uz_2301_3.01_tts

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: 0.4463

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use 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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4585	10.0	500	0.4543
0.4313	20.0	1000	0.4337
0.4032	30.0	1500	0.4295
0.3679	40.0	2000	0.4197
0.3623	50.0	2500	0.4206
0.3526	60.0	3000	0.4166
0.3356	70.0	3500	0.4243
0.3273	80.0	4000	0.4247
0.3267	90.0	4500	0.4366
0.3166	100.0	5000	0.4463

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0