Downloads · 30 days
16
2% of all-time downloads
bookbot/wav2vec2-xls-r-adult-child-id-cls
wav2vec2-xls-r-adult-child-id-cls is a audio classification model from bookbot. Use it for the audio classification task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
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 s…
Downloads · 30 days
16
2% of all-time downloads
All-time downloads
754
Public
Parameters
316M
6.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.bin1.3 GB · 50%
From the Hugging Face model README
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 | #params | Arch. | Training/Validation data (text) |
|---|---|---|---|
wav2vec2-xls-r-adult-child-id-cls | 300M | XLS-R | Adult/Child Indonesian Speech Classification Dataset |
The model achieves the following results on evaluation:
| Dataset | Loss | Accuracy | F1 |
|---|---|---|---|
| Adult/Child Indonesian Speech Classification | 0.1970 | 93.38% | 0.9307 |
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 with betas=(0.9,0.999) and epsilon=1e-08lr_scheduler_type: linearlr_scheduler_warmup_ratio: 0.1num_epochs: 4| 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 |
Do consider the biases which came from pre-training datasets that may be carried over into the results of this model.
Wav2Vec2 XLS-R Adult/Child Indonesian Speech Classifier was trained and evaluated by Ananto Joyoadikusumo. All computation and development are done on Kaggle.