Hugging Face's logo

Vyvo-Research
/
AST-Music-Classifier-1K

Audio Classification
Transformers
Safetensors
English
audio-spectrogram-transformer
music
speech
ast
Model card Files
xet
 Community
Aynursusuz commited on
Commit
53a0367
·
verified ·
1 Parent(s): 6d6b498

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +19 -19
README.md CHANGED
@@ -26,7 +26,7 @@ Fine-tuned Audio Spectrogram Transformer (AST) for music vs speech classificatio
26
  - **Base Model:** MIT/ast-finetuned-audioset-10-10-0.4593
27
  - **Task:** Binary Audio Classification (Music vs Speech)
28
  - **Training Dataset:** AIGenLab/speech-music-1k (1000 samples)
29
- - **Overall Accuracy:** 86.7% (26/30)
30
 
31
  ---
32
 
@@ -36,20 +36,20 @@ Fine-tuned Audio Spectrogram Transformer (AST) for music vs speech classificatio
36
  |----------|----------|---------|-------|
37
  | Pure Music | 100.0% | 10 | 10 |
38
  | Pure Speech | 70.0% | 7 | 10 |
39
- | Speech + Music | 90.0% | 9 | 10 |
40
 
41
  ### Pure Music
42
 
43
  | File | Music Score | Speech Score | Prediction | Result |
44
  |------|-------------|--------------|------------|--------|
45
  | music_1.wav | 1.000 | 0.000 | MUSIC | ✅ |
46
- | music_10.wav | 0.999 | 0.001 | MUSIC | ✅ |
47
- | music_2.wav | 0.999 | 0.001 | MUSIC | ✅ |
48
- | music_3.wav | 0.999 | 0.001 | MUSIC | ✅ |
49
  | music_4.wav | 1.000 | 0.000 | MUSIC | ✅ |
50
- | music_5.wav | 0.996 | 0.004 | MUSIC | ✅ |
51
  | music_6.wav | 1.000 | 0.000 | MUSIC | ✅ |
52
- | music_7.wav | 0.998 | 0.002 | MUSIC | ✅ |
53
  | music_8.wav | 1.000 | 0.000 | MUSIC | ✅ |
54
  | music_9.wav | 1.000 | 0.000 | MUSIC | ✅ |
55
 
@@ -58,28 +58,28 @@ Fine-tuned Audio Spectrogram Transformer (AST) for music vs speech classificatio
58
  | File | Music Score | Speech Score | Prediction | Result |
59
  |------|-------------|--------------|------------|--------|
60
  | speech_1.wav | 0.000 | 1.000 | SPEECH | ✅ |
61
- | speech_10.wav | 0.000 | 1.000 | SPEECH | ✅ |
62
  | speech_2.wav | 0.000 | 1.000 | SPEECH | ✅ |
63
- | speech_3.wav | 0.824 | 0.176 | MUSIC | ❌ |
64
- | speech_4.wav | 0.978 | 0.022 | MUSIC | ❌ |
65
- | speech_5.wav | 1.000 | 0.000 | MUSIC | ❌ |
66
- | speech_6.wav | 0.038 | 0.962 | SPEECH | ✅ |
67
- | speech_7.wav | 0.003 | 0.997 | SPEECH | ✅ |
68
- | speech_8.wav | 0.001 | 0.999 | SPEECH | ✅ |
69
- | speech_9.wav | 0.000 | 1.000 | SPEECH | ✅ |
70
 
71
  ### Speech + Music
72
 
73
  | File | Music Score | Speech Score | Prediction | Result |
74
  |------|-------------|--------------|------------|--------|
75
- | speech_and_music_1.wav | 1.000 | 0.000 | MUSIC | ✅ |
76
- | speech_and_music_10.wav | 1.000 | 0.000 | MUSIC | ✅ |
77
  | speech_and_music_2.wav | 1.000 | 0.000 | MUSIC | ✅ |
78
  | speech_and_music_3wav.wav | 1.000 | 0.000 | MUSIC | ✅ |
79
  | speech_and_music_4.wav | 1.000 | 0.000 | MUSIC | ✅ |
80
- | speech_and_music_5.wav | 1.000 | 0.000 | MUSIC | ✅ |
81
  | speech_and_music_6.wav | 1.000 | 0.000 | MUSIC | ✅ |
82
- | speech_and_music_7.wav | 0.353 | 0.647 | SPEECH | ❌ |
83
  | speech_and_music_8.wav | 1.000 | 0.000 | MUSIC | ✅ |
84
  | speech_and_music_9.wav | 1.000 | 0.000 | MUSIC | ✅ |
85
 
