Fahd1199/MergeV2-FineTuned

Whisper Small Darija

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

• eval_loss: 0.7074
• eval_runtime: 57.1463
• eval_samples_per_second: 2.625
• eval_steps_per_second: 0.332
• epoch: 1.9324
• step: 800

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: 0.0001
• 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: cosine_with_restarts
• lr_scheduler_warmup_steps: 200
• num_epochs: 2
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.44.0
• Pytorch 2.2.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1