vsisik/speecht5_tts_SK_v2

SpeechT5 TTS Slovak v2

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

• Loss: 0.4301

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: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• 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
0.5379	4.0	500	0.4771
0.4972	8.0	1000	0.4526
0.4854	12.0	1500	0.4409
0.4746	16.0	2000	0.4375
0.4733	20.0	2500	0.4335
0.4673	24.0	3000	0.4313
0.4577	28.0	3500	0.4306
0.4662	32.0	4000	0.4301

Framework versions

• Transformers 4.40.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2