# Load model directly
from transformers import AutoProcessor, AutoModelForAudioClassification
processor = AutoProcessor.from_pretrained("Kibalama/urban_sounds_classification_Model")
model = AutoModelForAudioClassification.from_pretrained("Kibalama/urban_sounds_classification_Model")Quick Links
urban_sounds_classification_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: 0.7128
- Accuracy: 0.8019
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4464 | 1.0 | 55 | 1.4501 | 0.5965 |
| 1.1235 | 2.0 | 110 | 1.2883 | 0.6285 |
| 1.0447 | 3.0 | 165 | 1.1324 | 0.6691 |
| 0.768 | 4.0 | 220 | 1.0824 | 0.6651 |
| 0.7529 | 5.0 | 275 | 0.9645 | 0.7172 |
| 0.6759 | 6.0 | 330 | 0.9236 | 0.7355 |
| 0.5837 | 7.0 | 385 | 0.7909 | 0.7653 |
| 0.5465 | 8.0 | 440 | 0.7330 | 0.7922 |
| 0.5112 | 9.0 | 495 | 0.7152 | 0.7997 |
| 0.4747 | 10.0 | 550 | 0.7128 | 0.8019 |
Framework versions
- Transformers 4.53.0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2
- Downloads last month
- 22
Model tree for Kibalama/urban_sounds_classification_Model
Base model
facebook/wav2vec2-base
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="Kibalama/urban_sounds_classification_Model")