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: 0.2708333333333333
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: 2.0374
- Accuracy: 0.2708
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: 0.6
- num_epochs: 14
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.4741 | 1.0 | 48 | 2.4767 | 0.1042 |
| 2.4794 | 2.0 | 96 | 2.4594 | 0.1042 |
| 2.4795 | 3.0 | 144 | 2.4242 | 0.1042 |
| 2.3636 | 4.0 | 192 | 2.3929 | 0.1042 |
| 2.2958 | 5.0 | 240 | 2.3036 | 0.1667 |
| 2.2177 | 6.0 | 288 | 2.1868 | 0.1771 |
| 1.9929 | 7.0 | 336 | 2.0746 | 0.2396 |
| 1.9842 | 8.0 | 384 | 2.0638 | 0.2292 |
| 1.934 | 9.0 | 432 | 2.0566 | 0.2292 |
| 1.7302 | 10.0 | 480 | 2.1105 | 0.2083 |
| 1.6971 | 11.0 | 528 | 1.9927 | 0.2292 |
| 1.4807 | 12.0 | 576 | 2.0434 | 0.2396 |
| 1.3496 | 13.0 | 624 | 2.0579 | 0.2708 |
| 1.3694 | 14.0 | 672 | 2.0374 | 0.2708 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0