README.md

metadata

license: apache-2.0
base_model: facebook/wav2vec2-base-960h
tags:
  - generated_from_trainer
datasets:
  - audiofolder
metrics:
  - accuracy
model-index:
  - name: audio_prosodic0.0.1
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: audiofolder
          type: audiofolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.3710377043710377

audio_prosodic0.0.1

This model is a fine-tuned version of facebook/wav2vec2-base-960h on the audiofolder dataset. It achieves the following results on the evaluation set:

• Loss: 1.0928
• Accuracy: 0.3710

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: 32
• 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	375	1.0940	0.3514
1.1294	2.0	750	1.0943	0.3710
1.0932	3.0	1125	1.0928	0.3710

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1