sumukhshadakshari/whisper-finetuned-cv-en

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

• Loss: 1.4536
• Wer: 31.4687

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.6045	1.0	121	2.1470	33.3727
1.6307	2.0	242	1.7560	30.4642
1.2067	3.0	363	1.4536	31.4687

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.1
• Datasets 2.21.0
• Tokenizers 0.20.1