speecht5_finetuned_p376_id_kavinda

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: 0.5203

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: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• 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: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.5139	11.1212	100	0.4523
3.0496	22.2424	200	0.4255
2.7186	33.3636	300	0.4142
2.6001	44.4848	400	0.4550
2.5284	55.6061	500	0.4699
2.4405	66.7273	600	0.4751
2.4856	77.8485	700	0.4660
2.3682	88.9697	800	0.4991
2.2906	100.0	900	0.5159
2.2566	111.1212	1000	0.5203

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0