Edit model card

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
Downloads last month
5
Safetensors
Model size
72.6M params
Tensor type
F32
·

Finetuned from

Dataset used to train iulik-pisik/busu_model_base

Evaluation results