Mms Tts Tem

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

This repository provides a text-to-speech (TTS) model checkpoint for the Themne (tem) language. It's part of Facebook's Massively Multilingual Speech project, aiming to offer speech technology across a wide range of languages. You can find more details about supported languages and their ISO 639-3 codes in the MMS Language Coverage Overview. All MMS-TTS checkpoints are available on the Hugging Face Hub: facebook/mms-tts.

🚀 Quick Start

MMS-TTS has been available in the 🤗 Transformers library since version 4.33. To use this checkpoint, you need to install the latest version of the library first:

pip install --upgrade transformers accelerate

✨ Features

• Multilingual Support: Part of a project aiming to provide speech technology for over a thousand languages.
• End-to-End Synthesis: Based on the VITS model, it can directly generate speech waveforms from text.
• Stochastic Duration Prediction: Allows for synthesizing speech with different rhythms from the same input text.

📦 Installation

To use this checkpoint, first install the latest version of the 🤗 Transformers library:

pip install --upgrade transformers accelerate

💻 Usage Examples

Basic Usage

from transformers import VitsModel, AutoTokenizer
import torch

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

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

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

Advanced Usage

Save the resulting waveform as a .wav file:

import scipy

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

Display the audio in a Jupyter Notebook / Google Colab:

from IPython.display import Audio

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

📚 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.

🔧 Technical Details

The model architecture is based on VITS, which is a conditional variational autoencoder (VAE). It consists of a posterior encoder, decoder, and conditional prior. The flow-based module predicts spectrogram-based acoustic features, and the spectrogram is decoded using transposed convolutional layers similar to the HiFi-GAN vocoder. The stochastic duration predictor allows for different speech rhythms from the same input text. The model is trained end-to-end with a combination of variational and adversarial losses, and normalizing flows are applied to the conditional prior distribution to improve expressiveness.

📚 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}
}