metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- minds14
metrics:
- accuracy
model-index:
- name: audio_classification_example
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: 0.07079646017699115
audio_classification_example
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: 2.6501
- Accuracy: 0.0708
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 2.6446 | 0.99 | 28 | 2.6533 | 0.0708 |
| 2.6501 | 1.98 | 56 | 2.6360 | 0.0442 |
| 2.6415 | 2.97 | 84 | 2.6452 | 0.0708 |
| 2.6469 | 4.0 | 113 | 2.6508 | 0.0708 |
| 2.6372 | 4.99 | 141 | 2.6463 | 0.0708 |
| 2.6364 | 5.98 | 169 | 2.6467 | 0.0708 |
| 2.6279 | 6.97 | 197 | 2.6497 | 0.0708 |
| 2.6331 | 8.0 | 226 | 2.6510 | 0.0708 |
| 2.6312 | 8.99 | 254 | 2.6504 | 0.0708 |
| 2.6214 | 9.91 | 280 | 2.6501 | 0.0708 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0