Hugging Face's logo

bookbot
/
wav2vec2-adult-child-id-cls

Audio Classification
Transformers
PyTorch
TensorBoard
Indonesian
wav2vec2
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
anantoj commited on
Commit
3198c3a
•
1 Parent(s): eb58e9b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +48 -40
README.md CHANGED
@@ -1,66 +1,74 @@
1
  ---
 
2
  license: apache-2.0
3
  tags:
4
- - generated_from_trainer
 
5
  metrics:
6
- - accuracy
7
- - f1
8
  model-index:
9
- - name: wav2vec2-adult-child-id-cls-v2
10
- results: []
11
  ---
12
 
13
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
- should probably proofread and complete it, then remove this comment. -->
15
 
16
- # wav2vec2-adult-child-id-cls-v2
17
 
18
- This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
19
- It achieves the following results on the evaluation set:
20
- - Loss: 0.2603
21
- - Accuracy: 0.9222
22
- - F1: 0.9202
23
 
24
- ## Model description
25
 
26
- More information needed
 
 
27
 
28
- ## Intended uses & limitations
29
 
30
- More information needed
31
 
32
- ## Training and evaluation data
33
-
34
- More information needed
35
 
36
  ## Training procedure
37
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 3e-05
42
- - train_batch_size: 32
43
- - eval_batch_size: 32
44
- - seed: 42
45
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
- - lr_scheduler_type: linear
47
- - lr_scheduler_warmup_ratio: 0.1
48
- - num_epochs: 5
 
 
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
- | 0.2415 | 1.0 | 305 | 0.2951 | 0.8804 | 0.8695 |
55
- | 0.202 | 2.0 | 610 | 0.2392 | 0.9124 | 0.9081 |
56
- | 0.2161 | 3.0 | 915 | 0.2508 | 0.9199 | 0.9161 |
57
- | 0.1348 | 4.0 | 1220 | 0.2748 | 0.9153 | 0.9126 |
58
- | 0.162 | 5.0 | 1525 | 0.2603 | 0.9222 | 0.9202 |
 
 
 
 
 
 
59
 
 
60
 
61
- ### Framework versions
62
 
63
- - Transformers 4.18.0
64
- - Pytorch 1.11.0+cu102
65
- - Datasets 2.2.0
66
- - Tokenizers 0.12.1
1
  ---
2
+ language: id
3
  license: apache-2.0
4
  tags:
5
+ - audio-classification
6
+ - generated_from_trainer
7
  metrics:
8
+ - accuracy
9
+ - f1
10
  model-index:
11
+ - name: wav2vec2-adult-child-id-cls
12
+ results: []
13
  ---
14
 
15
+ # Wav2Vec2 Adult/Child Indonesian Speech Classifier
 
16
 
17
+ Wav2Vec2 Adult/Child Indonesian Speech Classifier is an audio classification model based on the [wav2vec 2.0](https://arxiv.org/abs/2006.11477) architecture. This model is a fine-tuned version of [wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on a private adult/child Indonesian speech classification dataset.
18
 
19
+ This model was trained using HuggingFace's PyTorch framework. All training was done on a Tesla P100, provided by Kaggle. Training metrics were logged via Tensorboard.
 
 
 
 
20
 
21
+ ## Model
22
 
23
+ | Model | #params | Arch. | Training/Validation data (text) |
24
+ | ----------------------------- | ------- | ----------- | ---------------------------------------------------- |
25
+ | `wav2vec2-adult-child-id-cls` | 91M | wav2vec 2.0 | Adult/Child Indonesian Speech Classification Dataset |
26
 
27
+ ## Evaluation Results
28
 
29
+ The model achieves the following results on evaluation:
30
 
31
+ | Dataset | Loss | Accuracy | F1 |
32
+ | -------------------------------------------- | ------ | -------- | ------ |
33
+ | Adult/Child Indonesian Speech Classification | 0.2603 | 92.22% | 0.9202 |
34
 
35
  ## Training procedure
36
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+
41
+ - `learning_rate`: 3e-05
42
+ - `train_batch_size`: 32
43
+ - `eval_batch_size`: 32
44
+ - `seed`: 42
45
+ - `optimizer`: Adam with `betas=(0.9,0.999)` and `epsilon=1e-08`
46
+ - `lr_scheduler_type`: linear
47
+ - `lr_scheduler_warmup_ratio`: 0.1
48
+ - `gradient_accumulation_steps`: 1
49
+ - `num_epochs`: 5
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
+ | :-----------: | :---: | :--: | :-------------: | :------: | :----: |
55
+ | 0.2415 | 1.0 | 305 | 0.2951 | 0.8804 | 0.8695 |
56
+ | 0.202 | 2.0 | 610 | 0.2392 | 0.9124 | 0.9081 |
57
+ | 0.2161 | 3.0 | 915 | 0.2508 | 0.9199 | 0.9161 |
58
+ | 0.1348 | 4.0 | 1220 | 0.2748 | 0.9153 | 0.9126 |
59
+ | 0.162 | 5.0 | 1525 | 0.2603 | 0.9222 | 0.9202 |
60
+
61
+ ## Disclaimer
62
+
63
+ Do consider the biases which came from pre-training datasets that may be carried over into the results of this model.
64
+
65
+ ## Authors
66
 
67
+ Wav2Vec2 Adult/Child Indonesian Speech Classifier was trained and evaluated by [Ananto Joyoadikusumo](https://anantoj.github.io/). All computation and development are done on Kaggle.
68
 
69
+ ## Framework versions
70
 
71
+ - Transformers 4.18.0
72
+ - Pytorch 1.11.0+cu102
73
+ - Datasets 2.2.0
74
+ - Tokenizers 0.12.1