Edit model card

microsopt_uzb_tts

This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4618

Model description

microsopt_uzb_tts bu model deyarli 1 GB datasetga fine-tuned qilindi. Agarda qanaday qilib foydalanishni bilishni xoxlamoqchi bo'lsangiz. Bu linkdagi foydalanish qadamlarga ergashing.

https://huggingface.co/ai-nightcoder/UZBTTS

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: 4
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5477 3.75 1000 0.4948
0.513 7.5 2000 0.4808
0.5 11.26 3000 0.4670
0.4987 15.01 4000 0.4618

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.1.2
  • Datasets 2.1.0
  • Tokenizers 0.15.1
Downloads last month
1
Safetensors
Model size
144M params
Tensor type
F32
·
Inference API
This model can be loaded on Inference API (serverless).

Finetuned from