uz_2301_3_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: 0.4075

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 OptimizerNames.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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4978	10.0	500	0.4866
0.4712	20.0	1000	0.4466
0.4108	30.0	1500	0.4150
0.3871	40.0	2000	0.4034
0.3708	50.0	2500	0.4028
0.3618	60.0	3000	0.4029
0.3491	70.0	3500	0.4006
0.3319	80.0	4000	0.4070
0.3266	90.0	4500	0.4056
0.3178	100.0	5000	0.4075

Framework versions

• Transformers 4.48.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0