zuazo/whisper-large-v2-eu-cv22.0

openai/whisper-large-v2

This model is a fine-tuned version of openai/whisper-large-v2 on the common_voice_22_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2925
• Wer: 10.1655

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: 32
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 100000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0113	10.8234	5000	0.2195	9.4386
0.008	21.6457	10000	0.2475	10.0455
0.0049	32.4680	15000	0.2663	10.2737
0.0023	43.2904	20000	0.2671	9.6820
0.0019	54.1127	25000	0.2794	9.4809
0.0025	64.9361	30000	0.2925	10.1655

Framework versions

• Transformers 4.52.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1