whisper_final1

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

• Loss: 0.9131
• Wer: 72.0667

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: 8
• 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: 200
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0014	0.8772	100	0.9335	72.4138
0.0096	1.7544	200	0.9558	72.6937
0.0075	2.6316	300	0.9131	72.0667

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1