metadata
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- narad/ravdess
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-ravdess
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: RAVDESS
type: narad/ravdess
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.8194444444444444
distilhubert-finetuned-ravdess
This model is a fine-tuned version of ntu-spml/distilhubert on the RAVDESS dataset. It achieves the following results on the evaluation set:
- Loss: 0.6720
- Accuracy: 0.8194
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.795 | 1.0 | 162 | 1.8129 | 0.25 |
| 1.1416 | 2.0 | 324 | 1.2499 | 0.5278 |
| 1.1677 | 3.0 | 486 | 0.9141 | 0.6875 |
| 0.5474 | 4.0 | 648 | 0.7662 | 0.75 |
| 0.4129 | 5.0 | 810 | 0.6744 | 0.7569 |
| 0.2396 | 6.0 | 972 | 0.6781 | 0.7986 |
| 0.0626 | 7.0 | 1134 | 0.7809 | 0.75 |
| 0.1198 | 8.0 | 1296 | 0.6404 | 0.8194 |
| 0.0187 | 9.0 | 1458 | 0.6750 | 0.8264 |
| 0.012 | 10.0 | 1620 | 0.6720 | 0.8194 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1
- Datasets 2.19.1
- Tokenizers 0.19.1