wav2vec2-large-xlsr-turkish

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

• Loss: 0.4242
• Wer: 0.4827

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

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
5.0376	4.26	400	2.3690	1.0020
0.7983	8.51	800	0.4755	0.6328
0.3157	12.77	1200	0.4051	0.5408
0.2197	17.02	1600	0.4156	0.5149
0.1643	21.28	2000	0.4286	0.5036
0.1305	25.53	2400	0.4247	0.4908
0.1178	29.79	2800	0.4242	0.4827

Framework versions

• Transformers 4.24.0
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2