cantillation/whisper-medium-he-teamim-allNusah-13-03-24-warmup-100-RandomFalse

he

This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.7434
• eval_wer: 12.1548
• eval_avg_precision_Exact: 0.9045
• eval_avg_recall_Exact: 0.9047
• eval_avg_f1_Exact: 0.9042
• eval_avg_precision_Letter_Shift: 0.9263
• eval_avg_recall_Letter_Shift: 0.9265
• eval_avg_f1_Letter_Shift: 0.9260
• eval_avg_precision_Word_Level: 0.9288
• eval_avg_recall_Word_Level: 0.9291
• eval_avg_f1_Word_Level: 0.9285
• eval_avg_precision_Word_Shift: 0.9744
• eval_avg_recall_Word_Shift: 0.9757
• eval_avg_f1_Word_Shift: 0.9746
• eval_precision_median_exact: 1.0
• eval_recall_median_exact: 1.0
• eval_f1_median_exact: 1.0
• eval_precision_max_exact: 1.0
• eval_recall_max_exact: 1.0
• eval_f1_max_exact: 1.0
• eval_precision_min_Exact: 0.0
• eval_recall_min_Exact: 0.0
• eval_f1_min_Exact: 0.0
• eval_precision_min_Letter_Shift: 0.0
• eval_recall_min_Letter_Shift: 0.0
• eval_f1_min_Letter_Shift: 0.0
• eval_precision_min_Word_Level: 0.0
• eval_recall_min_Word_Level: 0.0
• eval_f1_min_Word_Level: 0.0
• eval_precision_min_Word_Shift: 0.0
• eval_recall_min_Word_Shift: 0.0
• eval_f1_min_Word_Shift: 0.0
• eval_runtime: 1534.2005
• eval_samples_per_second: 1.755
• eval_steps_per_second: 0.055
• step: 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
• 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: 100
• training_steps: 30000
• mixed_precision_training: Native AMP

Framework versions

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