speecht5_finetuned__ylacombe_one_speaker_dataset_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: 0.4739

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 OptimizerNames.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
3.259	20.0	100	0.4786
2.8687	40.0	200	0.4758
2.6007	60.0	300	0.4627
2.4877	80.0	400	0.4735
2.4701	100.0	500	0.4739

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Tokenizers 0.21.0