Mms Tts Pan

🚀 Massively Multilingual Speech (MMS): Punjabi, Eastern Text-to-Speech

This repository offers a text-to-speech (TTS) model checkpoint for the Punjabi, Eastern (pan) language, which is part of Facebook's Massively Multilingual Speech project aiming to provide speech technology across diverse languages.

🚀 Quick Start

MMS-TTS has been available in the 🤗 Transformers library since version 4.33. 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-pan")
tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-pan")

text = "some example text in the Punjabi, Eastern 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)

✨ Features

• Diverse Language Support: As part of the MMS project, it supports a wide range of languages, including Punjabi, Eastern.
• End - to - End Synthesis: The VITS model enables end - to - end speech synthesis, predicting speech waveforms based on input text sequences.
• Stochastic Duration Prediction: Allows the model to synthesize speech with different 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. It predicts a speech waveform conditional on an input text sequence. It is a conditional variational autoencoder (VAE) consisting 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, similar to the HiFi - GAN vocoder. Due to the one - to - many nature of the TTS problem, where the same text input can be spoken in multiple ways, the model includes a stochastic duration predictor, enabling it to synthesize speech with different rhythms from the same input text.

The model is trained end - to - end with a combination of losses from variational lower bound and adversarial training. To enhance the model's expressiveness, 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. Because of the stochastic nature of the duration predictor, the model is non - deterministic and requires a fixed seed to generate the same speech waveform.

For the MMS project, a separate VITS checkpoint is trained for each language.

📄 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}
}