Here we present Matxa-TTS 🍵 v2: a Catalan multispeaker and multi-accent neural TTS model working with graphemes.
It works together with a vocoder model to generate high quality and expressive speech efficiently.
You can use any vocoder such as 🥑 alVoCat
or Wavenext.
Model Description
Matxa-TTS 🍵 is based on Matcha-TTS, 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.
The decoder has essentially a U-Net backbone inspired by Grad-TTS, which is based on the Transformer architecture.
By replacing 2D CNNs by 1D CNNs in the decoder, 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.
Modifications
Decoder's number of channels and attention head dimension were increased to 512 and 128, respectively
Two timestep sampling techniques for diffusion were added: (1) stratified sampling, where each batch sample is assigned a different segment of [0,1) to guarantee uniform coverage of diffusion time; and (2) a cosine timestep scheduler
A denoiser is implemented on the generated spectrogram during inference
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 Catalan text, therefore if the model is used for other languages it will not produce intelligible samples after mapping
its output into a speech waveform.
The quality of the samples can vary depending on the speaker.
This may be due to the sensitivity of the model in learning specific frequencies and also due to the quality of samples for each speaker.
Know more about our Catalan voices (and their corresponding IDs in parenthesis):
LaFresCat
Balear
Central
North-Western
Valencian
Olga (0), Quim (1)
Elia (2), Grau (3)
Emma (4), Pere (5)
Gina (6), Lluc (7)
EnVeuAlta
Balear
Central
BM (10)
CF (11), CM (12)
ReFresCat
Valencian
North-Western
Northern
Arnau (8), Berta (9)
Estel (13)
Laura (14), Jordi (15)
Note: The names shown are not the real speakers’ names.
End-to-End ONNX Version
We provide an end-to-end Catalan multi-accent Matxa-TTS v2 in ONNX format.
This Catalan multi-accent Matxa-TTS v2 was exported to ONNX, and then concatenated with our 🥑 alVoCat (WaveNext ONNX version).
Training
This model has been trained from scratch with LaFresCat dataset together with other
studio-quality Catalan multi-accent recordings (ReFresCat and EnVeuAlta).
Using this set of hyperparameters:
Learning Rate → 5e-5
Scheduler → Cosine scheduler with a minimum learning rate 3e-5
Batch Size → 32
GPUs → 2
Num. Steps → 130K
Evaluation
We evaluated the model in terms of quality and intelligibility using a test set of 350 sentences extracted from
La creació d'Eva i altres contes by Josep Carner i Puig-Oriol, available on Project Gutenberg.
Speech quality was assessed using ScoreQ, a recent approach for evaluating synthesized speech.
Intelligibility was measured by computing Word Error Rate (WER) and Character Error Rate (CER)
using the whisper-bsc-large-v3-cat model, which was trained and evaluated on multi-accented Catalan data.
We used AlVoCat as a vocoder, already trained on Catalan data.
For comparison, we evaluated the model together with the same model trained with phonemes using the same set of sentences.
When training directly with graphemes, the model achieves better scores in terms of intelligibility while being competitive with the phoneme version in terms of audio
quality.
In addition, Matxa-TTS-v2-ca-multiaccent-graphemes does not require a phonemizer, making the model more flexible and easier to integrate.
Model
ScoreQ LaFresCat spks
ScoreQ ReFresCat spks
Phoneme Matxa-TTS
3.37
3.46
Matxa-TTS-v2-ca-multiaccent-graphemes
3.29
3.30
Model
WER LaFresCat spks
CER LaFresCat spks
WER ReFresCat spks
CER ReFresCat spks
Phoneme Matxa-TTS
12.4
4.07
11.53
3.79
Matxa-TTS-v2-ca-multiaccent-graphemes
9.44
3.04
9.15
3.02
Citation
If this code contributes to your research, please cite the work:
@misc{LangtechVeu2025matxattsv2multispeaker,
title={Grapheme-Based Catalan Multi-Accent Text-to-Speech},
author={Alex Peiró-Lilja and Jose Giraldo},
organization={Barcelona Supercomputing Center},
url={huggingface.co/BSC-LT/matxa-tts-v2-ca-multiaccent-graphemes},
year={2026}
}
Additional Information
Author
The Speech Team at the AI Institute, Barcelona Supercomputing Center.
Contact
For further information, please send an email to bsc-lt@bsc.es.
Copyright
Copyright(c) 2025 by the AI Institute, Barcelona Supercomputing Center.
License
This model is free to use for non-commercial and research purposes (see LICENSE.md for full terms). Commercial use is only possible through licensing by
the voice artists. For further information, contact bsc-lt@bsc.es and lafrescaproduccions@gmail.com.
Funding
This work is funded by the Ministerio para la Transformación Digital y de la Función Pública - Funded by EU – NextGenerationEU within the framework of the project ILENIA with reference 2022/TL22/00215337.
The conversion of the model was possible thanks to the computing time provided by Barcelona Supercomputing Center through MareNostrum 5.
