Edit model card

sew-mid-100k-ft-keyword-spotting

This model is a fine-tuned version of asapp/sew-mid-100k on the superb dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0975
  • Accuracy: 0.9757

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: 0
  • 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: 5.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5999 1.0 399 0.2262 0.9635
0.4271 2.0 798 0.1230 0.9697
0.3778 3.0 1197 0.1052 0.9731
0.3227 4.0 1596 0.0975 0.9757
0.3081 5.0 1995 0.0962 0.9753

Framework versions

  • Transformers 4.12.0.dev0
  • Pytorch 1.9.1+cu111
  • Datasets 1.14.0
  • Tokenizers 0.10.3
Downloads last month
116

Dataset used to train anton-l/sew-mid-100k-ft-keyword-spotting