metadata

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: 0.9832303618711385

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: 0.0782
Accuracy: 0.9832

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: 32
eval_batch_size: 32
seed: 0
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5065	0.9994	399	0.3426	0.9713
0.2089	1.9987	798	0.1267	0.9781
0.1834	2.9981	1197	0.0889	0.9804
0.142	4.0	1597	0.0854	0.9813
0.1472	4.9969	1995	0.0782	0.9832

Framework versions

Transformers 4.42.0.dev0
Pytorch 2.3.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1