whisper-small-bem2en-new

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

• Loss: 1.4084
• Wer: 66.4841

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.523	1.0	5323	1.4905	71.5167
1.1015	2.0	10646	1.3532	67.0779
0.607	2.9995	15966	1.4084	66.4841

Framework versions

• Transformers 4.51.3
• Pytorch 2.1.0+cu118
• Datasets 3.5.0
• Tokenizers 0.21.1