speecht5_indicvoices_r_ml

This model is a fine-tuned version of microsoft/speecht5_tts on the ai4bharat/indicvoices_r dataset. It achieves the following results on the evaluation set:

• Loss: 0.5052

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• 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: 500
• training_steps: 6000

Training results

Training Loss	Epoch	Step	Validation Loss
0.5752	8.0647	1000	0.5453
0.5566	16.1295	2000	0.5239
0.5381	24.1942	3000	0.5187
0.5279	32.2590	4000	0.5099
0.523	40.3237	5000	0.5109
0.5252	48.3885	6000	0.5052

Framework versions

• Transformers 4.57.1
• Pytorch 2.9.1
• Datasets 2.18.0
• Tokenizers 0.22.1