README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - tobiolatunji/afrispeech-200
model-index:
  - name: Whisper Small En - Owos
    results: []

Whisper Small En - Owos

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

• eval_loss: 0.6865
• eval_wer: 29.3845
• eval_runtime: 1774.5798
• eval_samples_per_second: 1.691
• eval_steps_per_second: 0.211
• epoch: 0.06
• step: 250

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: 8
• 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

Framework versions

• Transformers 4.27.0
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3