iulik-pisik/busu_model_base

Whisper Base Romanian - Vreme Florin Busuioc

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

• Loss: 0.2614
• Wer: 13.2066

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
0.0152	7.63	1000	0.1949	13.7015
0.0008	15.27	2000	0.2461	13.1545
0.0005	22.9	3000	0.2565	13.1024
0.0003	30.53	4000	0.2614	13.2066

Framework versions

• Transformers 4.39.1
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2