whisper-nm-nor

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: 0.0663
• Wer: 2.7237

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
• 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_steps: 132
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	5.5714	100	0.7192	5.0584
1.5787	11.1143	200	0.0608	2.7237
1.5787	16.6857	300	0.0601	2.7237
0.002	22.2286	400	0.0627	2.7237
0.002	27.8	500	0.0642	2.7237
0.0	33.3429	600	0.0653	2.7237
0.0	38.9143	700	0.0659	2.7237
0.0	44.4571	800	0.0663	2.7237

Framework versions

• Transformers 4.47.0.dev0
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0