zuazo/whisper-small-eu-from-es

Whisper Small Basque

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

• Loss: 0.4464
• Wer: 19.7639

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: 64
• eval_batch_size: 32
• 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
0.047	4.04	1000	0.3386	21.7425
0.0043	9.03	2000	0.3903	20.1770
0.0011	14.02	3000	0.4209	19.7801
0.0008	19.02	4000	0.4381	20.0170
0.0006	24.01	5000	0.4464	19.7639

Framework versions

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