demoasr - aachaldhote001

This model is a fine-tuned version of openai/whisper-small on the Common Voice 13 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2696
• Wer: 34.5636
• Cer: 12.1204

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: 50
• training_steps: 1500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.2253	0.61	500	0.3108	38.8089	14.0629
0.1171	1.22	1000	0.2834	35.7488	12.8354
0.1164	1.83	1500	0.2696	34.5636	12.1204

Framework versions

• Transformers 4.40.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2