wav2vec2-large-xls-r-300m-turkish-colab

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:

• Loss: 0.3701
• Wer: 0.2946

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: 32
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.8287	3.67	400	0.6628	0.6928
0.3926	7.34	800	0.4257	0.4716
0.1847	11.01	1200	0.4034	0.3931
0.1273	14.68	1600	0.4094	0.3664
0.0991	18.35	2000	0.4133	0.3375
0.0811	22.02	2400	0.4021	0.3301
0.0646	25.69	2800	0.3949	0.3166
0.0513	29.36	3200	0.3701	0.2946

Framework versions

• Transformers 4.11.3
• Pytorch 1.10.0+cu113
• Datasets 1.18.3
• Tokenizers 0.10.3