Whisper Small for Quran Recognition

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

  • Loss: 0.0275
  • Wer: 9.0597

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: 16
  • eval_batch_size: 8
  • 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: 4000

Training results

Training Loss Epoch Step Validation Loss Wer
0.075 1.62 500 0.0741 24.0846
0.006 3.24 1000 0.0345 12.3259
0.0016 4.85 1500 0.0273 9.7817
0.0004 6.47 2000 0.0266 9.1800
0.0002 8.09 2500 0.0268 9.0253
0.0002 9.71 3000 0.0274 9.0425
0.0002 11.33 3500 0.0275 9.0597
0.0001 12.94 4000 0.0275 9.0597

Framework versions

  • Transformers 4.40.0.dev0
  • Pytorch 2.1.2
  • Datasets 2.17.1
  • Tokenizers 0.15.2
Downloads last month
21
Safetensors
Model size
72.6M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for uoseftalaat/whisper-base

Finetuned
(2100)
this model

Evaluation results