mirari commited on
Commit
c8567bb
·
verified ·
1 Parent(s): 48c5c66

End of training

Browse files
Files changed (2) hide show
  1. README.md +72 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ language:
4
+ - spa
5
+ license: mit
6
+ base_model: pyannote/speaker-diarization-3.1
7
+ tags:
8
+ - speaker-diarization
9
+ - speaker-segmentation
10
+ - generated_from_trainer
11
+ datasets:
12
+ - diarizers-community/callhome
13
+ model-index:
14
+ - name: speaker-segmentation-fine-tuned-callhome-spa
15
+ results: []
16
+ ---
17
+
18
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
19
+ should probably proofread and complete it, then remove this comment. -->
20
+
21
+ # speaker-segmentation-fine-tuned-callhome-spa
22
+
23
+ This model is a fine-tuned version of [pyannote/speaker-diarization-3.1](https://huggingface.co/pyannote/speaker-diarization-3.1) on the diarizers-community/callhome dataset.
24
+ It achieves the following results on the evaluation set:
25
+ - Loss: 0.5595
26
+ - Der: 0.2894
27
+ - False Alarm: 0.2353
28
+ - Missed Detection: 0.0536
29
+ - Confusion: 0.0005
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 0.001
49
+ - train_batch_size: 64
50
+ - eval_batch_size: 64
51
+ - seed: 42
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: cosine
54
+ - num_epochs: 5
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Der | False Alarm | Missed Detection | Confusion |
59
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:-----------:|:----------------:|:---------:|
60
+ | 0.3614 | 1.0 | 226 | 0.4962 | 0.2910 | 0.2389 | 0.0520 | 0.0001 |
61
+ | 0.3465 | 2.0 | 452 | 0.5067 | 0.2860 | 0.2179 | 0.0679 | 0.0002 |
62
+ | 0.3325 | 3.0 | 678 | 0.5343 | 0.2941 | 0.2300 | 0.0636 | 0.0005 |
63
+ | 0.3189 | 4.0 | 904 | 0.5613 | 0.2906 | 0.2380 | 0.0522 | 0.0004 |
64
+ | 0.3238 | 5.0 | 1130 | 0.5595 | 0.2894 | 0.2353 | 0.0536 | 0.0005 |
65
+
66
+
67
+ ### Framework versions
68
+
69
+ - Transformers 4.45.1
70
+ - Pytorch 2.4.1
71
+ - Datasets 3.0.1
72
+ - Tokenizers 0.20.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19d3f12249f504a162e52eb0717019f2fe4b02df448fe1e5f5079824f9627a39
3
  size 5899124
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:222c34726f6d568731c64c9a7c8133d70dd817e7ee54efedc8e6b3705305cb80
3
  size 5899124