Edit model card

ser_model_fixed_label

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

  • Loss: 0.7010
  • Accuracy: 0.8367

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: 3e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.7645 0.96 18 1.5899 0.4333
1.5148 1.96 36 1.4152 0.4433
1.3042 2.96 54 1.1857 0.5767
1.1184 3.96 72 1.0508 0.62
0.9588 4.96 90 0.9329 0.7
0.9789 5.96 108 0.8638 0.74
0.7835 6.96 126 0.7730 0.8133
0.7259 7.96 144 0.7355 0.83
0.6783 8.96 162 0.7190 0.8333
0.6644 9.96 180 0.7010 0.8367

Framework versions

  • Transformers 4.25.1
  • Pytorch 1.12.1
  • Datasets 2.7.1
  • Tokenizers 0.13.2
Downloads last month
58

Spaces using aherzberg/ser_model_fixed_label 5