Hugging Face's logo

ArtFair
/
fine_tuned_segmentation-3.0_1e-3_32

TensorBoard
Safetensors
pyannet
speaker-diarization
speaker-segmentation
Generated from Trainer
Model card Files Metrics Community
hsethu commited on
Commit
b76456e
•
1 Parent(s): c9c10b8

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -10
  2. model.safetensors +1 -1
  3. runs/Sep20_22-38-22_ip-172-31-27-176.us-west-2.compute.internal/events.out.tfevents.1726872443.ip-172-31-27-176.us-west-2.compute.internal.29748.0 +2 -2
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [pyannote/segmentation-3.0](https://huggingface.co/pyannote/segmentation-3.0) on the ArtFair/diarizers_dataset_70-15-15 default dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.3946
23
- - Der: 0.2838
24
- - False Alarm: 0.1527
25
- - Missed Detection: 0.1039
26
- - Confusion: 0.0272
27
 
28
  ## Model description
29
 
@@ -54,11 +54,11 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Der | False Alarm | Missed Detection | Confusion |
56
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-----------:|:----------------:|:---------:|
57
- | 0.4087 | 1.0 | 747 | 0.4294 | 0.3215 | 0.1936 | 0.0951 | 0.0328 |
58
- | 0.369 | 2.0 | 1494 | 0.4232 | 0.3133 | 0.1932 | 0.0914 | 0.0287 |
59
- | 0.3403 | 3.0 | 2241 | 0.3954 | 0.2912 | 0.1689 | 0.0956 | 0.0267 |
60
- | 0.325 | 4.0 | 2988 | 0.3948 | 0.2843 | 0.1502 | 0.1076 | 0.0265 |
61
- | 0.3242 | 5.0 | 3735 | 0.3946 | 0.2838 | 0.1527 | 0.1039 | 0.0272 |
62
 
63
 
64
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [pyannote/segmentation-3.0](https://huggingface.co/pyannote/segmentation-3.0) on the ArtFair/diarizers_dataset_70-15-15 default dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.3590
23
+ - Der: 0.2602
24
+ - False Alarm: 0.1497
25
+ - Missed Detection: 0.0864
26
+ - Confusion: 0.0241
27
 
28
  ## Model description
29
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Der | False Alarm | Missed Detection | Confusion |
56
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-----------:|:----------------:|:---------:|
57
+ | 0.392 | 1.0 | 929 | 0.3807 | 0.2790 | 0.1647 | 0.0865 | 0.0278 |
58
+ | 0.3543 | 2.0 | 1858 | 0.3680 | 0.2685 | 0.1530 | 0.0889 | 0.0266 |
59
+ | 0.3494 | 3.0 | 2787 | 0.3526 | 0.2567 | 0.1427 | 0.0901 | 0.0238 |
60
+ | 0.3287 | 4.0 | 3716 | 0.3592 | 0.2605 | 0.1496 | 0.0869 | 0.0240 |
61
+ | 0.3339 | 5.0 | 4645 | 0.3590 | 0.2602 | 0.1497 | 0.0864 | 0.0241 |
62
 
63
 
64
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a438d33cc7e7d29f704b488051ca50548d789d37f158bd1369a6e675839a277
3
  size 497684
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e92f0631cb06002db4ca00f0e256e5ac61b8908567e8320903b1e5060a9b613d
3
  size 497684
runs/Sep20_22-38-22_ip-172-31-27-176.us-west-2.compute.internal/events.out.tfevents.1726872443.ip-172-31-27-176.us-west-2.compute.internal.29748.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff0725473b2851d903645259400c4fc8a486ce97da6256054d80436438079c4b
3
- size 12245
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f954f2fa9f162081b32122f069d3c72df94322569c990b3c3d7839b81f575be3
3
+ size 14498