README.md

metadata

language:
  - 'no'
  - nb
license: apache-2.0
library_name: transformers
tags:
  - generated_from_trainer
datasets:
  - coscan-speech2
metrics:
  - accuracy
pipeline_tag: audio-classification
base_model: facebook/wav2vec2-base
model-index:
  - name: wav2vec2-base-coscan-no-age_group
    results:
      - task:
          type: audio-classification
          name: Audio Classification
        dataset:
          name: Coscan Speech
          type: NbAiLab/coscan-speech
        metrics:
          - type: accuracy
            value: 0.6618436706215234
            name: Test Accuracy
          - type: accuracy
            value: 0.7624056323691577
            name: Validation Accuracy

wav2vec2-base-coscan-no-age_group

This model is a fine-tuned version of facebook/wav2vec2-base on the coscan-speech2 dataset. It achieves the following results on the evaluation set:

• Loss: 1.5582
• Accuracy: 0.7624

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: 16
• eval_batch_size: 16
• 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0082	1.0	6468	1.5582	0.7624

Framework versions

• Transformers 4.22.0.dev0
• Pytorch 1.10.1+cu102
• Datasets 2.4.1.dev0
• Tokenizers 0.12.1