tamasheq-99

This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-arabic on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3007
• Wer: 0.4911

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: 3e-05
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
11.9337	6.0	300	3.2207	1.0
2.8261	12.0	600	0.9838	0.7251
0.5773	18.0	900	0.3437	0.5014
0.3252	24.0	1200	0.3029	0.4940
0.2821	30.0	1500	0.3007	0.4911

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3