Vits Rasa 13

🚀 VITS TTS for Indian Languages

This repository houses a VITS-based Text-to-Speech (TTS) model that has been fine - tuned for Indian languages. The model supports multiple Indian languages, a wide array of speaking styles, and emotions. It is well - suited for diverse applications such as conversational AI, audiobooks, and more.

🚀 Quick Start

This VITS-based TTS model is designed to convert text into speech for multiple Indian languages. It offers various speaking styles and emotions, enhancing the user experience in different scenarios.

✨ Features

The model ai4bharat/vits_rasa_13 is based on the VITS architecture and comes with the following features:

• Languages: Supports multiple Indian languages.
• Styles: Offers various speaking styles and emotions.
• Speaker IDs: Has predefined speaker profiles for male and female voices.

📦 Installation

pip install transformers torch

💻 Usage Examples

Basic Usage

import soundfile as sf
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("ai4bharat/vits_rasa_13", trust_remote_code=True).to("cuda")
tokenizer = AutoTokenizer.from_pretrained("ai4bharat/vits_rasa_13", trust_remote_code=True)

text = "ਕੀ ਮੈਂ ਇਸ ਹਫਤੇ ਦੇ ਅੰਤ ਵਿੱਚ ਰੁੱਝਿਆ ਹੋਇਆ ਹਾਂ?"  # Example text in Punjabi
speaker_id = 16  # PAN_M
style_id = 0  # ALEXA

inputs = tokenizer(text=text, return_tensors="pt").to("cuda")
outputs = model(inputs['input_ids'], speaker_id=speaker_id, emotion_id=style_id)
sf.write("audio.wav", outputs.waveform.squeeze(), model.config.sampling_rate)
print(outputs.waveform.shape)

📚 Documentation

Supported Languages

• Assamese
• Bengali
• Bodo
• Dogri
• Kannada
• Maithili
• Malayalam
• Marathi
• Nepali
• Punjabi
• Sanskrit
• Tamil
• Telugu

Speaker - Style Identifier Overview

📄 License

This project is licensed under the CC - BY - 4.0 license.

📚 Citation

If you use this model in your research, please cite:

@article{ai4bharat_vits_rasa_13,
  title={VITS TTS for Indian Languages},
  author={Ashwin Sankar},
  year={2024},
  publisher={Hugging Face}
}