whisper_small_saida

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.3761
• Wer: 22.5056

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-08
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 128
• total_train_batch_size: 1024
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 800

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.4732	30.45	800	4.3761	22.5056

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.1+cu121
• Datasets 2.12.0
• Tokenizers 0.14.1