8 1 62

Florian Lux PRO

Flux9665

https://www.ims.uni-stuttgart.de/en/institute/team/Lux/

AI & ML interests

Text-to-Speech, Speech Processing, Low Resource

Recent Activity

liked a model 3 days ago

nvidia/nemo-nano-codec-22khz-1.78kbps-12.5fps

updated a model about 1 month ago

Flux9665/random_files

liked a model about 1 month ago

thewh1teagle/phonikud-onnx

View all activity

Organizations

None yet

Flux9665 's Spaces 12

219

MassivelyMultilingualTTS

🌍

Generate speech from text in multiple languages

ArticulatoryFeatures

🗣

Visualize articulatory features of a sentence

LatentSync

👄

Audio Conditioned LipSync with Latent Diffusion Models

NeutralToucan

🎨

Generate speech from IPA symbols

SimpleToucanTTS

🦜

Generate speech from text input

NearestNeighborLanguages

🌍

Visualize language relationships based on different distance metrics

LanguageDistance

🌎

Compare language distances using various metrics

Transform poetry readings with customizable voice controls

ThisSpeakerDoesNotExist

🗣

Design and customize a speaker's voice

Multilingual TTS

🌍

Convert text into speech in multiple languages