whisper

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

• Loss: 3.9871
• Wer: 83.6108

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: 64
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.965	0.1408	10	3.9871	83.6108

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.1.dev0
• Tokenizers 0.19.1