Potatoasdasdasdasda/whisper-base-es-improved

Whisper base Spanish Improved

This model is a fine-tuned version of openai/whisper-base on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2940
• Wer: 22.1706

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: 8
• 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: 8000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3981	0.12	1000	0.4923	28.2216
0.3628	0.25	2000	0.4366	25.6041
0.4008	0.38	3000	0.4076	24.6159
0.2844	0.5	4000	0.3698	27.3086
0.3651	0.62	5000	0.3469	21.5056
0.3037	0.75	6000	0.3244	20.3408
0.2162	0.88	7000	0.3053	24.8691
0.3015	1.0	8000	0.2940	22.1706

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1
• Datasets 2.15.0
• Tokenizers 0.15.0