speecht5_finetuned_vietnamese

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

• Loss: 0.5406

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use 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: 100
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6213	0.0035	100	0.6012
0.6087	0.0069	200	0.5743
0.592	0.0104	300	0.5571
0.5708	0.0139	400	0.5512
0.5596	0.0173	500	0.5406

Framework versions

• Transformers 4.47.0.dev0
• Pytorch 2.5.1
• Datasets 2.19.1
• Tokenizers 0.20.1