wav2vec2-base-Stella20_Arabic_ASR-colab

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0393
• Wer: 0.2998

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: 5e-05
• train_batch_size: 3
• 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
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4298	8.8496	1000	1.0054	0.4013
0.2797	17.6991	2000	1.1398	0.3388
0.1989	26.5487	3000	1.0393	0.2998

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1