Selim Özten
comarproject
AI & ML interests
AI Engineer building Turkish language models. Creator of lale (Turkish instruct model) and terazi (Turkish LM benchmark). Co-founder @ inpocket.ai
Recent Activity
upvoted an article about 19 hours ago
Deploy GLM-5.2-FP8 as your open, frontier-level agent liked a dataset about 19 hours ago
Glint-Research/Fable-5-traces liked a dataset about 19 hours ago
LiquidAI/antidoom-mix-v1.0Organizations
a collection of text to speech papers.
-
BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data
Paper • 2402.08093 • Published • 61 -
E3 TTS: Easy End-to-End Diffusion-based Text to Speech
Paper • 2311.00945 • Published • 16 -
Matcha-TTS: A fast TTS architecture with conditional flow matching
Paper • 2309.03199 • Published • 15 -
Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
Paper • 1712.05884 • Published • 3
a collection of text to speech papers.
-
BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data
Paper • 2402.08093 • Published • 61 -
E3 TTS: Easy End-to-End Diffusion-based Text to Speech
Paper • 2311.00945 • Published • 16 -
Matcha-TTS: A fast TTS architecture with conditional flow matching
Paper • 2309.03199 • Published • 15 -
Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
Paper • 1712.05884 • Published • 3
datasets 0
None public yet