README.md

metadata

language:
  - ha
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - Seon25/common_voice_16_0_
metrics:
  - wer
model-index:
  - name: Whisper Small Ha adam_w v4 - Eldad Akhaumere
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 16.0
          type: Seon25/common_voice_16_0_
          config: ha
          split: None
          args: 'config: ha, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 78.86568308105001

Whisper Small Ha adam_w v4 - Eldad Akhaumere

This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:

• Loss: 2.2150
• Wer Ortho: 81.0547
• Wer: 78.8657

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• num_epochs: 15.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0995	3.1847	500	1.7910	90.4297	88.1778
0.0468	6.3694	1000	1.9594	82.8320	81.1458
0.0394	9.5541	1500	2.0776	89.8438	87.7563
0.0314	12.7389	2000	2.2150	81.0547	78.8657

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1