Edit model card

wa2vec2-5epochs

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

  • Loss: 0.3049
  • Accuracy: 0.9282

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: 4
  • 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
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 454 0.7179 0.7599
0.6962 2.0 908 0.3806 0.8911
0.3776 3.0 1362 0.3299 0.9109
0.2071 4.0 1816 0.3021 0.9257
0.1262 5.0 2270 0.3049 0.9282

Framework versions

  • Transformers 4.19.2
  • Pytorch 1.11.0+cu113
  • Datasets 2.2.3.dev0
  • Tokenizers 0.12.1
Downloads last month
2
Unable to determine this model’s pipeline type. Check the docs .