metadata
library_name: transformers
tags:
- audio-classification
- generated_from_trainer
datasets:
- voxceleb
metrics:
- accuracy
model-index:
- name: etdnn-voxceleb1
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: confit/voxceleb
type: voxceleb
config: verification
split: train
args: verification
metrics:
- name: Accuracy
type: accuracy
value: 0.9340733266061217
etdnn-voxceleb1
This model is a fine-tuned version of on the confit/voxceleb dataset. It achieves the following results on the evaluation set:
- Loss: 0.3594
- Accuracy: 0.9341
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 256
- eval_batch_size: 1
- seed: 914
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.489 | 1.0 | 523 | 4.2089 | 0.1722 |
| 3.0685 | 2.0 | 1046 | 2.7621 | 0.4110 |
| 2.2892 | 3.0 | 1569 | 1.6627 | 0.6543 |
| 1.7576 | 4.0 | 2092 | 1.1761 | 0.7586 |
| 1.3706 | 5.0 | 2615 | 0.8903 | 0.8204 |
| 1.1258 | 6.0 | 3138 | 0.7555 | 0.8433 |
| 0.9379 | 7.0 | 3661 | 0.5587 | 0.8897 |
| 0.7925 | 8.0 | 4184 | 0.4518 | 0.9117 |
| 0.6733 | 9.0 | 4707 | 0.3889 | 0.9293 |
| 0.6187 | 10.0 | 5230 | 0.3594 | 0.9341 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.0.0+cu117
- Datasets 3.2.0
- Tokenizers 0.21.0