MMS TTS THAI FEMALE PODCAST

🚀 Thai Text-to-Speech Fine-tuning Project

This project focuses on fine-tuning Thai text-to-speech models. It provides multiple ways to train and use the models, including on Google Colab and local computers.

🚀 Quick Start

Fine-tuning on GitHub

You can find the fine-tuning code on GitHub: Finetune GitHub Code

Fine-tuning on Google Colab

Train your own speech model on Google Colab: Finetune-colab

Local Usage

Use the model on your local computer: Local Usage Code

💻 Usage Examples

Basic Usage

import torch
from transformers import VitsTokenizer, VitsModel, set_seed
import scipy

tokenizer = VitsTokenizer.from_pretrained("VIZINTZOR/MMS-TTS-THAI-FEMALE-PODCAST",cache_dir="./mms")
model = VitsModel.from_pretrained("VIZINTZOR/MMS-TTS-THAI-FEMALE-PODCAST",cache_dir="./mms")

inputs = tokenizer(text="สวัสดีค่ะ นี่คือเสียงพูดภาษาไทย", return_tensors="pt")

set_seed(456)  # make deterministic

with torch.no_grad():
   outputs = model(**inputs)

waveform = outputs.waveform[0]

# Convert PyTorch tensor to NumPy array
waveform_array = waveform.numpy()

scipy.io.wavfile.write("techno_output.wav", rate=model.config.sampling_rate, data=waveform_array)

⚠️ Important Note

The code and models in this project are based on relevant open - source projects. Please ensure you comply with the corresponding license agreements.

💡 Usage Tip

When using the model on Google Colab or a local computer, make sure your environment has installed the necessary dependencies, such as torch, transformers, and scipy.