | 0.0044 | 0.1616 | 0.0841 | 0.0639 | 0.0136 |
61
- | 0.2954 | 1.8519 | 900 | 0.3437 | 0.0044 | 0.1595 | 0.0811 | 0.0689 | 0.0095 |
62
- | 0.2761 | 2.4691 | 1200 | 0.3453 | 0.0044 | 0.1568 | 0.0754 | 0.0722 | 0.0091 |
63
- | 0.2572 | 3.0864 | 1500 | 0.3363 | 0.0044 | 0.1539 | 0.0645 | 0.0810 | 0.0084 |
64
- | 0.24 | 3.7037 | 1800 | 0.3319 | 0.0044 | 0.1553 | 0.0683 | 0.0753 | 0.0117 |
65
- | 0.2395 | 4.3210 | 2100 | 0.3399 | 0.0044 | 0.1537 | 0.0722 | 0.0732 | 0.0083 |
66
- | 0.234 | 4.9383 | 2400 | 0.3272 | 0.0044 | 0.1526 | 0.0748 | 0.0668 | 0.0110 |
67
- | 0.2202 | 5.5556 | 2700 | 0.3349 | 0.0044 | 0.1468 | 0.0696 | 0.0694 | 0.0078 |
68
- | 0.212 | 6.1728 | 3000 | 0.3239 | 0.0044 | 0.1417 | 0.0665 | 0.0681 | 0.0071 |
69
- | 0.2077 | 6.7901 | 3300 | 0.3298 | 0.0044 | 0.1411 | 0.0665 | 0.0652 | 0.0094 |
70
- | 0.1971 | 7.4074 | 3600 | 0.3266 | 0.0044 | 0.1397 | 0.0622 | 0.0684 | 0.0091 |
71
- | 0.2034 | 8.0247 | 3900 | 0.3134 | 0.0044 | 0.1440 | 0.0622 | 0.0727 | 0.0091 |
72
- | 0.1965 | 8.6420 | 4200 | 0.3188 | 0.0044 | 0.1448 | 0.0713 | 0.0633 | 0.0102 |
73
- | 0.1922 | 9.2593 | 4500 | 0.3129 | 0.0044 | 0.1401 | 0.0699 | 0.0608 | 0.0094 |
74
- | 0.1885 | 9.8765 | 4800 | 0.3173 | 0.0044 | 0.1384 | 0.0700 | 0.0588 | 0.0096 |
75
- | 0.1835 | 10.4938 | 5100 | 0.3127 | 0.0044 | 0.1368 | 0.0649 | 0.0626 | 0.0093 |
76
- | 0.1841 | 11.1111 | 5400 | 0.3163 | 0.0044 | 0.1400 | 0.0655 | 0.0651 | 0.0094 |
77
- | 0.1769 | 11.7284 | 5700 | 0.3162 | 0.0044 | 0.1391 | 0.0650 | 0.0650 | 0.0092 |
78
- | 0.1773 | 12.3457 | 6000 | 0.3116 | 0.0044 | 0.1358 | 0.0642 | 0.0630 | 0.0085 |
79
- | 0.1745 | 12.9630 | 6300 | 0.3160 | 0.0044 | 0.1371 | 0.0655 | 0.0633 | 0.0083 |
80
- | 0.1743 | 13.5802 | 6600 | 0.3165 | 0.0044 | 0.1377 | 0.0665 | 0.0627 | 0.0085 |
81
- | 0.1772 | 14.1975 | 6900 | 0.3135 | 0.0044 | 0.1365 | 0.0655 | 0.0627 | 0.0083 |
82
- | 0.1731 | 14.8148 | 7200 | 0.3149 | 0.0044 | 0.1367 | 0.0655 | 0.0627 | 0.0085 |
83
 
