pathe_tts-RB-data_V0

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

• Loss: 0.4809

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: 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: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6129	6.6715	700	0.4851
0.5137	13.3357	1400	0.4725
0.4888	20.0	2100	0.4774
0.4775	26.6715	2800	0.4734
0.4687	33.3357	3500	0.4767
0.4673	40.0	4200	0.4791
0.4634	46.6715	4900	0.4809

Framework versions

• Transformers 4.49.0.dev0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0