# Load model directly
from transformers import AutoProcessor, AutoModelForAudioClassification
processor = AutoProcessor.from_pretrained("heado/audio_cls_hhd2")
model = AutoModelForAudioClassification.from_pretrained("heado/audio_cls_hhd2")Quick Links
audio_cls_hhd2
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4219
- Accuracy: 0.9244
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 15 | 0.8368 | 0.8235 |
| No log | 2.0 | 30 | 0.6420 | 0.8655 |
| No log | 3.0 | 45 | 0.5034 | 0.9076 |
| No log | 4.0 | 60 | 0.4384 | 0.9076 |
| No log | 5.0 | 75 | 0.4219 | 0.9244 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 5
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="heado/audio_cls_hhd2")