deepgeek/Matcha-TTS
2
0
Fork 0
mirror of https://github.com/shivammehta25/Matcha-TTS.git synced 2026-02-04 17:59:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update demo page

Browse Source 
Tweak the text, mention ICASSP acceptance, and update citation information.
This commit is contained in:
Gustav Eje Henter
2024-01-14 15:43:13 +01:00
committed by GitHub
parent 188cdb6844
commit 5a7f220662
1 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@@ -23,17 +23,17 @@
<img src="images/logo.png" height="128"/> <img src="images/logo.png" height="128"/>
</p> </p>
We propose 🍵 Matcha-TTS, a new approach to non-autoregressive neural TTS, that uses conditional flow matching (similar to rectified flows) to speed up ODE-based speech synthesis. Our method: We propose 🍵 Matcha-TTS, a new approach to non-autoregressive neural TTS, that uses [conditional flow matching](https://arxiv.org/abs/2210.02747) (similar to [rectified flows](https://arxiv.org/abs/2209.03003)) to speed up ODE-based speech synthesis. Our method:
- Is probabilistic - Is probabilistic
- Has compact memory footprint - Has compact memory footprint
- Sounds highly natural - Sounds highly natural
- Is very fast to synthesise from - Is very fast to synthesise from
Check out our [demo page][this_page]. Read our [arXiv preprint for more details][arxiv_link]. See below for audio examples, or read [our ICASSP 2024 paper][arxiv_link] for more details.
Code is available in our [GitHub repository][github_link], along with pre-trained models. Code is available in our [GitHub repository][github_link], along with pre-trained models.
[Try 🍵 Matcha-TTS on HuggingFace 🤗 spaces!][hf_space] You can also [try 🍵 Matcha-TTS in your browser on HuggingFace 🤗 spaces][hf_space].
[shivam_profile]: https://www.kth.se/profile/smehta [shivam_profile]: https://www.kth.se/profile/smehta
[ruibo_profile]: https://www.kth.se/profile/ruibo [ruibo_profile]: https://www.kth.se/profile/ruibo
@@ -510,11 +510,11 @@ Currently loaded stimulus: <span id="stimuli-from-listening-test-span" style="fo
## Citation information ## Citation information
``` ```
@article{mehta2023matcha, @inproceedings{mehta2024matcha,
title={Matcha-TTS: A fast TTS architecture with conditional flow matching}, title={Matcha-{TTS}: A fast {TTS} architecture with conditional flow matching},
author={Mehta, Shivam and Tu, Ruibo and Beskow, Jonas and Sz{\'e}kely, {\'E}va and Henter, Gustav Eje}, author={Mehta, Shivam and Tu, Ruibo and Beskow, Jonas and Sz{\'e}kely, {\'E}va and Henter, Gustav Eje},
journal={arXiv preprint arXiv:2309.03199}, booktitle={Proc. ICASSP},
year={2023} year={2024}
} }
``` ```