Whisper Small Audio Emotion Classification

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• 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
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 4.4.2
• Tokenizers 0.22.1

--- library_name: transformers license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer datasets: - lucasvmigotto/audio-emotions-collection model-index: - name: Whisper Small - Audio Emotion Classifier results: [] --- <!-- 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. --> # Whisper Small - Audio Emotion Classifier This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Audio Emotions Collection dataset. It achieves the following results on the evaluation set: - Loss: 0.9543 ## 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: 5e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - 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 - lr_scheduler_warmup_steps: 500 - training_steps: 5000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 0.672 | 1.0 | 685 | 0.7548 | | 0.4456 | 2.0 | 1370 | 0.6081 | | 0.2742 | 3.0 | 2055 | 0.5351 | | 0.2174 | 4.0 | 2740 | 0.7506 | | 0.0612 | 5.0 | 3425 | 1.0163 | | 0.0661 | 6.0 | 4110 | 0.9165 | | 0.0276 | 7.0 | 4795 | 0.9554 | | 0.0007 | 7.2993 | 5000 | 0.9543 | ### Framework versions - Transformers 4.57.3 - Pytorch 2.9.0+cu126 - Datasets 4.4.2 - Tokenizers 0.22.1