wav2vec2-base-finetuned-stop-classification-5
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: 0.1860
- Accuracy: 0.9326
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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 |
---|---|---|---|---|
0.6912 | 0.99 | 18 | 0.6572 | 0.6887 |
0.6092 | 1.97 | 36 | 0.5213 | 0.7636 |
0.4822 | 2.96 | 54 | 0.3353 | 0.8883 |
0.3866 | 4.0 | 73 | 0.2711 | 0.8978 |
0.3293 | 4.99 | 91 | 0.2208 | 0.9230 |
0.3004 | 5.97 | 109 | 0.2206 | 0.9237 |
0.2799 | 6.96 | 127 | 0.2097 | 0.9223 |
0.2688 | 8.0 | 146 | 0.1853 | 0.9305 |
0.2333 | 8.99 | 164 | 0.1850 | 0.9305 |
0.2461 | 9.86 | 180 | 0.1860 | 0.9326 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.0
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 0
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.