DistilWav2Vec2 Adult/Child Speech Classifier 37M
DistilWav2Vec2 Adult/Child Speech Classifier is an audio classification model based on the wav2vec 2.0 architecture. This model is a distilled version of wav2vec2-adult-child-cls on a private adult/child speech classification dataset.
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.
Model
Model | #params | Arch. | Training/Validation data (text) |
---|---|---|---|
distil-wav2vec2-adult-child-cls-37m |
37M | wav2vec 2.0 | Adult/Child Speech Classification Dataset |
Evaluation Results
The model achieves the following results on evaluation:
Dataset | Loss | Accuracy | F1 |
---|---|---|---|
Adult/Child Speech Classification | 0.1431 | 95.89% | 0.9624 |
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate
: 3e-05train_batch_size
: 32eval_batch_size
: 32seed
: 42gradient_accumulation_steps
: 4total_train_batch_size
: 128optimizer
: Adam withbetas=(0.9,0.999)
andepsilon=1e-08
lr_scheduler_type
: linearlr_scheduler_warmup_ratio
: 0.1num_epochs
: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.2586 | 1.0 | 96 | 0.2257 | 0.9298 | 0.9363 |
0.1917 | 2.0 | 192 | 0.1743 | 0.9460 | 0.9500 |
0.1568 | 3.0 | 288 | 0.1701 | 0.9511 | 0.9545 |
0.0965 | 4.0 | 384 | 0.1501 | 0.9548 | 0.9584 |
0.1179 | 5.0 | 480 | 0.1431 | 0.9589 | 0.9624 |
Disclaimer
Do consider the biases which came from pre-training datasets that may be carried over into the results of this model.
Authors
DistilWav2Vec2 Adult/Child Speech Classifier was trained and evaluated by Ananto Joyoadikusumo. All computation and development are done on Kaggle.
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.2+cu102
- Datasets 1.18.3
- Tokenizers 0.10.3
- Downloads last month
- 15