wav2vec2-lg-xlsr-en-speech-emotion-recognition-finetuned-babycry-v2

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: 0.8522
• 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: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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
0.6078	0.4854	25	0.8682	{'accuracy': 0.8043478260869565}	0.7171	0.6470	0.8043
0.7269	0.9709	50	0.8559	{'accuracy': 0.8043478260869565}	0.7171	0.6470	0.8043
0.6815	1.4563	75	0.8204	{'accuracy': 0.8043478260869565}	0.7171	0.6470	0.8043
0.6144	1.9417	100	0.8417	{'accuracy': 0.8043478260869565}	0.7171	0.6470	0.8043
0.6246	2.4272	125	0.8454	{'accuracy': 0.8043478260869565}	0.7171	0.6470	0.8043
0.5687	2.9126	150	0.8527	{'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