 
26
  - **Base Model:** MIT/ast-finetuned-audioset-10-10-0.4593
27
  - **Task:** Binary Audio Classification (Music vs Speech)
28
  - **Training Dataset:** AIGenLab/speech-music-1k (1000 samples)
29
+ - **Overall Accuracy:** 90.0% (27/30)
30
 
31
  ---
32
 
 
36
  |----------|----------|---------|-------|
37
  | Pure Music | 100.0% | 10 | 10 |
38
  | Pure Speech | 70.0% | 7 | 10 |
39
+ | Speech + Music | 100.0% | 10 | 10 |
40
 
41
  ### Pure Music
42
 
43
  | File | Music Score | Speech Score | Prediction | Result |
44
  |------|-------------|--------------|------------|--------|
45
  | music_1.wav | 1.000 | 0.000 | MUSIC | ✅ |
46
+ | music_10.wav | 1.000 | 0.000 | MUSIC | ✅ |
47
+ | music_2.wav | 1.000 | 0.000 | MUSIC | ✅ |
48
+ | music_3.wav | 1.000 | 0.000 | MUSIC | ✅ |
49
  | music_4.wav | 1.000 | 0.000 | MUSIC | ✅ |
50
+ | music_5.wav | 1.000 | 0.000 | MUSIC | ✅ |
51
  | music_6.wav | 1.000 | 0.000 | MUSIC | ✅ |
52
+ | music_7.wav | 1.000 | 0.000 | MUSIC | ✅ |
53
  | music_8.wav | 1.000 | 0.000 | MUSIC | ✅ |
54
  | music_9.wav | 1.000 | 0.000 | MUSIC | ✅ |
55
 
 
58
  | File | Music Score | Speech Score | Prediction | Result |
59
  |------|-------------|--------------|------------|--------|
60
  | speech_1.wav | 0.000 | 1.000 | SPEECH | ✅ |
61
+ | speech_10.wav | 0.002 | 0.998 | SPEECH | ✅ |
62
  | speech_2.wav | 0.000 | 1.000 | SPEECH | ✅ |
63
+ | speech_3.wav | 0.714 | 0.286 | MUSIC | ❌ |
64
+ | speech_4.wav | 0.906 | 0.094 | MUSIC | ❌ |
65
+ | speech_5.wav | 0.350 | 0.650 | SPEECH | ✅ |
66
+ | speech_6.wav | 0.895 | 0.105 | MUSIC | ❌ |
67
+ | speech_7.wav | 0.068 | 0.932 | SPEECH | ✅ |
68
+ | speech_8.wav | 0.097 | 0.903 | SPEECH | ✅ |
69
+ | speech_9.wav | 0.083 | 0.917 | SPEECH | ✅ |
70
 
71
  ### Speech + Music
72
 
73
  | File | Music Score | Speech Score | Prediction | Result |
74
  |------|-------------|--------------|------------|--------|
75
+ | speech_and_music_1.wav | 0.995 | 0.005 | MUSIC | ✅ |
76
+ | speech_and_music_10.wav | 0.987 | 0.013 | MUSIC | ✅ |
77
  | speech_and_music_2.wav | 1.000 | 0.000 | MUSIC | ✅ |
78
  | speech_and_music_3wav.wav | 1.000 | 0.000 | MUSIC | ✅ |
79
  | speech_and_music_4.wav | 1.000 | 0.000 | MUSIC | ✅ |
80
+ | speech_and_music_5.wav | 0.998 | 0.002 | MUSIC | ✅ |
81
  | speech_and_music_6.wav | 1.000 | 0.000 | MUSIC | ✅ |
82
+ | speech_and_music_7.wav | 1.000 | 0.000 | MUSIC | ✅ |
83
  | speech_and_music_8.wav | 1.000 | 0.000 | MUSIC | ✅ |
84
  | speech_and_music_9.wav | 1.000 | 0.000 | MUSIC | ✅ |
85