Edit model card

wav2vec2-base-finetuned-ks-balanced2

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

  • Loss: 1.6199
  • Accuracy: 0.4860

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: 64
  • eval_batch_size: 64
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • 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
1.4624 0.99 79 1.8039 0.4685
0.8255 1.99 159 1.6513 0.4843
0.6409 3.0 239 1.6199 0.4860
0.5099 4.0 319 1.6686 0.4790
0.4903 4.95 395 1.7152 0.4682

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.13.3
Downloads last month
11
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for selinawisco/wav2vec2-base-finetuned-ks-balanced2

Finetuned
(632)
this model

Dataset used to train selinawisco/wav2vec2-base-finetuned-ks-balanced2

Evaluation results