#dastlab run qiling :
    !pip install transformers datasets

    from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech

    processor = SpeechT5Processor.from_pretrained("ai-nightcoder/UZBTTS")
    model = SpeechT5ForTextToSpeech.from_pretrained("ai-nightcoder/UZBTTS")

    # ***************************************************************************
    text = "O‘zbekistonda import qilingan sovitkich,
           muzlatkich va konditsionerlarni energosamaradorlik bo‘yicha sinovdan o‘tkazish boshlandi.
           Kun.uz'ga murojaat qilgan importchi tadbirkorlarga ko‘ra, bu yangilik ham vaqt,
           ham naqd nuqtayi nazaridan yangi xarajatlarga olib kelgan.
           Kelgusida bunday tekshiruv boshqa turdagi maishiy texnikalarga ham joriy etilishi kutilyapti."

    inputs = processor(text=text, return_tensors="pt")

    # ***************************************************************************

    from datasets import load_dataset

    embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")

    import torch
    # voice clone uchun ham ishlatilsa bo'ladi.
    speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)

    spectrogram = model.generate_speech(inputs["input_ids"], speaker_embeddings)

    from transformers import SpeechT5HifiGan

    vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")

    # ****************************************************************************

    speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)

    from IPython.display import Audio

    Audio(speech, rate=16000)


### 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.479         | 137.93 | 1000 | 0.5174          |
| 0.4318        | 275.86 | 2000 | 0.5177          |
| 0.4111        | 413.79 | 3000 | 0.5302          |
| 0.4081        | 551.72 | 4000 | 0.5190          |


### Framework versions

- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1