Downloads · 30 days
133
2% of all-time downloads
bookbot/distil-wav2vec2-adult-child-cls-52m
distil-wav2vec2-adult-child-cls-52m 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.
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 classi…
Downloads · 30 days
133
2% of all-time downloads
All-time downloads
7.1K
Public
Parameters
52M
833 MB on disk
Likes
0
Public
Click a slice to open those files.
.bin208 MB · 50%
From the Hugging Face model README
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 | #params | Arch. | Training/Validation data (text) |
|---|---|---|---|
distil-wav2vec2-adult-child-cls-52m | 52M | wav2vec 2.0 | Adult/Child Speech Classification Dataset |
The model achieves the following results on evaluation:
| Dataset | Loss | Accuracy | F1 |
|---|---|---|---|
| Adult/Child Speech Classification | 0.1301 | 96.03% | 0.9639 |
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 with betas=(0.9,0.999) and epsilon=1e-08lr_scheduler_type: linearlr_scheduler_warmup_ratio: 0.1num_epochs: 3| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.212 | 1.0 | 96 | 0.1561 | 0.9561 | 0.9596 |
| 0.1523 | 2.0 | 192 | 0.1408 | 0.9575 | 0.9616 |
| 0.0844 | 3.0 | 288 | 0.1301 | 0.9603 | 0.9639 |
Do consider the biases which came from pre-training datasets that may be carried over into the results of this model.
DistilWav2Vec2 Adult/Child Speech Classifier was trained and evaluated by Wilson Wongso. All computation and development are done on Kaggle.