README.md

metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - sitwala/whisper-small-lwazi-pitori
metrics:
  - wer
model-index:
  - name: Whisper whisper-small lwazi multilingual
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Lwazi_asr_multilingual
          type: sitwala/whisper-small-lwazi-pitori
          args: 'split: test'
        metrics:
          - name: Wer
            type: wer
            value: 170.73170731707316

Whisper whisper-small lwazi multilingual

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

• Loss: 2.6640
• Wer Ortho: 117.0732
• Wer: 170.7317

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: 64
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 150
• training_steps: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
2.4105	50.0	50	2.6640	117.0732	170.7317

Framework versions

• Transformers 4.52.0
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.4