From 158d95e278cc08a0c8f43e70d36f2ceed104a84e Mon Sep 17 00:00:00 2001 From: Shivam Mehta Date: Sun, 17 Sep 2023 15:54:16 +0000 Subject: [PATCH] Updating docs --- README.md | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index 59d7155..e42e4fe 100644 --- a/README.md +++ b/README.md @@ -23,15 +23,18 @@

-We propose Matcha-TTS, a new approach to non-autoregressive neural TTS, that uses conditional flow matching 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 (similar to rectified flows) to speed up ODE-based speech synthesis. Our method: -- Is probabilistic -- Has compact memory footprint -- Sounds highly natural -- Is very fast to synthesise from +* Is probabilistic +* Has compact memory footprint +* Sounds highly natural +* Is very fast to synthesise from -Please check out the audio examples below and [read our arXiv preprint for more details][arxiv_link]. -Code and pre-trained models will be made available shortly after the ICASSP deadline. + +Check out our [demo page][this_page]. Read our [arXiv preprint for more details][arxiv_link]. +Code is available in our [GitHub repository][github_link], along with pre-trained models. + +[Try 🍵 Matcha-TTS on HuggingFace 🤗 spaces!][hf_space] [shivam_profile]: https://www.kth.se/profile/smehta [ruibo_profile]: https://www.kth.se/profile/ruibo @@ -43,6 +46,8 @@ Code and pre-trained models will be made available shortly after the ICASSP dead [grad_tts_paper]: https://arxiv.org/abs/2105.06337 [vits_paper]: https://arxiv.org/abs/2106.06103 [fastspeech2_paper]: https://arxiv.org/abs/2006.04558 +[github_link]: https://github.com/shivammehta25/Matcha-TTS +[hf_space]: https://huggingface.co/spaces/shivammehta25/Matcha-TTS