Wav2Vec2 XLS-R Adult/Child Indonesian Speech Classifier
Wav2Vec2 XLS-R Adult/Child Indonesian Speech Classifier is an audio classification model based on the XLS-R architecture. This model is a fine-tuned version of wav2vec2-xls-r-300m on a private adult/child Indonesian 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) |
---|---|---|---|
wav2vec2-xls-r-adult-child-id-cls |
300M | XLS-R | Adult/Child Indonesian Speech Classification Dataset |
Evaluation Results
The model achieves the following results on evaluation:
Dataset | Loss | Accuracy | F1 |
---|---|---|---|
Adult/Child Indonesian Speech Classification | 0.1970 | 93.38% | 0.9307 |
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate
: 3e-05train_batch_size
: 8eval_batch_size
: 8seed
: 42gradient_accumulation_steps
: 4total_train_batch_size
: 32optimizer
: Adam withbetas=(0.9,0.999)
andepsilon=1e-08
lr_scheduler_type
: linearlr_scheduler_warmup_ratio
: 0.1num_epochs
: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.336 | 1.0 | 305 | 0.3146 | 0.8845 | 0.8698 |
0.2345 | 2.0 | 610 | 0.2140 | 0.9251 | 0.9202 |
0.3215 | 3.0 | 915 | 0.2038 | 0.9315 | 0.9286 |
0.2059 | 4.0 | 1220 | 0.1970 | 0.9338 | 0.9307 |
Disclaimer
Do consider the biases which came from pre-training datasets that may be carried over into the results of this model.
Authors
Wav2Vec2 XLS-R Adult/Child Indonesian Speech Classifier was trained and evaluated by Ananto Joyoadikusumo. All computation and development are done on Kaggle.
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu102
- Datasets 2.2.0
- Tokenizers 0.12.1
- Downloads last month
- 10