metadata
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-accents
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: audiofolder
type: audiofolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.39097744360902253
distilhubert-finetuned-accents
This model is a fine-tuned version of ntu-spml/distilhubert on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.8429
- Accuracy: 0.3910
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: 0.7
- num_epochs: 14
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.5546 | 1.0 | 67 | 2.5463 | 0.1729 |
| 2.4756 | 2.0 | 134 | 2.4641 | 0.1654 |
| 2.3726 | 3.0 | 201 | 2.4065 | 0.2030 |
| 2.464 | 4.0 | 268 | 2.3753 | 0.2256 |
| 2.2215 | 5.0 | 335 | 2.3161 | 0.2481 |
| 2.346 | 6.0 | 402 | 2.2739 | 0.2556 |
| 1.8318 | 7.0 | 469 | 2.0260 | 0.3383 |
| 1.9612 | 8.0 | 536 | 1.8926 | 0.3684 |
| 1.7699 | 9.0 | 603 | 1.8646 | 0.3835 |
| 1.5864 | 10.0 | 670 | 2.0469 | 0.3083 |
| 1.5774 | 11.0 | 737 | 1.8156 | 0.3609 |
| 1.5087 | 12.0 | 804 | 1.8061 | 0.3609 |
| 1.2649 | 13.0 | 871 | 1.8970 | 0.3383 |
| 1.2179 | 14.0 | 938 | 1.8429 | 0.3910 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0