flavioegoncalves/speecht5_tts_portuguese

SpeechT5 TTS Portuguese

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

• Loss: 0.3452

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: 10000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4091	1.68	1000	0.3728
0.3906	3.35	2000	0.3598
0.3899	5.03	3000	0.3543
0.3842	6.71	4000	0.3518
0.376	8.38	5000	0.3492
0.3745	10.06	6000	0.3474
0.3773	11.74	7000	0.3473
0.3774	13.41	8000	0.3461
0.3719	15.09	9000	0.3454
0.3712	16.76	10000	0.3452

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0