speecht5_finetuned_emirhan_tr

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: 0.2990

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• 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
0.5108	0.0571	100	0.4464
0.42	0.1142	200	0.3574
0.377	0.1713	300	0.3402
0.3568	0.2284	400	0.3280
0.3474	0.2855	500	0.3244
0.3439	0.3426	600	0.3145
0.3337	0.3997	700	0.3114
0.3307	0.4568	800	0.3041
0.3243	0.5140	900	0.3001
0.3231	0.5711	1000	0.2990

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0