wav2vec2-large-xls-r-300m-tr-cv6.1

This model is a fine-tuned version of rumeyskeskn/wav2vec2-large-xls-r-300m-tr-cv6.1 on the common_voice_6_1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5295
• Wer: 0.4836

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: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.715	6.96	400	0.6946	0.6729
0.3226	13.91	800	0.5295	0.4836

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2