cantillation/Teamim-AllNusah-whisper-small_Random-True_Mid

<!-- 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: 0.1845
• —Wer: 12.0473
• —Avg Precision Exact: 0.9003
• —Avg Recall Exact: 0.8996
• —Avg F1 Exact: 0.8996
• —Avg Precision Letter Shift: 0.9202
• —Avg Recall Letter Shift: 0.9196
• —Avg F1 Letter Shift: 0.9195
• —Avg Precision Word Level: 0.9230
• —Avg Recall Word Level: 0.9222
• —Avg F1 Word Level: 0.9223
• —Avg Precision Word Shift: 0.9761
• —Avg Recall Word Shift: 0.9759
• —Avg F1 Word Shift: 0.9756
• —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: 0.0909
• —Recall Min Word Shift: 0.125
• —F1 Min Word Shift: 0.1053

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: 8
• —evalbatchsize: 32
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 1000
• —training_steps: 100000
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.39.0.dev0
• —Pytorch 2.2.1+cu121
• —Datasets 2.16.1
• —Tokenizers 0.15.0