Bengali_finetuned_speecht5_tts

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: 0.6190

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 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: 600
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
6.1441	1.9422	100	0.7127
5.5876	3.8988	200	0.6550
5.2451	5.8554	300	0.6514
5.1514	7.8120	400	0.6227
4.9727	9.7687	500	0.6220
4.9797	11.7253	600	0.6190

Framework versions

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