violence-detect-44
This model is a fine-tuned version of facebook/wav2vec2-base-960h on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3533
- Accuracy: 0.8933
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6788 | 1.0 | 19 | 0.6183 | 0.6 |
| 0.6395 | 2.0 | 38 | 0.5397 | 0.8533 |
| 0.5565 | 3.0 | 57 | 0.4855 | 0.8667 |
| 0.5235 | 4.0 | 76 | 0.3962 | 0.9067 |
| 0.4561 | 5.0 | 95 | 0.3675 | 0.8933 |
| 0.4113 | 6.0 | 114 | 0.3872 | 0.8667 |
| 0.5303 | 7.0 | 133 | 0.3533 | 0.8933 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 38
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Hemg/violence-detect-44
Base model
facebook/wav2vec2-base-960h