iulik-pisik/vreme_model_tiny

Whisper Tiny Romanian - Vreme

This model is a fine-tuned version of openai/whisper-tiny on the Vreme ProTv dataset. It achieves the following results on the evaluation set:

• Loss: 0.2668
• Wer: 13.9129

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: 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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0494	6.02	1000	0.1717	14.1184
0.0033	12.05	2000	0.2362	14.3855
0.0011	18.07	3000	0.2596	13.9540
0.0008	24.1	4000	0.2668	13.9129

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2