README.md

metadata

library_name: transformers
license: apache-2.0
base_model: arbml/whisper-small-ar
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper Small Ar 4000 Finetuned - AzeemX
    results: []

Whisper Small Ar 4000 Finetuned - AzeemX

This model is a fine-tuned version of arbml/whisper-small-ar on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0551
• Wer: 137.1649

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: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1103	1.0323	1000	0.1106	77.6886
0.042	2.0645	2000	0.0782	75.1757
0.0146	3.0968	3000	0.0606	107.6103
0.0064	4.1290	4000	0.0551	137.1649

Framework versions

• Transformers 4.45.2
• Pytorch 2.3.1
• Datasets 3.0.1
• Tokenizers 0.20.0