speecht5_finetuned_with_Uzbek_data

This model is a fine-tuned version of microsoft/speecht5_tts on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5099

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: 0.0002
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• 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: 200
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6618	0.7331	250	0.6034
0.594	1.4663	500	0.5597
0.5596	2.1994	750	0.5249
0.5437	2.9326	1000	0.5099

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3