wav2vec2-lg-xlsr-en-speech-emotion-recognition-finetuned-babycry-v1

This model is a fine-tuned version of ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition on the audiofolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.8444
• Accuracy: {'accuracy': 0.8043478260869565}
• F1: 0.7171
• Precision: 0.6470
• Recall: 0.8043

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: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.6556	0.9615	25	0.8356	{'accuracy': 0.8043478260869565}	0.7171	0.6470	0.8043
0.6427	1.9231	50	0.8207	{'accuracy': 0.8043478260869565}	0.7171	0.6470	0.8043
0.612	2.8846	75	0.8447	{'accuracy': 0.8043478260869565}	0.7171	0.6470	0.8043

Framework versions

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