Hugging Face's logo

aydink
/
ast-finetuned-audioset-10-10-0.4593-finetuned-common_voice

Audio Classification
Transformers
TensorBoard
Safetensors
audio-spectrogram-transformer
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
aydink commited on
Commit
2b4b83a
•
1 Parent(s): f7d8f79

Model save

Browse files
Files changed (2) hide show
  1. README.md +17 -17
  2. model.safetensors +1 -1
README.md CHANGED
@@ -20,13 +20,13 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.4652
24
- - Accuracy: 0.905
25
- - F1: 0.9049
26
- - Recall: 0.905
27
- - Precision: 0.9057
28
- - Mcc: 0.8814
29
- - Auc: 0.9874
30
 
31
  ## Model description
32
 
@@ -59,16 +59,16 @@ The following hyperparameters were used during training:
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision | Mcc | Auc |
61
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|:------:|:------:|
62
- | 1.0765 | 1.0 | 200 | 0.9662 | 0.5925 | 0.5411 | 0.5925 | 0.6493 | 0.5098 | 0.9152 |
63
- | 0.5977 | 2.0 | 400 | 0.5536 | 0.8 | 0.7999 | 0.8 | 0.8146 | 0.7532 | 0.9670 |
64
- | 0.1826 | 3.0 | 600 | 0.5388 | 0.8375 | 0.8385 | 0.8375 | 0.8491 | 0.7994 | 0.9759 |
65
- | 0.1125 | 4.0 | 800 | 0.6617 | 0.85 | 0.8486 | 0.85 | 0.8636 | 0.8161 | 0.9798 |
66
- | 0.0025 | 5.0 | 1000 | 0.5859 | 0.865 | 0.8653 | 0.865 | 0.8733 | 0.8333 | 0.984 |
67
- | 0.0058 | 6.0 | 1200 | 0.5043 | 0.8975 | 0.8968 | 0.8975 | 0.9001 | 0.8728 | 0.9882 |
68
- | 0.0 | 7.0 | 1400 | 0.4883 | 0.8925 | 0.8932 | 0.8925 | 0.8957 | 0.8660 | 0.9859 |
69
- | 0.0 | 8.0 | 1600 | 0.4652 | 0.905 | 0.9050 | 0.905 | 0.9055 | 0.8814 | 0.9871 |
70
- | 0.0 | 9.0 | 1800 | 0.4655 | 0.905 | 0.9049 | 0.905 | 0.9057 | 0.8814 | 0.9873 |
71
- | 0.0 | 10.0 | 2000 | 0.4652 | 0.905 | 0.9049 | 0.905 | 0.9057 | 0.8814 | 0.9874 |
72
 
73
 
74
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0148
24
+ - Accuracy: 0.9925
25
+ - F1: 0.9925
26
+ - Recall: 0.9925
27
+ - Precision: 0.9926
28
+ - Mcc: 0.9906
29
+ - Auc: 1.0000
30
 
31
  ## Model description
32
 
 
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision | Mcc | Auc |
61
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|:------:|:------:|
62
+ | 0.2357 | 1.0 | 200 | 0.0914 | 0.96 | 0.9603 | 0.96 | 0.9637 | 0.9508 | 0.9997 |
63
+ | 0.2769 | 2.0 | 400 | 0.1397 | 0.965 | 0.9653 | 0.9650 | 0.9673 | 0.9567 | 0.9982 |
64
+ | 0.0736 | 3.0 | 600 | 0.0468 | 0.9875 | 0.9875 | 0.9875 | 0.9880 | 0.9845 | 0.9998 |
65
+ | 0.0672 | 4.0 | 800 | 0.0554 | 0.985 | 0.9849 | 0.985 | 0.9854 | 0.9814 | 0.9999 |
66
+ | 0.0024 | 5.0 | 1000 | 0.1224 | 0.97 | 0.9703 | 0.9700 | 0.9724 | 0.9630 | 0.9997 |
67
+ | 0.0 | 6.0 | 1200 | 0.0109 | 0.995 | 0.9950 | 0.9950 | 0.9951 | 0.9938 | 1.0000 |
68
+ | 0.0 | 7.0 | 1400 | 0.0255 | 0.9925 | 0.9925 | 0.9925 | 0.9926 | 0.9906 | 1.0000 |
69
+ | 0.0 | 8.0 | 1600 | 0.0169 | 0.9925 | 0.9925 | 0.9925 | 0.9926 | 0.9906 | 1.0000 |
70
+ | 0.0 | 9.0 | 1800 | 0.0154 | 0.9925 | 0.9925 | 0.9925 | 0.9926 | 0.9906 | 1.0000 |
71
+ | 0.0 | 10.0 | 2000 | 0.0148 | 0.9925 | 0.9925 | 0.9925 | 0.9926 | 0.9906 | 1.0000 |
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77b28a80082632004c687d03723372eab5f251d3e816a7e42486b970d2f7a19b
3
  size 344799268
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00dc49800230faf98fc35c62b8fffbe1d552edc4699c5fc16779c3323504fce1
3
  size 344799268