speecht5_finetuned_emirhan_tr

This model is a fine-tuned version of emirhanbilgic/speecht5_finetuned_emirhan_tr on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1523

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.0626	100.0	100	1.0759
0.0601	200.0	200	1.1602
0.0505	300.0	300	1.1778
0.0475	400.0	400	1.1646
0.0495	500.0	500	1.1523

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0