metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- minds14
metrics:
- accuracy
model-index:
- name: wav2vec2-base-finetuned-minds-1
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: minds14
type: minds14
config: en-US
split: train
args: en-US
metrics:
- name: Accuracy
type: accuracy
value: 0.7610619469026548
wav2vec2-base-finetuned-minds-1
This model is a fine-tuned version of facebook/wav2vec2-base on the minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 1.4208
- Accuracy: 0.7611
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 |
|---|---|---|---|---|
| 2.6059 | 1.0 | 57 | 2.5954 | 0.0973 |
| 2.5183 | 2.0 | 114 | 2.5787 | 0.0973 |
| 2.5497 | 3.0 | 171 | 2.5629 | 0.1416 |
| 2.3827 | 4.0 | 228 | 2.5407 | 0.1858 |
| 2.309 | 5.0 | 285 | 2.3023 | 0.2301 |
| 2.0098 | 6.0 | 342 | 2.0528 | 0.3540 |
| 1.797 | 7.0 | 399 | 1.8558 | 0.4602 |
| 1.4416 | 8.0 | 456 | 1.6847 | 0.5841 |
| 1.3491 | 9.0 | 513 | 1.4911 | 0.6991 |
| 1.3468 | 10.0 | 570 | 1.4208 | 0.7611 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2