Tts Thai Last Step

🚀 Thai Text-to-Speech Model

This is a Thai Text-to-Speech (TTS) model. It uses voices from the Common Voice dataset and modifies them to sound different from the original.

🚀 Quick Start

To get started with this model, you need to install the necessary libraries. Run the following command:

pip install nemo_toolkit['tts'] soundfile

💻 Usage Examples

Basic Usage

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)

📚 Documentation

For more detailed information about this Thai TTS model, you can refer to the following Medium article: Text-To-Speech ภาษาไทยด้วย Tacotron2

📄 License

This project is licensed under the MIT license.