Post
4654
Researchers developed Sonic AI enabling precise facial animation from speech cues 🎧 Decouples head/expression control via audio tone analysis + time-aware fusion for natural long-form synthesis
Kadir Nar
kadirnar
AI & ML interests
AI Research Engineer 🤖 Building Omni & TTS Models
Recent Activity
updated
a model
1 day ago
Closed-TTS/Pre-En-JA-ALL
published
a model
1 day ago
Closed-TTS/Pre-En-JA-ALL
updated
a model
3 days ago
kadirnar/WavTokenizer
Organizations
Posts
8
Post
3784
I created my own AI image and video from scratch using the fal.ai platform 💫
Workflow: Flux Lora Training + Upscale + Kling AI(1.6)
Workflow: Flux Lora Training + Upscale + Kling AI(1.6)
spaces
18
Running
95
Yolov10
📉
Identify and label objects in images
Running
Grok Game
⚡
Building
on
A10G
480
ComfyUI-Demo
⚡
Display loading spinner with Hugging Face logo
Runtime error
14
AuroFlow V3
🐠
Generate images from text prompts
Runtime error
5
LeYOLO
😻
Detect objects in an image
Runtime error
71
Yolov9
🏃
State-of-the-art Object Detection YOLOV9 Demo
models
171
kadirnar/WavTokenizer
Updated
kadirnar/pre-ko-ja-test-v2
Updated
•
5
kadirnar/pre-ko-ja-test
Updated
•
2
kadirnar/Orpheus-Pre-Emilia-Ja
Updated
kadirnar/Qwen2.5-1.5M-TTS
Updated
kadirnar/Orpheus-Pretrain-De
Updated
kadirnar/Orpheus-TTS-Nekopara
Text Generation
•
Updated
•
7
kadirnar/Orpheus-Anime-Speech-v2-Beta
Text Generation
•
Updated
•
11
kadirnar/Orpheus-AKIN-TR
Text Generation
•
Updated
•
8
kadirnar/Orpheus-Cml
Text Generation
•
Updated
•
10
•
1
datasets
41
kadirnar/mls_eng_10k
Updated
•
23
kadirnar/pre-ko-ja-test-v2
Updated
•
8
kadirnar/Combined-Japanese-TTS
Viewer
•
Updated
•
326k
•
226
kadirnar/belebele-italian
Viewer
•
Updated
•
898
•
38
kadirnar/Hscene-Speech
Viewer
•
Updated
•
585k
•
21
kadirnar/moe-speech-plus
Updated
•
19
kadirnar/Emilia-All-Ja-Phi-4-mini-instruct
Viewer
•
Updated
•
1.32M
•
73
kadirnar/Emilia-All-Ja-Qwen-Orpheus
Viewer
•
Updated
•
1.32M
•
19
kadirnar/Emilia-Yodas-JA
Viewer
•
Updated
•
454k
•
142
kadirnar/Emilia-JA
Viewer
•
Updated
•
870k
•
83