README.md

metadata

base_model: microsoft/wavlm-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: 0.9694027655192704

wav2vec2-base-ft-keyword-spotting

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

• Loss: 0.2270
• Accuracy: 0.9694

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: 0
• 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: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3203	1.0	199	1.2906	0.6328
0.9587	2.0	399	0.7793	0.7355
0.6218	3.0	599	0.3858	0.9289
0.4379	4.0	799	0.2581	0.9688
0.3779	4.98	995	0.2270	0.9694

Framework versions

• Transformers 4.34.0.dev0
• Pytorch 2.0.0.post302
• Datasets 2.14.5
• Tokenizers 0.13.3