metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
model-index:
- name: audio-voilence-detection-vii
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: 0.6
audio-voilence-detection-vii
This model is a fine-tuned version of facebook/wav2vec2-base on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6731
- Accuracy: 0.6
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6671 | 0.95 | 9 | 0.4106 | 0.8933 |
| 0.674 | 2.0 | 19 | 0.6732 | 0.6 |
| 0.7163 | 2.95 | 28 | 0.6747 | 0.6 |
| 0.6465 | 4.0 | 38 | 0.6730 | 0.6 |
| 0.7088 | 4.95 | 47 | 0.6730 | 0.6 |
| 0.6445 | 6.0 | 57 | 0.6730 | 0.6 |
| 0.7132 | 6.95 | 66 | 0.6731 | 0.6 |
| 0.6201 | 7.58 | 72 | 0.6731 | 0.6 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2