README.md

metadata

license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
datasets:
  - arrow
metrics:
  - accuracy
model-index:
  - name: eeem069_heart_murmur_classification
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: arrow
          type: arrow
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8221153846153846

eeem069_heart_murmur_classification

This model is a fine-tuned version of facebook/wav2vec2-base on the arrow dataset. It achieves the following results on the evaluation set:

• Loss: 0.5614
• Accuracy: 0.8221

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: 42
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0582	0.92	9	0.8806	0.8045
0.804	1.95	19	0.6482	0.8045
0.6425	2.97	29	0.6061	0.8045
0.6025	4.0	39	0.5924	0.8045
0.5865	4.92	48	0.5879	0.8045
0.6228	5.95	58	0.5834	0.8045
0.5676	6.97	68	0.5840	0.8045
0.5856	8.0	78	0.5890	0.8045
0.5946	8.92	87	0.5785	0.8045
0.586	9.95	97	0.5726	0.8045
0.5846	10.97	107	0.5723	0.8045
0.5545	12.0	117	0.5707	0.8237
0.5569	12.92	126	0.5846	0.8141
0.5997	13.95	136	0.5649	0.8173
0.5404	14.97	146	0.5625	0.8221
0.5438	16.0	156	0.5641	0.8189
0.5294	16.92	165	0.5633	0.8221
0.5196	17.95	175	0.5613	0.8205
0.5369	18.46	180	0.5614	0.8221

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2