Audio Classification
English
music
art
admin commited on
Commit
1d35a8e
·
1 Parent(s): ac48b37
Files changed (1) hide show
  1. README.md +16 -4
README.md CHANGED
@@ -30,7 +30,19 @@ cd chest_falsetto
30
  ```
31
 
32
  ## Results
33
- A fine-tuning result of MaxViT-T on CQT:
 
 
 
 
 
 
 
 
 
 
 
 
34
  <style>
35
  #falsetto td {
36
  vertical-align: middle !important;
@@ -43,15 +55,15 @@ A fine-tuning result of MaxViT-T on CQT:
43
  <table id="falsetto">
44
  <tr>
45
  <th>Loss curve</th>
46
- <td><img src="https://www.modelscope.cn/models/ccmusic-database/chest_falsetto/resolve/master/maxvit_t_cqt_2024-07-30_17-23-12/loss.jpg"></td>
47
  </tr>
48
  <tr>
49
  <th>Training and validation accuracy</th>
50
- <td><img src="https://www.modelscope.cn/models/ccmusic-database/chest_falsetto/resolve/master/maxvit_t_cqt_2024-07-30_17-23-12/acc.jpg"></td>
51
  </tr>
52
  <tr>
53
  <th>Confusion matrix</th>
54
- <td><img src="https://www.modelscope.cn/models/ccmusic-database/chest_falsetto/resolve/master/maxvit_t_cqt_2024-07-30_17-23-12/mat.jpg"></td>
55
  </tr>
56
  </table>
57
 
 
30
  ```
31
 
32
  ## Results
33
+ | Backbone | Mel | CQT | Chroma |
34
+ | :---------------: | :-------------------------: | :---------: | :---------: |
35
+ | Swin-S V2 | **_0.968_** | 0.268 | **_0.268_** |
36
+ | MaxViT-T | 0.820 | **_0.933_** | 0.250 |
37
+ | | | | |
38
+ | AlexNet | [**_0.994_**](#best-result) | **_0.963_** | **_0.586_** |
39
+ | ShuffleNet V2 2.0 | 0.939 | 0.669 | 0.222 |
40
+ | GoogleNet | 0.983 | 0.274 | 0.292 |
41
+ | MNASNet-A3 | 0.756 | 0.260 | 0.320 |
42
+ | SqueezeNet 1.1 | 0.963 | 0.900 | 0.378 |
43
+ | Average | 0.918 | 0.610 | 0.331 |
44
+
45
+ ### Best Result
46
  <style>
47
  #falsetto td {
48
  vertical-align: middle !important;
 
55
  <table id="falsetto">
56
  <tr>
57
  <th>Loss curve</th>
58
+ <td><img src="https://www.modelscope.cn/models/ccmusic-database/chest_falsetto/resolve/master/alexnet_mel_2024-07-30_11-52-53/loss.jpg"></td>
59
  </tr>
60
  <tr>
61
  <th>Training and validation accuracy</th>
62
+ <td><img src="https://www.modelscope.cn/models/ccmusic-database/chest_falsetto/resolve/master/alexnet_mel_2024-07-30_11-52-53/acc.jpg"></td>
63
  </tr>
64
  <tr>
65
  <th>Confusion matrix</th>
66
+ <td><img src="https://www.modelscope.cn/models/ccmusic-database/chest_falsetto/resolve/master/alexnet_mel_2024-07-30_11-52-53/mat.jpg"></td>
67
  </tr>
68
  </table>
69