---
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: microsopt_uzb_tts
  results: []
---

<!-- 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. -->

# microsopt_uzb_tts

This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/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