Nikita Torgashov PRO

herimor

·

https://herimor.github.io

AI & ML interests

Text-to-Speech, Speaker Recognition

Recent Activity

authored a paper about 9 hours ago

FASTDIAR: Frame-level speaker encoder for Streaming Diarization

updated a model about 12 hours ago

herimor/voxtream2

updated a model about 12 hours ago

herimor/voxtream2.1

View all activity

Organizations

herimor 's Spaces 3

VoXtream

Generate speech from text and an audio prompt

VoXtream2

Zero-shot TTS with Controllable Speaking-rate

FASTDIAR

Streaming speaker diarization with a 960 ms delay