deepdml's picture
Update README.md
b29a4fa
|
Raw
History Blame Contribute Delete
2.29 kB
metadata
language:
  - ig
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - deepdml/igbo-dict-16khz
  - deepdml/igbo-dict-expansion-16khz
metrics:
  - wer
model-index:
  - name: Whisper Small ig
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: google/fleurs
          type: google/fleurs
          config: ig_ng
          split: test
        metrics:
          - name: Wer
            type: wer
            value: 46.10372101384145

Whisper Small ig

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

  • Loss: 1.5879
  • Wer: 46.1037

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: 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: 5000

Training results

Training Loss Epoch Step Validation Loss Wer
0.1171 0.2 1000 1.2732 44.9937
0.028 1.0814 2000 1.4495 46.2251
0.0277 1.2814 3000 1.4894 45.3892
0.0084 2.1628 4000 1.5629 44.6881
0.0065 3.0442 5000 1.5879 46.1037

Framework versions

  • Transformers 4.42.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1

Citation

@misc{deepdml/whisper-small-ig-mix,
      title={Fine-tuned Whisper small ASR model for speech recognition in Igbo},
      author={Jimenez, David},
      howpublished={\url{https://huggingface.co/deepdml/whisper-small-ig-mix}},
      year={2025}
    }