Hugging Face's logo

bookbot
/
distil-wav2vec2-xls-r-adult-child-cls-64m

Audio Classification
Transformers
PyTorch
TensorBoard
Safetensors
English
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
anantoj commited on
Commit
99a1146
•
1 Parent(s): 41a5999

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +46 -39
README.md CHANGED
@@ -1,68 +1,75 @@
1
  ---
 
2
  license: apache-2.0
3
  tags:
4
- - generated_from_trainer
 
5
  metrics:
6
- - accuracy
7
- - f1
8
  model-index:
9
- - name: distil-wav2vec2-xls-r-adult-child-cls
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
- # distil-wav2vec2-xls-r-adult-child-cls
17
 
18
- This model is a fine-tuned version of [w11wo/wav2vec2-xls-r-adult-child-cls](https://huggingface.co/w11wo/wav2vec2-xls-r-adult-child-cls) on the None dataset.
19
- It achieves the following results on the evaluation set:
20
- - Loss: 0.2571
21
- - Accuracy: 0.9386
22
- - F1: 0.9425
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: 16
43
- - eval_batch_size: 16
44
- - seed: 42
45
- - gradient_accumulation_steps: 4
46
- - total_train_batch_size: 64
47
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
- - lr_scheduler_type: linear
49
- - lr_scheduler_warmup_ratio: 0.1
50
- - num_epochs: 5
 
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
56
- | 0.5509 | 1.0 | 191 | 0.3685 | 0.9086 | 0.9131 |
57
- | 0.4543 | 2.0 | 382 | 0.3113 | 0.9247 | 0.9285 |
58
- | 0.409 | 3.0 | 573 | 0.2723 | 0.9372 | 0.9418 |
59
- | 0.3024 | 4.0 | 764 | 0.2786 | 0.9381 | 0.9417 |
60
- | 0.3103 | 5.0 | 955 | 0.2571 | 0.9386 | 0.9425 |
 
 
 
 
 
 
61
 
 
62
 
63
- ### Framework versions
64
 
65
  - Transformers 4.17.0.dev0
66
  - Pytorch 1.10.2+cu102
67
  - Datasets 1.18.3
68
- - Tokenizers 0.11.0
 
1
  ---
2
+ language: en
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: distil-wav2vec2-xls-r-adult-child-cls-64m
12
+ results: []
13
  ---
14
 
15
+ # DistilWav2Vec2 XLS-R Adult/Child Speech Classifier 64M
 
16
 
17
+ DistilWav2Vec2 XLS-R Adult/Child Speech Classifier is an audio classification model based on the [XLS-R](https://arxiv.org/abs/2111.09296) architecture. This model is a distilled version of [wav2vec2-xls-r-adult-child-cls](https://huggingface.co/bookbot/wav2vec2-xls-r-adult-child-cls) on a private adult/child 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
+ | `distil-wav2vec2-xls-r-adult-child-cls-64m` | 64M | XLS-R | Adult/Child 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 Speech Classification | 0.2571 | 93.86% | 0.9425 |
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`: 16
43
+ - `eval_batch_size`: 16
44
+ - `seed`: 42
45
+ - `gradient_accumulation_steps`: 4
46
+ - `total_train_batch_size`: 64
47
+ - `optimizer`: Adam with `betas=(0.9,0.999)` and `epsilon=1e-08`
48
+ - `lr_scheduler_type`: linear
49
+ - `lr_scheduler_warmup_ratio`: 0.1
50
+ - `num_epochs`: 5
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
+ | :-----------: | :---: | :--: | :-------------: | :------: | :----: |
56
+ | 0.5509 | 1.0 | 191 | 0.3685 | 0.9086 | 0.9131 |
57
+ | 0.4543 | 2.0 | 382 | 0.3113 | 0.9247 | 0.9285 |
58
+ | 0.409 | 3.0 | 573 | 0.2723 | 0.9372 | 0.9418 |
59
+ | 0.3024 | 4.0 | 764 | 0.2786 | 0.9381 | 0.9417 |
60
+ | 0.3103 | 5.0 | 955 | 0.2571 | 0.9386 | 0.9425 |
61
+
62
+ ## Disclaimer
63
+
64
+ Do consider the biases which came from pre-training datasets that may be carried over into the results of this model.
65
+
66
+ ## Authors
67
 
68
+ DistilWav2Vec2 XLS-R Adult/Child Speech Classifier was trained and evaluated by [Ananto Joyoadikusumo](https://anantoj.github.io/). All computation and development are done on Kaggle.
69
 
70
+ ## Framework versions
71
 
72
  - Transformers 4.17.0.dev0
73
  - Pytorch 1.10.2+cu102
74
  - Datasets 1.18.3
75
+ - Tokenizers 0.11.0