Hugging Face's logo

taohoang
/
whisper-tiny-finetuned-gtzan

Audio Classification
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
taohoang commited on
Commit
2c313e8
•
1 Parent(s): cf864a8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +105 -0
README.md ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: openai/whisper-tiny
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - marsyas/gtzan
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: whisper-tiny-finetuned-gtzan
12
+ results:
13
+ - task:
14
+ name: Audio Classification
15
+ type: audio-classification
16
+ dataset:
17
+ name: GTZAN
18
+ type: marsyas/gtzan
19
+ config: all
20
+ split: train
21
+ args: all
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.91
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # whisper-tiny-finetuned-gtzan
32
+
33
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the GTZAN dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.6420
36
+ - Accuracy: 0.91
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 0.0001
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_steps: 10
62
+ - num_epochs: 10
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.9835 | 0.33 | 37 | 1.4610 | 0.62 |
69
+ | 1.5031 | 0.65 | 74 | 1.1531 | 0.63 |
70
+ | 1.1644 | 0.98 | 111 | 0.8526 | 0.73 |
71
+ | 0.9035 | 1.31 | 148 | 0.8748 | 0.69 |
72
+ | 0.7942 | 1.64 | 185 | 0.7811 | 0.78 |
73
+ | 0.8435 | 1.96 | 222 | 0.8262 | 0.7 |
74
+ | 0.5999 | 2.29 | 259 | 0.6450 | 0.72 |
75
+ | 0.6187 | 2.62 | 296 | 0.6616 | 0.79 |
76
+ | 0.6329 | 2.95 | 333 | 0.6479 | 0.81 |
77
+ | 0.3549 | 3.27 | 370 | 0.6246 | 0.78 |
78
+ | 0.3362 | 3.6 | 407 | 0.5348 | 0.81 |
79
+ | 0.3329 | 3.93 | 444 | 0.4657 | 0.85 |
80
+ | 0.2224 | 4.26 | 481 | 0.4433 | 0.89 |
81
+ | 0.208 | 4.58 | 518 | 0.6448 | 0.84 |
82
+ | 0.1983 | 4.91 | 555 | 0.6080 | 0.86 |
83
+ | 0.1736 | 5.24 | 592 | 0.6201 | 0.86 |
84
+ | 0.0976 | 5.57 | 629 | 0.6952 | 0.87 |
85
+ | 0.025 | 5.89 | 666 | 0.5872 | 0.9 |
86
+ | 0.0509 | 6.22 | 703 | 0.5845 | 0.91 |
87
+ | 0.1474 | 6.55 | 740 | 0.6800 | 0.89 |
88
+ | 0.0594 | 6.88 | 777 | 0.6280 | 0.87 |
89
+ | 0.0023 | 7.2 | 814 | 0.6850 | 0.88 |
90
+ | 0.0058 | 7.53 | 851 | 0.6766 | 0.89 |
91
+ | 0.023 | 7.86 | 888 | 0.8498 | 0.87 |
92
+ | 0.0272 | 8.19 | 925 | 0.7815 | 0.86 |
93
+ | 0.0011 | 8.51 | 962 | 0.6570 | 0.9 |
94
+ | 0.0012 | 8.84 | 999 | 0.6395 | 0.91 |
95
+ | 0.023 | 9.17 | 1036 | 0.6412 | 0.91 |
96
+ | 0.0009 | 9.5 | 1073 | 0.6416 | 0.91 |
97
+ | 0.001 | 9.82 | 1110 | 0.6420 | 0.91 |
98
+
99
+
100
+ ### Framework versions
101
+
102
+ - Transformers 4.31.0
103
+ - Pytorch 2.0.1+cu118
104
+ - Datasets 2.14.3
105
+ - Tokenizers 0.13.3