metadata
license: bsd-3-clause
base_model: MIT/ast-finetuned-audioset-10-10-0.4593
tags:
- generated_from_trainer
metrics:
- accuracy
- wer
model-index:
- name: ast-finetuned-audioset-10-10-0.4593-keyword_spotting2
results: []
ast-finetuned-audioset-10-10-0.4593-keyword_spotting2
This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0123
- Accuracy: 0.8228
- Wer: 0.1772
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: 3e-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
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Wer |
|---|---|---|---|---|---|
| 0.0008 | 1.0 | 28 | 1.3229 | 0.8228 | 0.1772 |
| 0.3356 | 2.0 | 56 | 1.3607 | 0.8228 | 0.1772 |
| 0.0035 | 3.0 | 84 | 1.0123 | 0.8228 | 0.1772 |
| 0.0051 | 4.0 | 112 | 1.5980 | 0.8228 | 0.1772 |
| 0.0001 | 5.0 | 140 | 1.4630 | 0.8228 | 0.1772 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.7.dev0
- Tokenizers 0.14.1