zuazo/whisper-tiny-eu-from-es

Whisper Tiny Basque

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

• Loss: 0.6730
• Wer: 32.5793

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: 3.75e-05
• train_batch_size: 256
• eval_batch_size: 128
• 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
0.0073	19.0	1000	0.6110	33.5352
0.001	38.0	2000	0.6730	32.5793
0.0005	57.01	3000	0.7140	32.7352
0.0003	76.01	4000	0.7406	32.9357
0.0003	96.0	5000	0.7481	33.0714

Framework versions

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