Teamim-small_WeightDecay-0.05_Augmented_Combined-Data_date-11-07-2024_12-42

<!-- 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 openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1474
• Wer: 9.8084
• Avg Precision Exact: 0.9128
• Avg Recall Exact: 0.9142
• Avg F1 Exact: 0.9131
• Avg Precision Letter Shift: 0.9270
• Avg Recall Letter Shift: 0.9286
• Avg F1 Letter Shift: 0.9274
• Avg Precision Word Level: 0.9292
• Avg Recall Word Level: 0.9309
• Avg F1 Word Level: 0.9297
• Avg Precision Word Shift: 0.9711
• Avg Recall Word Shift: 0.9735
• Avg F1 Word Shift: 0.9719
• Precision Median Exact: 1.0
• Recall Median Exact: 1.0
• F1 Median Exact: 1.0
• 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: 0.1429
• Recall Min Word Shift: 0.125
• F1 Min Word Shift: 0.1333

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: 32
• 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: 200000
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.41.2
• Pytorch 2.2.1
• Datasets 2.20.0
• Tokenizers 0.19.1