Zheng Li
End of training
3602a49 verified
|
raw
history blame
2.38 kB
metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - audio-classification
  - generated_from_trainer
datasets:
  - superb
metrics:
  - accuracy
model-index:
  - name: wav2vec2-base-ft-keyword-spotting
    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: 0.9763165636952045

wav2vec2-base-ft-keyword-spotting

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: 0.4062
  • Accuracy: 0.9763

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: 1e-05
  • train_batch_size: 64
  • eval_batch_size: 32
  • seed: 0
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 8.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.8801 0.9962 199 1.7454 0.6209
1.389 1.9962 398 1.2404 0.6518
1.1239 2.9962 597 1.0690 0.7880
0.9107 3.9962 796 0.7700 0.8961
0.7231 4.9962 995 0.6167 0.9659
0.5972 5.9962 1194 0.4838 0.9735
0.5143 6.9962 1393 0.4227 0.9762
0.5159 7.9962 1592 0.4062 0.9763

Framework versions

  • Transformers 4.49.0
  • Pytorch 2.6.0+cu118
  • Datasets 3.3.1
  • Tokenizers 0.21.0