Request access to dyu-mms-tts

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

dyu-mms-tts is a GO AI Corp model shared for non-commercial research (CC BY-NC 4.0). Commercial use needs written permission from contact@goaicorporation.org. Please read the card, its terms and licenses before requesting access, and make sure you understand them.

Log in or Sign Up to review the conditions and access this model content.

dyu-mms-tts

Dioula text-to-speech: MMS-TTS (VITS) fine-tuned by GO AI Corp.

Task Text-to-speech, Dioula (dyu)
Base model facebook/mms-tts
Training data Not recorded
Published May 2026

Résumé en français. Synthèse vocale en dioula : MMS-TTS (VITS) affiné par GO AI Corp à partir de facebook/mms-tts. Données d'entraînement non notées. Publié en mai 2026. Licence CC BY-NC 4.0 ; tout usage commercial demande l'autorisation écrite de contact@goaicorporation.org. Accès sur demande.

Quick start

import torch, scipy.io.wavfile
from transformers import VitsModel, AutoTokenizer

name = "goaicorp/dyu-mms-tts"
model, tok = VitsModel.from_pretrained(name), AutoTokenizer.from_pretrained(name)
with torch.no_grad():
    wav = model(**tok("I ni ce.", return_tensors="pt")).waveform[0].numpy()
scipy.io.wavfile.write("out.wav", model.config.sampling_rate, wav)

Evaluation

Test set CER (ASR loopback) UTMOS Speaker similarity
Dioula held-out set (to be fixed) pending pending pending

CER is measured by transcribing the synthetic speech with a fixed Mooré ASR model.

Limits

  • Training data is not documented. The earlier card was titled "Bambara TTS"; the model is tagged and described as Dioula.
  • One voice; no voice cloning.

License

CC BY-NC 4.0. Commercial use needs written permission from contact@goaicorporation.org.

Citation

@misc{goaicorp2026dyummstts,
  title        = {dyu-mms-tts: Dioula text-to-speech with MMS-TTS},
  author       = {Nyantudre, Wendyellé Abubakrh Alban and Bandaogo, Aristide},
  year         = {2026},
  howpublished = {Hugging Face Models, GO AI Corp},
  url          = {https://huggingface.co/goaicorp/dyu-mms-tts}
}

Developed and maintained by

Downloads last month
8
Safetensors
Model size
36.3M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for goaicorp/dyu-mms-tts

Base model

facebook/mms-tts
Finetuned
(15)
this model