speecht5-persian-tts-finglish

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: 0.4180

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5188	1.1851	500	0.4640
0.4829	2.3701	1000	0.4370
0.4717	3.5552	1500	0.4283
0.4669	4.7402	2000	0.4239
0.4623	5.9253	2500	0.4208
0.4581	7.1091	3000	0.4186
0.4545	8.2942	3500	0.4177
0.4569	9.4792	4000	0.4180

Framework versions

• Transformers 4.57.2
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1