matxa tts cat multiaccent EU AI Act Compliance Profile

🍵 Matxa-TTS (Matcha-TTS) Catalan Multiaccent

Table of Contents

• Model description
• Intended uses and limitations
• How to use
• Training
• Evaluation
• Citation
• Additional information

Summary

Here we present 🍵 Matxa, the first multispeaker, multidialectal neural TTS model. It works together with the vocoder model 🥑 alVoCat, to generate high quality and expressive speech efficiently in four dialects:

• Balear
• Central
• North-Occidental
• Valencian

Both models are trained with open data; 🍵 Matxa models are free (as in freedom) to use for non-comercial purposes, but for commercial purposes it needs licensing from the voice artist. To listen to the voices you can visit the dedicated space.

Model Description

🍵 Matxa-TTS is based on Matcha-TTS that is an encoder-decoder architecture designed for fast acoustic modelling in TTS. The encoder part is based on a text encoder and a phoneme duration prediction that together predict averaged acoustic features. And the decoder has essentially a U-Net backbone inspired by Grad-TTS, which is based on the Transformer architecture. In the latter, by replacing 2D CNNs by 1D CNNs, a large reduction in memory consumption and fast synthesis is achieved.

Matxa-TTS is a non-autorregressive model trained with optimal-transport conditional flow matching (OT-CFM). This yields an ODE-based decoder capable of generating high output quality in fewer synthesis steps than models trained using score matching.

Intended Uses and Limitations

This model is intended to serve as an acoustic feature generator for multispeaker text-to-speech systems for the Catalan language. It has been finetuned using a Cat

Your obligations as a matxa tts cat multiaccent deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Languages

Base Model