jialicheng's picture
Upload folder using huggingface_hub
bd39069 verified
|
raw
history blame
2.27 kB
metadata
license: apache-2.0
base_model: openai/whisper-small
tags:
  - audio-classification
  - generated_from_trainer
datasets:
  - superb
metrics:
  - accuracy
model-index:
  - name: superb_ks_42
    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: 0.9848484848484849

superb_ks_42

This model is a fine-tuned version of openai/whisper-small on the superb dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0976
  • Accuracy: 0.9848

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: 5e-05
  • train_batch_size: 32
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.3599 1.0 1597 0.1546 0.9707
0.0819 2.0 3194 0.0998 0.9762
0.0635 3.0 4791 0.1049 0.9800
0.0437 4.0 6388 0.0905 0.9797
0.0411 5.0 7985 0.0898 0.9809
0.0283 6.0 9582 0.1006 0.9812
0.0229 7.0 11179 0.0976 0.9848
0.0186 8.0 12776 0.1143 0.9825
0.0094 9.0 14373 0.1136 0.9835
0.0066 10.0 15970 0.1172 0.9834

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1