README.md

metadata

language:
  - yo
license: apache-2.0
base_model: DereAbdulhameed/new_whisper_yoruba
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - OpenSLR
metrics:
  - wer
model-index:
  - name: Whisper Small Yoruba - Dere Abdulhameed
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 16.1 & SLR86
          type: OpenSLR
          config: yo
          split: None
          args: yo
        metrics:
          - name: Wer
            type: wer
            value: 33.08135740700457

Whisper Small Yoruba - Dere Abdulhameed

This model is a fine-tuned version of DereAbdulhameed/new_whisper_yoruba on the Common Voice 16.1 & SLR86 dataset. It achieves the following results on the evaluation set:

• Loss: 1.7726
• Wer: 33.0814

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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0001	17.01	1000	1.6166	33.3043
0.0001	35.01	2000	1.7029	32.9563
0.0	53.01	3000	1.7515	33.0868
0.0	71.01	4000	1.7726	33.0814

Framework versions

• Transformers 4.40.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2