Hugging Face's logo

Juardo
/
bsc_ai_thesis_torgo_model-1

Audio Classification
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Juardo commited on
Commit
75396f5
•
1 Parent(s): c8b5854

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -16
README.md CHANGED
@@ -6,6 +6,7 @@ metrics:
6
  - accuracy
7
  - precision
8
  - recall
 
9
  model-index:
10
  - name: bsc_ai_thesis_torgo_model-1
11
  results: []
@@ -18,10 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.3445
22
- - Accuracy: 0.8675
23
- - Precision: 0.8670
24
- - Recall: 0.8873
 
25
 
26
  ## Model description
27
 
@@ -53,18 +55,18 @@ The following hyperparameters were used during training:
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall |
57
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|
58
- | 0.6837 | 0.96 | 12 | 0.6315 | 0.695 | 0.6717 | 0.8357 |
59
- | 0.576 | 2.0 | 25 | 0.4980 | 0.7675 | 0.8125 | 0.7324 |
60
- | 0.5089 | 2.96 | 37 | 0.4431 | 0.8125 | 0.8255 | 0.8216 |
61
- | 0.405 | 4.0 | 50 | 0.4718 | 0.8325 | 0.8687 | 0.8075 |
62
- | 0.3436 | 4.96 | 62 | 0.4669 | 0.795 | 0.7331 | 0.9671 |
63
- | 0.318 | 6.0 | 75 | 0.5111 | 0.7225 | 0.6903 | 0.8685 |
64
- | 0.2837 | 6.96 | 87 | 0.5359 | 0.7625 | 0.7783 | 0.7746 |
65
- | 0.2361 | 8.0 | 100 | 0.4633 | 0.805 | 0.8358 | 0.7887 |
66
- | 0.2327 | 8.96 | 112 | 0.3232 | 0.88 | 0.8733 | 0.9061 |
67
- | 0.2036 | 9.6 | 120 | 0.3445 | 0.8675 | 0.8670 | 0.8873 |
68
 
69
 
70
  ### Framework versions
 
6
  - accuracy
7
  - precision
8
  - recall
9
+ - f1
10
  model-index:
11
  - name: bsc_ai_thesis_torgo_model-1
12
  results: []
 
19
 
20
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.3532
23
+ - Accuracy: 0.8625
24
+ - Precision: 0.8349
25
+ - Recall: 0.9055
26
+ - F1: 0.8687
27
 
28
  ## Model description
29
 
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
+ | 0.6855 | 0.96 | 12 | 0.6603 | 0.6225 | 0.5772 | 0.9303 | 0.7124 |
61
+ | 0.5875 | 2.0 | 25 | 0.5249 | 0.785 | 0.7533 | 0.8507 | 0.7991 |
62
+ | 0.4858 | 2.96 | 37 | 0.5584 | 0.7575 | 0.6940 | 0.9254 | 0.7932 |
63
+ | 0.3951 | 4.0 | 50 | 0.5366 | 0.785 | 0.7220 | 0.9303 | 0.8130 |
64
+ | 0.3962 | 4.96 | 62 | 0.4707 | 0.805 | 0.7450 | 0.9303 | 0.8274 |
65
+ | 0.3069 | 6.0 | 75 | 0.4032 | 0.8325 | 0.8190 | 0.8557 | 0.8370 |
66
+ | 0.2973 | 6.96 | 87 | 0.3753 | 0.855 | 0.8593 | 0.8507 | 0.855 |
67
+ | 0.2585 | 8.0 | 100 | 0.3719 | 0.8625 | 0.8259 | 0.9204 | 0.8706 |
68
+ | 0.2365 | 8.96 | 112 | 0.3503 | 0.855 | 0.8357 | 0.8856 | 0.8599 |
69
+ | 0.2244 | 9.6 | 120 | 0.3532 | 0.8625 | 0.8349 | 0.9055 | 0.8687 |
70
 
71
 
72
  ### Framework versions