speecht5_finetuned_voxpopuli_es

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: 0.4625

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: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5118	2.3419	250	0.4745
0.501	4.6838	500	0.4680
0.4988	7.0258	750	0.4645
0.4945	9.3677	1000	0.4625

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Tokenizers 0.19.1