whisper-base-ig-mix / README.md
deepdml's picture
Update README.md
fd8efe7 verified
metadata
language:
  - ig
license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
datasets:
  - deepdml/igbo-dict-16khz
  - deepdml/igbo-dict-expansion-16khz
metrics:
  - wer
model-index:
  - name: Whisper Base 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: 93.38037030379292

Whisper Base ig

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

  • Loss: 1.7179
  • Wer: 93.3804

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
0.2396 0.2 1000 1.3704 57.7791
0.0803 1.0814 2000 1.5414 71.3104
0.0636 1.2814 3000 1.6047 94.5668
0.0346 2.1628 4000 1.6904 83.7003
0.035 3.0442 5000 1.7179 93.3804

Framework versions

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

Citation

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