wav2vec2-large-xlsr-53-ary

This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-arabic on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9398
• Wer: 0.5876

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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
0.9944	6.6667	100	0.8681	0.7354
0.503	13.3333	200	0.7610	0.6337
0.3064	20.0	300	0.8371	0.5955
0.2105	26.6667	400	0.9398	0.5876

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1