Hugging Face's logo

vumichien
/
trillsson3-ft-keyword-spotting-13

Audio Classification
Transformers
PyTorch
trillsson_efficient
text-classification
Generated from Trainer
Inference Endpoints
Model card Files Community
1
vumichien commited on
Commit
14c6955
•
1 Parent(s): 4267ae9

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -23
README.md CHANGED
@@ -1,6 +1,5 @@
1
  ---
2
  tags:
3
- - audio-classification
4
  - generated_from_trainer
5
  datasets:
6
  - superb
@@ -18,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [vumichien/nonsemantic-speech-trillsson3](https://huggingface.co/vumichien/nonsemantic-speech-trillsson3) on the superb dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.3085
22
- - Accuracy: 0.9153
23
 
24
  ## Model description
25
 
@@ -54,26 +53,26 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
57
- | 1.8064 | 1.0 | 798 | 0.9359 | 0.6403 |
58
- | 0.8601 | 2.0 | 1596 | 0.4832 | 0.8528 |
59
- | 0.7585 | 3.0 | 2394 | 0.3952 | 0.8854 |
60
- | 0.7026 | 4.0 | 3192 | 0.3623 | 0.9050 |
61
- | 0.6924 | 5.0 | 3990 | 0.3456 | 0.9035 |
62
- | 0.6816 | 6.0 | 4788 | 0.3405 | 0.9006 |
63
- | 0.6461 | 7.0 | 5586 | 0.3384 | 0.9004 |
64
- | 0.6697 | 8.0 | 6384 | 0.3272 | 0.9045 |
65
- | 0.6575 | 9.0 | 7182 | 0.3237 | 0.9109 |
66
- | 0.6634 | 10.0 | 7980 | 0.3258 | 0.9026 |
67
- | 0.6604 | 11.0 | 8778 | 0.3179 | 0.9042 |
68
- | 0.6483 | 12.0 | 9576 | 0.3203 | 0.9059 |
69
- | 0.6578 | 13.0 | 10374 | 0.3160 | 0.9089 |
70
- | 0.654 | 14.0 | 11172 | 0.3139 | 0.9091 |
71
- | 0.6418 | 15.0 | 11970 | 0.3091 | 0.9125 |
72
- | 0.6394 | 16.0 | 12768 | 0.3223 | 0.9029 |
73
- | 0.637 | 17.0 | 13566 | 0.3085 | 0.9153 |
74
- | 0.6258 | 18.0 | 14364 | 0.3182 | 0.9069 |
75
- | 0.6438 | 19.0 | 15162 | 0.3127 | 0.9078 |
76
- | 0.6569 | 20.0 | 15960 | 0.3101 | 0.9114 |
77
 
78
 
79
  ### Framework versions
 
1
  ---
2
  tags:
 
3
  - generated_from_trainer
4
  datasets:
5
  - superb
 
17
 
18
  This model is a fine-tuned version of [vumichien/nonsemantic-speech-trillsson3](https://huggingface.co/vumichien/nonsemantic-speech-trillsson3) on the superb dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.3115
21
+ - Accuracy: 0.9100
22
 
23
  ## Model description
24
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
56
+ | 1.7756 | 1.0 | 798 | 0.9283 | 0.6396 |
57
+ | 0.8631 | 2.0 | 1596 | 0.4884 | 0.8573 |
58
+ | 0.7551 | 3.0 | 2394 | 0.3967 | 0.8832 |
59
+ | 0.6968 | 4.0 | 3192 | 0.3644 | 0.8989 |
60
+ | 0.67 | 5.0 | 3990 | 0.3428 | 0.9057 |
61
+ | 0.6854 | 6.0 | 4788 | 0.3408 | 0.9026 |
62
+ | 0.6701 | 7.0 | 5586 | 0.3359 | 0.9013 |
63
+ | 0.6734 | 8.0 | 6384 | 0.3285 | 0.9059 |
64
+ | 0.6581 | 9.0 | 7182 | 0.3199 | 0.9095 |
65
+ | 0.6557 | 10.0 | 7980 | 0.3301 | 0.8986 |
66
+ | 0.6768 | 11.0 | 8778 | 0.3174 | 0.9047 |
67
+ | 0.6459 | 12.0 | 9576 | 0.3192 | 0.9031 |
68
+ | 0.6607 | 13.0 | 10374 | 0.3173 | 0.9066 |
69
+ | 0.656 | 14.0 | 11172 | 0.3142 | 0.9094 |
70
+ | 0.6302 | 15.0 | 11970 | 0.3093 | 0.9153 |
71
+ | 0.636 | 16.0 | 12768 | 0.3184 | 0.9044 |
72
+ | 0.6327 | 17.0 | 13566 | 0.3104 | 0.9117 |
73
+ | 0.6428 | 18.0 | 14364 | 0.3158 | 0.9084 |
74
+ | 0.6515 | 19.0 | 15162 | 0.3129 | 0.9097 |
75
+ | 0.6441 | 20.0 | 15960 | 0.3115 | 0.9100 |
76
 
77
 
78
  ### Framework versions