speecht5_base_covost2_en_es

This model is a fine-tuned version of sophiayk20/speecht5_tts_voxpopuli_es on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4577

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: 4
• total_train_batch_size: 128
• 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: 4000

Training results

Training Loss	Epoch	Step	Validation Loss
0.526	0.8997	500	0.4934
0.5125	1.7989	1000	0.4759
0.5017	2.6982	1500	0.4692
0.4913	3.5974	2000	0.4632
0.4917	4.4966	2500	0.4613
0.4979	5.3959	3000	0.4593
0.4914	6.2951	3500	0.4588
0.4902	7.1943	4000	0.4577

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.0
• Tokenizers 0.21.0