---
license: mit
datasets:
- lunarlist/edited_common_voice
language:
- th
library_name: nemo
pipeline_tag: text-to-speech
---

This model is a Thai TTS model that use a voice from [Common Voice dataset](https://commonvoice.mozilla.org/) and modify the voice to not to sound like the original.

> pip install nemo_toolkit['tts'] soundfile

```python
from nemo.collections.tts.models import UnivNetModel
from nemo.collections.tts.models import Tacotron2Model
import torch
import soundfile as sf

model = Tacotron2Model.from_pretrained("lunarlist/tts-thai-last-step").to('cpu')
vcoder_model = UnivNetModel.from_pretrained(model_name="tts_en_libritts_univnet")
text='ภาษาไทย ง่าย นิด เดียว'
dict_idx={k:i for i,k in enumerate(model.hparams["cfg"]['labels'])}
parsed2=torch.Tensor([[66]+[dict_idx[i] for i in text if i]+[67]]).int().to("cpu")
spectrogram2 = model.generate_spectrogram(tokens=parsed2)
audio2 = vcoder_model.convert_spectrogram_to_audio(spec=spectrogram2)

# Save the audio to disk in a file called speech.wav
sf.write("speech.wav", audio2.to('cpu').detach().numpy()[0], 22050)
```

Medium: [Text-To-Speech ภาษาไทยด้วย Tacotron2](https://medium.com/@taetiyateachamatavorn/text-to-speech-%E0%B8%A0%E0%B8%B2%E0%B8%A9%E0%B8%B2%E0%B9%84%E0%B8%97%E0%B8%A2%E0%B8%94%E0%B9%89%E0%B8%A7%E0%B8%A2-tacotron2-986417b44edc)