pranavdaware/speecht5_tts_marathi_train1

SpeechT5 TTS marathi train1

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

• Loss: 0.7604

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-06
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use 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: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.0728	5.2632	100	0.9236
1.8554	10.5263	200	0.8116
1.7615	15.7895	300	0.7807
1.6881	21.0526	400	0.7641
1.6793	26.3158	500	0.7604

Framework versions

• Transformers 4.46.0.dev0
• Pytorch 2.5.0+cu121
• Datasets 3.0.2
• Tokenizers 0.20.1