urdu_tts_recovery_A

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

urdu_tts_recovery_A

This model is a fine-tuned version of Shaju07/urdu_tts_0.1_B on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.4344
• eval_runtime: 28.3679
• eval_samples_per_second: 37.225
• eval_steps_per_second: 18.613
• epoch: 14.7059
• step: 2750

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 16
• 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: constant_with_warmup
• lr_scheduler_warmup_steps: 2000
• training_steps: 10000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0