speecht5_finetuned_emirhan_tr2

This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4583

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: 2
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use 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: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
5.3014	0.0497	100	0.5731
4.8007	0.0994	200	0.5634
4.4991	0.1491	300	0.5075
4.3261	0.1987	400	0.5087
4.2605	0.2484	500	0.4883
4.196	0.2981	600	0.4805
4.108	0.3478	700	0.4697
4.1053	0.3975	800	0.4655
4.0197	0.4472	900	0.4595
4.0208	0.4969	1000	0.4583

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0