speecht5_fine_tuned_dhivehi_tts_V006

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3309

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• 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: cosine_with_restarts
• lr_scheduler_warmup_steps: 500
• training_steps: 10000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.3708	2.6464	1000	0.3373
0.369	5.2914	2000	0.3363
0.3699	7.9377	3000	0.3346
0.3662	10.5828	4000	0.3342
0.3617	13.2278	5000	0.3328
0.3642	15.8742	6000	0.3325
0.3654	18.5192	7000	0.3318
0.3591	21.1642	8000	0.3308
0.3657	23.8106	9000	0.3311
0.3625	26.4556	10000	0.3309

Framework versions

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