Whisper Small WO - Team

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

• eval_loss: 0.2271
• eval_wer: 66.4499
• eval_runtime: 2330.8657
• eval_samples_per_second: 1.114
• eval_steps_per_second: 0.139
• epoch: 4.6225
• step: 3000

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-06
• train_batch_size: 16
• 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

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0