anton-l HF staff commited on
Commit
a2c3a20
1 Parent(s): 6c01941

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +68 -0
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - audio-classification
5
+ - generated_from_trainer
6
+ datasets:
7
+ - superb
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: distilhubert-ft-keyword-spotting
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # distilhubert-ft-keyword-spotting
19
+
20
+ This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the superb dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.1163
23
+ - Accuracy: 0.9706
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 3e-05
43
+ - train_batch_size: 256
44
+ - eval_batch_size: 32
45
+ - seed: 0
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 5.0
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
+ | 0.8176 | 1.0 | 200 | 0.7718 | 0.8116 |
57
+ | 0.2364 | 2.0 | 400 | 0.2107 | 0.9662 |
58
+ | 0.1198 | 3.0 | 600 | 0.1374 | 0.9678 |
59
+ | 0.0891 | 4.0 | 800 | 0.1163 | 0.9706 |
60
+ | 0.085 | 5.0 | 1000 | 0.1180 | 0.9690 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.12.0.dev0
66
+ - Pytorch 1.9.1+cu111
67
+ - Datasets 1.14.0
68
+ - Tokenizers 0.10.3