mirror of
https://github.com/shivammehta25/Matcha-TTS.git
synced 2026-02-05 18:29:19 +08:00
Removing architecture from the docs
This commit is contained in:
15
README.md
15
README.md
@@ -25,11 +25,10 @@
|
|||||||
|
|
||||||
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 (similar to rectified flows) 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].
|
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.
|
Code is available in our [GitHub repository][github_link], along with pre-trained models.
|
||||||
@@ -225,9 +224,9 @@ audio {
|
|||||||
|
|
||||||
<script src="transcripts.js"></script>
|
<script src="transcripts.js"></script>
|
||||||
|
|
||||||
## Architecture
|
<!-- ## Architecture
|
||||||
|
|
||||||
<img src="images/architecture.png" alt="Architecture of Matcha-TTS" width="750"/>
|
<img src="images/architecture.png" alt="Architecture of Matcha-TTS" width="750"/> -->
|
||||||
|
|
||||||
<script>
|
<script>
|
||||||
|
|
||||||
@@ -519,6 +518,4 @@ Currently loaded stimulus: <span id="stimuli-from-listening-test-span" style="fo
|
|||||||
}
|
}
|
||||||
```
|
```
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
[][this_page]
|
[][this_page]
|
||||||
|
|||||||
Reference in New Issue
Block a user