whisper-small-ro-finetuned

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

• Loss: 0.2681
• Wer: 24.5531

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: 8
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 100
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.8226	0.3086	100	0.8870	32.4815
0.2026	0.6173	200	0.3149	27.9333
0.1947	0.9259	300	0.2813	25.4876
0.0664	1.2346	400	0.2714	24.7018
0.0772	1.5432	500	0.2681	24.5531

Framework versions

• Transformers 4.53.2
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.2