Mms Tts Kor

🚀 Massively Multilingual Speech (MMS): Korean Text-to-Speech

This repository provides the Korean (kor) text-to-speech (TTS) model checkpoint. It's part of Facebook's Massively Multilingual Speech project, aiming to offer speech technology across a wide range of languages.

🚀 Quick Start

MMS-TTS is available in the 🤗 Transformers library from version 4.33 onwards. To use this checkpoint, first install the latest version of the library:

pip install --upgrade transformers accelerate

Then, run inference with the following code-snippet:

from transformers import VitsModel, AutoTokenizer
import torch

model = VitsModel.from_pretrained("facebook/mms-tts-kor")
tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-kor")

text = "some example text in the Korean language"
inputs = tokenizer(text, return_tensors="pt")

with torch.no_grad():
    output = model(**inputs).waveform

The resulting waveform can be saved as a .wav file:

import scipy

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

Or displayed in a Jupyter Notebook / Google Colab:

from IPython.display import Audio

Audio(output, rate=model.config.sampling_rate)

⚠️ Important Note

For this checkpoint, the input text must be converted to the Latin alphabet first using the uroman tool.

✨ Features

• Multilingual Support: Part of a project aiming to provide speech technology for over 1000 languages.
• End - to - End Synthesis: The VITS model predicts speech waveforms directly from input text.
• Stochastic Duration Prediction: Allows for different speech rhythms from the same input text.

📚 Documentation

Model Details

VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is an end-to-end speech synthesis model that predicts a speech waveform conditional on an input text sequence. It is a conditional variational autoencoder (VAE) comprised of a posterior encoder, decoder, and conditional prior.

A set of spectrogram-based acoustic features are predicted by the flow-based module, which is formed of a Transformer-based text encoder and multiple coupling layers. The spectrogram is decoded using a stack of transposed convolutional layers, much in the same style as the HiFi-GAN vocoder. Motivated by the one-to-many nature of the TTS problem, where the same text input can be spoken in multiple ways, the model also includes a stochastic duration predictor, which allows the model to synthesise speech with different rhythms from the same input text.

The model is trained end-to-end with a combination of losses derived from variational lower bound and adversarial training. To improve the expressiveness of the model, normalizing flows are applied to the conditional prior distribution. During inference, the text encodings are up-sampled based on the duration prediction module, and then mapped into the waveform using a cascade of the flow module and HiFi-GAN decoder. Due to the stochastic nature of the duration predictor, the model is non-deterministic, and thus requires a fixed seed to generate the same speech waveform.

For the MMS project, a separate VITS checkpoint is trained on each langauge.

📄 License

The model is licensed as CC-BY-NC 4.0.

📚 BibTex citation

This model was developed by Vineel Pratap et al. from Meta AI. If you use the model, consider citing the MMS paper:

@article{pratap2023mms,
    title={Scaling Speech Technology to 1,000+ Languages},
    author={Vineel Pratap and Andros Tjandra and Bowen Shi and Paden Tomasello and Arun Babu and Sayani Kundu and Ali Elkahky and Zhaoheng Ni and Apoorv Vyas and Maryam Fazel-Zarandi and Alexei Baevski and Yossi Adi and Xiaohui Zhang and Wei-Ning Hsu and Alexis Conneau and Michael Auli},
    journal={arXiv},
    year={2023}
}