README.md

metadata

language:
  - so
license: apache-2.0
base_model: steja/whisper-small-somali
tags:
  - generated_from_trainer
datasets:
  - google/fleurs
metrics:
  - wer
model-index:
  - name: Whisper Small So - kheder yusuf
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: google/fleurs
          type: google/fleurs
          config: so_so
          split: None
          args: 'config: so_so, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 21.001297668382936

Whisper Small So - kheder yusuf

This model is a fine-tuned version of steja/whisper-small-somali on the google/fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 0.2840
• Wer: 21.0013

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.257	3.47	1000	0.2840	21.0013

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.15.2