GitHub - broutonlab/mellotron-style-transfer: Voice and music style transfer in depth with Nvidia Mellotron
![NVIDIA Research Unveils Flowtron, an Expressive and Natural Speech Synthesis Model | NVIDIA Developer Blog NVIDIA Research Unveils Flowtron, an Expressive and Natural Speech Synthesis Model | NVIDIA Developer Blog](https://developer-blogs.nvidia.com/wp-content/uploads/2020/05/flowtron_Feature.png)
NVIDIA Research Unveils Flowtron, an Expressive and Natural Speech Synthesis Model | NVIDIA Developer Blog
![Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens | DeepAI Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens | DeepAI](https://images.deepai.org/publication-preview/mellotron-multispeaker-expressive-voice-synthesis-by-conditioning-on-rhythm-pitch-and-global-style-tokens-page-4-medium.jpg)
Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens | DeepAI
![Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens - NVIDIA ADLR Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens - NVIDIA ADLR](https://nv-adlr.github.io/images/mellotron_logo.png)