speecht5_tamil_1

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: 0.4286

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: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5979	0.4393	100	0.5265
0.5397	0.8786	200	0.4946
0.5145	1.3207	300	0.4670
0.4984	1.7600	400	0.4593
0.4872	2.2021	500	0.4511
0.4851	2.6414	600	0.4451
0.4896	3.0835	700	0.4370
0.4668	3.5228	800	0.4346
0.462	3.9621	900	0.4311
0.4601	4.4042	1000	0.4286

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.6.0
• Tokenizers 0.21.0