README.md

metadata

library_name: transformers
language:
  - wo
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - IndabaxSenegal/asr-wolof-dataset
metrics:
  - wer
model-index:
  - name: Whisper small Wolof
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: ASR Wolof Dataset
          type: IndabaxSenegal/asr-wolof-dataset
          args: 'config: wo, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 51.21087255114581

Whisper small Wolof

This model is a fine-tuned version of openai/whisper-small on the ASR Wolof Dataset dataset. It achieves the following results on the evaluation set:

• Loss: 1.1760
• Wer: 51.2109

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0367	1.0	450	1.1685	50.4807
0.0191	2.0	900	1.1760	51.2109

Framework versions

• Transformers 4.46.3
• Pytorch 2.4.0
• Datasets 3.1.0
• Tokenizers 0.20.0