speecht5_finetuned_uz_customDat_3

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: 0.5390

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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: 500
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5014	11.7879	200	0.4656
0.4407	23.5455	400	0.4460
0.418	35.3030	600	0.4447
0.3972	47.0606	800	0.4652
0.3819	58.8485	1000	0.4874
0.373	70.6061	1200	0.4850
0.3709	82.3636	1400	0.5019
0.3631	94.1212	1600	0.5121
0.3595	105.9091	1800	0.5319
0.3647	117.6667	2000	0.5390

Framework versions

• Transformers 4.47.0.dev0
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3