ahirtonlopes's picture
End of training
7142ea6
metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
datasets:
  - superb
metrics:
  - accuracy
model-index:
  - name: wav2vec2-base-finetuned-ks
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: superb
          type: superb
          config: ks
          split: validation
          args: ks
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9010002942041777

wav2vec2-base-finetuned-ks

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: 0.5155
  • Accuracy: 0.9010

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: 128
  • eval_batch_size: 128
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 512
  • 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
1.4701 1.0 100 1.4821 0.6209
1.1434 2.0 200 1.0657 0.6649
0.8086 3.0 300 0.7112 0.8320
0.659 4.0 400 0.5686 0.8789
0.5987 5.0 500 0.5155 0.9010

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3