cantillation/Teamim-AllNusah-whisper-medium_Warmup_steps-1000_LR-1e-05_Random-True

<!-- 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-medium on an unknown dataset. It achieves the following results on the evaluation set:

• —eval_loss: 0.1666
• —eval_wer: 10.9128
• —evalavgprecision_Exact: 0.9184
• —evalavgrecall_Exact: 0.9197
• —evalavgf1_Exact: 0.9188
• —evalavgprecisionLetterShift: 0.9365
• —evalavgrecallLetterShift: 0.9379
• —evalavgf1LetterShift: 0.9369
• —evalavgprecisionWordLevel: 0.9382
• —evalavgrecallWordLevel: 0.9395
• —evalavgf1WordLevel: 0.9385
• —evalavgprecisionWordShift: 0.9779
• —evalavgrecallWordShift: 0.9797
• —evalavgf1WordShift: 0.9784
• —evalprecisionmedian_exact: 1.0
• —evalrecallmedian_exact: 1.0
• —evalf1median_exact: 1.0
• —evalprecisionmax_exact: 1.0
• —evalrecallmax_exact: 1.0
• —evalf1max_exact: 1.0
• —evalprecisionmin_Exact: 0.0
• —evalrecallmin_Exact: 0.0
• —evalf1min_Exact: 0.0
• —evalprecisionminLetterShift: 0.0
• —evalrecallminLetterShift: 0.0
• —evalf1minLetterShift: 0.0
• —evalprecisionminWordLevel: 0.0
• —evalrecallminWordLevel: 0.0
• —evalf1minWordLevel: 0.0
• —evalprecisionminWordShift: 0.1429
• —evalrecallminWordShift: 0.1111
• —evalf1minWordShift: 0.125
• —eval_runtime: 1554.5785
• —evalsamplesper_second: 1.732
• —evalstepsper_second: 0.055
• —epoch: 4.0
• —step: 50000

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: 50000
• —mixedprecisiontraining: Native AMP

Framework versions

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