whisper-tiny-ar

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

• Loss: 0.8394
• Wer: 86.0500

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: 128
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.0265	1.0	122	1.0110	98.4608
0.9208	2.0	244	0.9148	88.3812
0.8169	3.0	366	0.8394	86.0500

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.12.1
• Datasets 2.7.1
• Tokenizers 0.13.2