Distilhubert Finetuned Babycry V6

🚀 distilhubert-finetuned-babycry-v6

This model is a fine - tuned version of ntu-spml/distilhubert on the audiofolder dataset, achieving high - performance results in audio classification.

🚀 Quick Start

This model is a fine - tuned version of ntu-spml/distilhubert on the audiofolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.6676
• Accuracy: {'accuracy': 0.8260869565217391}
• F1: 0.7474
• Precision: 0.6824
• Recall: 0.8261

📚 Documentation

Model Information

Model Index

• Name: distilhubert - finetuned - babycry - v6
• Results:
  • Task:
    • Name: Audio Classification
    • Type: audio - classification
  • Dataset:
    • Name: audiofolder
    • Type: audiofolder
    • Config: default
    • Split: train
    • Args: default
  • Metrics:
    • Name: Accuracy, Type: accuracy, Value: 0.8260869565217391
    • Name: F1, Type: f1, Value: 0.7474120082815735
    • Name: Precision, Type: precision, Value: 0.6824196597353497
    • Name: Recall, Type: recall, Value: 0.8260869565217391

Training Procedure

Training Hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9, 0.999) and epsilon = 1e - 08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 8

Training Results

Framework Versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1