metadata
license: apache-2.0
base_model: facebook/hubert-base-ls960
tags:
- generated_from_trainer
datasets:
- common_language
metrics:
- accuracy
model-index:
- name: hubert-base-ls960-finetuned-common_language-finetuned-common_language
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: Common Language
type: common_language
config: full
split: test
args: full
metrics:
- name: Accuracy
type: accuracy
value: 0.8011068254234446
hubert-base-ls960-finetuned-common_language-finetuned-common_language
This model is a fine-tuned version of facebook/hubert-base-ls960 on the Common Language dataset. It achieves the following results on the evaluation set:
- Loss: 1.4164
- Accuracy: 0.8011
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.9713 | 1.0 | 2774 | 3.0764 | 0.1615 |
| 1.7443 | 2.0 | 5549 | 1.8279 | 0.4734 |
| 1.1304 | 3.0 | 8323 | 1.3202 | 0.6371 |
| 1.2718 | 4.0 | 11098 | 1.1571 | 0.6968 |
| 0.769 | 5.0 | 13872 | 1.2917 | 0.7127 |
| 0.2656 | 6.0 | 16647 | 1.1549 | 0.7479 |
| 0.2939 | 7.0 | 19421 | 1.2372 | 0.7736 |
| 0.1278 | 8.0 | 22196 | 1.2985 | 0.7875 |
| 0.5175 | 9.0 | 24970 | 1.3664 | 0.7986 |
| 0.0547 | 10.0 | 27740 | 1.4164 | 0.8011 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3