mlsanityData to 14 Oct 2026

F5-TTS-RO: Extending F5-TTS to Romanian TTS via Lightweight Input Adaptation

arXiv 2512.12297 ↗First posted 13 Dec 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

This work introduces a lightweight input-level adapter for the F5-TTS model that enables Romanian Language support. To preserve the existing capabilities of the model (voice cloning, English and Chinese support), we keep the original weights frozen, append a sub-network to the model and train it as an extension for the textual embedding matrix of the text encoder. For simplicity, we rely on ConvNeXt module implemented in F5-TTS to also model the co-dependencies between the new character-level embeddings. The module serves as a ``soft`` letter-to-sound layer, converting Romanian text into a continuous representation that the F5-TTS model uses to produce naturally sounding Romanian utterances. We evaluate the model with a pool of 20 human listeners across three tasks: (a) audio similarity between reference and generated speech, (b) pronunciation and naturalness and (c) Romanian-English code-switching. The results indicate that our approach maintains voice cloning capabilities and enables, to a certain extent, code-switching within the same utterance; however, residual English accent characteristics remain. We open-source our code and provide example audio samples at https://github.com/racai-ro/Ro-F5TTS.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 22 references that are in the map. First posted on arXiv 13 Dec 2025.

Builds on

12 of 22 references.

References · 12

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  3. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  4. 2023Scaling Speech Technology to 1,000+ Languagescited by 411
  5. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  6. 2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 278
  7. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 179
  8. 2024E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTScited by 152
  9. 2020FastPitch: Parallel Text-to-speech with Pitch Predictioncited by 151
  10. 2025Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Modelscited by 11
  11. 2024Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgettingcited by 9
  12. 2024Efficient training strategies for natural sounding speech synthesis and speaker adaptation based on FastPitchcited by 1

Built on by

Not cited yet.