speecht5-tts-finetuned-es-voxpopuli-commonvoice16

This model is a fine-tuned version of Daniel981215/speecht5-tts-finetuned-es-voxpopuli-commonvoice16 on the mozilla-foundation/common_voice_16_1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4681

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: 8
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• 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: 10000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5187	0.1953	1000	0.4877
0.5038	0.3906	2000	0.4823
0.5063	0.5859	3000	0.4788
0.5018	0.7812	4000	0.4744
0.4958	0.9764	5000	0.4728
0.4981	1.1717	6000	0.4713
0.4944	1.3670	7000	0.4703
0.4949	1.5623	8000	0.4683
0.4902	1.7576	9000	0.4687
0.4924	1.9529	10000	0.4681

Framework versions

• Transformers 4.41.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1