speecht5_finetuned_voxpopuli_es

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

• Loss: 0.4810

Model description

SpeechT5

Intended uses & limitations

Text-to-speech

Training and evaluation data

qmeeus/voxpopuli (Spanish)

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• 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: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.7176	1.063	250	0.5425
4.3640	2.126	500	0.4921
4.3475	4.002	750	0.4836
4.2815	5.065	1000	0.4810

Framework versions

• Transformers 5.12.1
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2