Whisper-Base-Darija

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

• eval_loss: 2.0852
• eval_wer: 243.5823
• eval_runtime: 210.226
• eval_samples_per_second: 0.376
• eval_steps_per_second: 0.376
• epoch: 100.0
• step: 2000

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: 16
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 300
• training_steps: 3000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1