CheeLi03/whisper-large-v3-ar-preprocessed

Whisper Large V3 tr finetuned 3 - Chee Li

This model is a fine-tuned version of openai/whisper-large-v3 on the Google Fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 0.2954
• Wer: 497.6687

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0075	6.6667	1000	0.2375	284.7117
0.0015	13.3333	2000	0.2613	384.6258
0.0001	20.0	3000	0.2883	500.4663
0.0001	26.6667	4000	0.2954	497.6687

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1