# Load model directly
from transformers import AutoProcessor, AutoModelForAudioClassification
processor = AutoProcessor.from_pretrained("jdmartinev/CREMA_D_Model")
model = AutoModelForAudioClassification.from_pretrained("jdmartinev/CREMA_D_Model")Quick Links
CREMA_D_Model
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8221
- Accuracy: 0.7322
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|
| 1.7381 | 0.99 | 37 | 1.6700 | 0.3359 |
| 1.4143 | 1.99 | 74 | 1.4013 | 0.4878 |
| 1.1738 | 2.98 | 111 | 1.1820 | 0.6029 |
| 1.0229 | 4.0 | 149 | 1.0244 | 0.6532 |
| 0.8688 | 4.99 | 186 | 0.9101 | 0.7036 |
| 0.7578 | 5.99 | 223 | 0.8787 | 0.7112 |
| 0.705 | 6.98 | 260 | 0.8292 | 0.7229 |
| 0.6469 | 8.0 | 298 | 0.8509 | 0.7179 |
| 0.5684 | 8.99 | 335 | 0.8412 | 0.7288 |
| 0.5611 | 9.93 | 370 | 0.8221 | 0.7322 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Downloads last month
- 10
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="jdmartinev/CREMA_D_Model")