eng_Emp_reco

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0001
• Accuracy: {'accuracy': 1.0}
• F1score: {'f1': 1.0}

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1score
0.0254	1.0	320	0.0106	{'accuracy': 0.9984375}	{'f1': 0.9984376713627683}
0.002	2.0	640	0.0013	{'accuracy': 1.0}	{'f1': 1.0}
0.0019	3.0	960	0.0006	{'accuracy': 1.0}	{'f1': 1.0}
0.0019	4.0	1280	0.0004	{'accuracy': 1.0}	{'f1': 1.0}
0.0003	5.0	1600	0.0063	{'accuracy': 0.9984375}	{'f1': 0.9984376713627683}
0.0003	6.0	1920	0.0002	{'accuracy': 1.0}	{'f1': 1.0}
0.0003	7.0	2240	0.0001	{'accuracy': 1.0}	{'f1': 1.0}
0.0002	8.0	2560	0.0001	{'accuracy': 1.0}	{'f1': 1.0}
0.0002	9.0	2880	0.0001	{'accuracy': 1.0}	{'f1': 1.0}
0.0002	10.0	3200	0.0001	{'accuracy': 1.0}	{'f1': 1.0}

Framework versions

• Transformers 4.18.0
• Pytorch 1.11.0
• Datasets 2.1.0
• Tokenizers 0.12.1