<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
wav2vec2-base-finetuned-stop-classification
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: 0.1647
- Accuracy: 0.9470
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.671 | 0.98 | 26 | 0.5553 | 0.8347 |
| 0.3525 | 1.98 | 52 | 0.2647 | 0.9163 |
| 0.291 | 2.98 | 78 | 0.2474 | 0.9070 |
| 0.2733 | 3.98 | 104 | 0.1729 | 0.9439 |
| 0.2467 | 4.98 | 130 | 0.1647 | 0.9470 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0
- Datasets 2.7.1
- Tokenizers 0.13.2
