adrianSauer/whisper-base-cer-extension

Common Voice 16 - Guarani

This model is a fine-tuned version of openai/whisper-base on the Common Voice 16 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4508
• Cer: 12.2672

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: 5e-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: constant_with_warmup
• lr_scheduler_warmup_steps: 3000
• training_steps: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
2.3843	0.4955	500	0.7760	20.1410
0.832	0.9911	1000	0.5657	16.6787
0.4694	1.4866	1500	0.5170	14.5543
0.3654	1.9822	2000	0.4646	12.7373
0.2036	2.4777	2500	0.4744	12.9181
0.1912	2.9732	3000	0.4508	12.2672

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1