speecht5_finetuned_tamil_voice

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: 0.4529

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_FUSED 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
0.4803	1.0312	100	0.4670
0.4797	2.0623	200	0.4720
0.4729	3.0935	300	0.4570
0.4713	4.1247	400	0.4545
0.4659	5.1558	500	0.4600
0.4565	6.1870	600	0.4545
0.4521	7.2182	700	0.4519
0.4514	8.2494	800	0.4569
0.438	9.2805	900	0.4512
0.4425	10.3117	1000	0.4529

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1