Hugging Face's logo

mahmoudmamdouh13
/
ast-mlcommons-speech-commands

Audio Classification
Transformers
TensorBoard
Safetensors
audio-spectrogram-transformer
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
mahmoudmamdouh13 commited on
Commit
4f71c67
·
verified ·
1 Parent(s): 83f88d8

End of training

Browse files
Files changed (1) hide show
  1. README.md +14 -14
README.md CHANGED
@@ -25,13 +25,13 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.9661601051155746
29
  - name: Recall
30
  type: recall
31
- value: 0.9662664379645511
32
  - name: F1
33
  type: f1
34
- value: 0.9661541075893276
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,10 +41,10 @@ should probably proofread and complete it, then remove this comment. -->
41
 
42
  This model is a fine-tuned version of [MIT/ast-finetuned-audioset-12-12-0.447](https://huggingface.co/MIT/ast-finetuned-audioset-12-12-0.447) on the audiofolder dataset.
43
  It achieves the following results on the evaluation set:
44
- - Loss: 0.1790
45
- - Precision: 0.9662
46
- - Recall: 0.9663
47
- - F1: 0.9662
48
 
49
  ## Model description
50
 
@@ -75,13 +75,13 @@ The following hyperparameters were used during training:
75
 
76
  ### Training results
77
 
78
- | Training Loss | Epoch | Step | F1 | Validation Loss | Precision | Recall |
79
- |:-------------:|:-----:|:-----:|:------:|:---------------:|:---------:|:------:|
80
- | 0.0795 | 1.0 | 3496 | 0.9342 | 0.2169 | 0.9357 | 0.9347 |
81
- | 0.1295 | 2.0 | 6992 | 0.9467 | 0.1728 | 0.9486 | 0.9473 |
82
- | 0.0279 | 3.0 | 10488 | 0.9551 | 0.1717 | 0.9558 | 0.9556 |
83
- | 0.0029 | 4.0 | 13984 | 0.9621 | 0.1733 | 0.9624 | 0.9621 |
84
- | 0.0023 | 5.0 | 17480 | 0.9662 | 0.1790 | 0.9663 | 0.9662 |
85
 
86
 
87
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.9743628199079283
29
  - name: Recall
30
  type: recall
31
+ value: 0.9743424814179531
32
  - name: F1
33
  type: f1
34
+ value: 0.9743165983480835
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
41
 
42
  This model is a fine-tuned version of [MIT/ast-finetuned-audioset-12-12-0.447](https://huggingface.co/MIT/ast-finetuned-audioset-12-12-0.447) on the audiofolder dataset.
43
  It achieves the following results on the evaluation set:
44
+ - Loss: 0.1346
45
+ - Precision: 0.9744
46
+ - Recall: 0.9743
47
+ - F1: 0.9743
48
 
49
  ## Model description
50
 
 
75
 
76
  ### Training results
77
 
78
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
79
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|
80
+ | 0.0799 | 1.0 | 3496 | 0.1498 | 0.9596 | 0.9573 | 0.9577 |
81
+ | 0.0624 | 2.0 | 6992 | 0.1141 | 0.9689 | 0.9687 | 0.9685 |
82
+ | 0.0091 | 3.0 | 10488 | 0.1285 | 0.9713 | 0.9713 | 0.9711 |
83
+ | 0.0384 | 4.0 | 13984 | 0.1237 | 0.9743 | 0.9743 | 0.9742 |
84
+ | 0.0019 | 5.0 | 17480 | 0.1346 | 0.9744 | 0.9743 | 0.9743 |
85
 
86
 
87
  ### Framework versions