Whisper Small Ar- Martha

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

• eval_loss: 2.6636
• eval_wer: 48.2981
• eval_runtime: 6533.5828
• eval_samples_per_second: 0.866
• eval_steps_per_second: 0.866
• epoch: 0.01
• step: 5

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: 500
• training_steps: 5655

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.13.0
• Tokenizers 0.13.3