cantillation/Teamim-IvritAI-large-v3-turbo_WeightDecay-0.005_Augmented_WithSRT_date-15-04-2025

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

he-cantillation

This model is a fine-tuned version of ivrit-ai/whisper-large-v3-turbo on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 0.4220
• —Wer: 35.5610
• —Avg Precision Exact: 0.4895
• —Avg Recall Exact: 0.5009
• —Avg F1 Exact: 0.4943
• —Avg Precision Letter Shift: 0.5105
• —Avg Recall Letter Shift: 0.5234
• —Avg F1 Letter Shift: 0.5157
• —Avg Precision Word Level: 0.5228
• —Avg Recall Word Level: 0.5364
• —Avg F1 Word Level: 0.5279
• —Avg Precision Word Shift: 0.6946
• —Avg Recall Word Shift: 0.7228
• —Avg F1 Word Shift: 0.7055
• —Precision Median Exact: 0.4524
• —Recall Median Exact: 0.4833
• —F1 Median Exact: 0.4706
• —Precision Max Exact: 1.0
• —Recall Max Exact: 1.0
• —F1 Max Exact: 1.0
• —Precision Min Exact: 0.0
• —Recall Min Exact: 0.0
• —F1 Min Exact: 0.0
• —Precision Min Letter Shift: 0.0
• —Recall Min Letter Shift: 0.0
• —F1 Min Letter Shift: 0.0
• —Precision Min Word Level: 0.0
• —Recall Min Word Level: 0.0
• —F1 Min Word Level: 0.0
• —Precision Min Word Shift: 0.0
• —Recall Min Word Shift: 0.0
• —F1 Min Word Shift: 0.0

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
• —trainbatchsize: 16
• —evalbatchsize: 2
• —seed: 42
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 1000
• —training_steps: 60000
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.49.0
• —Pytorch 2.6.0+cu126
• —Datasets 2.12.0
• —Tokenizers 0.20.1