rishithabcdefghijklmnop/custom

SpeechT5 TTS Dutch

This model is a fine-tuned version of microsoft/speecht5_tts on the indian_accent_english dataset. It achieves the following results on the evaluation set:

• Loss: 0.3974

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: 4
• eval_batch_size: 4
• seed: 42
• 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: 10000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5341	0.6570	1000	0.4899
0.5078	1.3141	2000	0.4635
0.4703	1.9711	3000	0.4352
0.4579	2.6281	4000	0.4205
0.455	3.2852	5000	0.4173
0.4643	3.9422	6000	0.4100
0.4493	4.5992	7000	0.4029
0.4208	5.2562	8000	0.3991
0.4468	5.9133	9000	0.4017
0.4117	6.5703	10000	0.3974

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.2