Edit model card

wav2vec2-base-finetuned-ks

This model is a fine-tuned version of facebook/wav2vec2-base on the speech_commands dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0880
  • Accuracy: 0.9780

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • 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

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.6408 1.0 2651 0.2399 0.9609
0.4113 2.0 5303 0.1284 0.9686
0.3014 3.0 7954 0.1144 0.9706
0.2914 4.0 10606 0.0962 0.9760
0.1621 5.0 13255 0.0880 0.9780

Framework versions

  • Transformers 4.27.3
  • Pytorch 1.13.1+cu116
  • Datasets 2.10.1
  • Tokenizers 0.13.2
Downloads last month
2

Dataset used to train Dc26/wav2vec2-base-finetuned-ks