84
 
85
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [pyannote/segmentation-3.0](https://huggingface.co/pyannote/segmentation-3.0) on the amitysolution/sample-voice-dataset dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.3859
24
+ - Model Preparation Time: 0.0036
25
+ - Der: 0.1703
26
+ - False Alarm: 0.0833
27
+ - Missed Detection: 0.0724
28
+ - Confusion: 0.0147
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 0.0001
48
  - train_batch_size: 32
49
  - eval_batch_size: 32
50
  - seed: 42
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der | False Alarm | Missed Detection | Confusion |
58
  |:-------------:|:-------:|:----:|:---------------:|:----------------------:|:------:|:-----------:|:----------------:|:---------:|
59
+ | 0.7173 | 0.6173 | 300 | 0.5827 | 0.0036 | 0.2729 | 0.0856 | 0.1579 | 0.0294 |
60
+ | 0.5741 | 1.2346 | 600 | 0.5245 | 0.0036 | 0.2527 | 0.0797 | 0.1465 | 0.0266 |
61
+ | 0.5122 | 1.8519 | 900 | 0.4829 | 0.0036 | 0.2298 | 0.0889 | 0.1161 | 0.0249 |
62
+ | 0.4546 | 2.4691 | 1200 | 0.4643 | 0.0036 | 0.2139 | 0.0874 | 0.1055 | 0.0211 |
63
+ | 0.4272 | 3.0864 | 1500 | 0.4459 | 0.0036 | 0.1997 | 0.0854 | 0.0943 | 0.0201 |
64
+ | 0.4063 | 3.7037 | 1800 | 0.4342 | 0.0036 | 0.1958 | 0.0870 | 0.0900 | 0.0189 |
65
+ | 0.3894 | 4.3210 | 2100 | 0.4303 | 0.0036 | 0.1911 | 0.0861 | 0.0871 | 0.0179 |
66
+ | 0.3806 | 4.9383 | 2400 | 0.4134 | 0.0036 | 0.1853 | 0.0936 | 0.0749 | 0.0168 |
67
+ | 0.3639 | 5.5556 | 2700 | 0.4033 | 0.0036 | 0.1815 | 0.0899 | 0.0751 | 0.0165 |
68
+ | 0.3576 | 6.1728 | 3000 | 0.4122 | 0.0036 | 0.1829 | 0.0879 | 0.0785 | 0.0164 |
69
+ | 0.3449 | 6.7901 | 3300 | 0.3998 | 0.0036 | 0.1792 | 0.0872 | 0.0762 | 0.0157 |
70
+ | 0.3458 | 7.4074 | 3600 | 0.4015 | 0.0036 | 0.1764 | 0.0823 | 0.0791 | 0.0150 |
71
+ | 0.3329 | 8.0247 | 3900 | 0.3985 | 0.0036 | 0.1742 | 0.0850 | 0.0740 | 0.0152 |
72
+ | 0.3287 | 8.6420 | 4200 | 0.3949 | 0.0036 | 0.1741 | 0.0855 | 0.0731 | 0.0155 |
73
+ | 0.331 | 9.2593 | 4500 | 0.3868 | 0.0036 | 0.1724 | 0.0871 | 0.0697 | 0.0156 |
74
+ | 0.3257 | 9.8765 | 4800 | 0.3903 | 0.0036 | 0.1711 | 0.0840 | 0.0719 | 0.0152 |
75
+ | 0.321 | 10.4938 | 5100 | 0.3865 | 0.0036 | 0.1701 | 0.0835 | 0.0718 | 0.0148 |
76
+ | 0.3224 | 11.1111 | 5400 | 0.3841 | 0.0036 | 0.1704 | 0.0838 | 0.0722 | 0.0143 |
77
+ | 0.3085 | 11.7284 | 5700 | 0.3876 | 0.0036 | 0.1711 | 0.0838 | 0.0723 | 0.0149 |
78
+ | 0.3157 | 12.3457 | 6000 | 0.3868 | 0.0036 | 0.1708 | 0.0839 | 0.0721 | 0.0148 |
79
+ | 0.3215 | 12.9630 | 6300 | 0.3840 | 0.0036 | 0.1702 | 0.0838 | 0.0720 | 0.0145 |
80
+ | 0.3141 | 13.5802 | 6600 | 0.3830 | 0.0036 | 0.1701 | 0.0832 | 0.0725 | 0.0144 |
81
+ | 0.3084 | 14.1975 | 6900 | 0.3845 | 0.0036 | 0.1704 | 0.0833 | 0.0724 | 0.0147 |
82
+ | 0.3176 | 14.8148 | 7200 | 0.3859 | 0.0036 | 0.1703 | 0.0833 | 0.0724 | 0.0147 |
83
 
84
 
85
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed6c6bfc08431c0391ffe98d65d5c93143ec0b4673c47ab2332148e37dc258b5
3
  size 5899124
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aa03a3dce615b4e49c6a5509b07480e8e5fbb944c3610e38bc5ff66b8279905
3
  size 5899124