zuazo/whisper-base-eu-from-es

Whisper Base Basque

This model is a fine-tuned version of zuazo/whisper-base-es on the mozilla-foundation/common_voice_13_0 eu dataset. It achieves the following results on the evaluation set:

• Loss: 0.5285
• Wer: 25.7524

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: 2.5e-05
• train_batch_size: 128
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0161	9.01	1000	0.4767	27.8403
0.0014	19.01	2000	0.5285	25.7524
0.0007	29.0	3000	0.5603	25.8739
0.0004	38.02	4000	0.5803	26.0885
0.0004	48.01	5000	0.5885	26.0885

Framework versions

• Transformers 4.33.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3