Edit model card

wavlm-both

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

  • Loss: 0.7733
  • Accuracy: 0.8829

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: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • 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
1.0804 1.0 13 0.9762 0.7428
0.9797 2.0 26 0.8233 0.8816
0.8876 3.0 39 0.7733 0.8829

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
1
Safetensors
Model size
94.6M params
Tensor type
F32
·

Finetuned from