whisper-large-v2-basque

This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2262
• Wer: 13.5490

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: 256
• eval_batch_size: 32
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 512
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1893	0.42	500	0.3062	21.7477
0.1486	0.84	1000	0.2539	17.3600
0.1156	1.26	1500	0.2362	15.0533
0.1098	1.68	2000	0.2244	14.3350
0.0831	2.1	2500	0.2195	13.8835
0.0831	2.52	3000	0.2164	13.6967
0.0814	2.94	3500	0.2141	13.3950
0.0623	3.36	4000	0.2209	13.4361
0.0616	3.78	4500	0.2189	13.2309
0.0503	4.2	5000	0.2262	13.5490

Framework versions

• Transformers 4.38.0
• Pytorch 2.1.1+cu121
• Datasets 2.8.0
• Tokenizers 0.15.2