🤝 Open to Collab

Ivan PRO

aufklarer

·

https://blog.ivan.digital

AI & ML interests

GenAI

Recent Activity

updated a Space 25 minutes ago

aufklarer/full-duplex-leaderboard

updated a dataset about 14 hours ago

aufklarer/central-bank-communications

repliedto their post 8 days ago

We’ve published Soniqo’s voice-agent leaderboard and an article explaining what we measured. https://huggingface.co/spaces/aufklarer/full-duplex-leaderboard The board covers three parts of a speech system: - Turn-taking · TurnBench: detecting turn endings, false alarms and decision delay. - Commands · SLURP: choosing the correct tool and matching its argument values. - Voice style · InstructTTSEval: following voice descriptions, delivery directions and role-play instructions, with separate scores for each. Models include VAP, p99, Smart Turn, Qwen3-TTS, VoxCPM2, FireRedTTS3 and MOSS-VoiceGenerator, alongside cloud configurations from OpenAI, Google, AWS and ElevenLabs. Each table shows run sizes and links to the protocol. We also published https://huggingface.co/aufklarer/P99-Turn-1-Mini-CoreML, https://huggingface.co/aufklarer/VAP-OTO-CoreML and https://huggingface.co/soniqo/VAP-OTO-ONNX exports. Both models have native Swift APIs; VAP also has C++ and Android support. Explore the leaderboard https://huggingface.co/spaces/aufklarer/full-duplex-leaderboard · Read the article https://soniqo.audio/blog/voice-agent-benchmarks

View all activity

Organizations

aufklarer 's models 170

aufklarer/F5TTS-v1-Base-MLX-fp16

Text-to-Speech • 0.3B • Updated Jul 10 • 101

aufklarer/IndexTTS2-MLX-fp16

Text-to-Speech • Updated Jul 8 • 144

aufklarer/Audio2Face-3D-v2.3.1-Claire-MLX

Updated Jul 7 • 31 • 1

aufklarer/Audio2Face-3D-v2.3.1-James-MLX

Updated Jul 7 • 29

aufklarer/Audio2Face-3D-v2.3-Mark-MLX

Updated Jul 7 • 37 • 2

aufklarer/Chatterbox-Flash-CoreML

Text-to-Speech • Updated Jul 7 • 49

aufklarer/CosyVoice3-0.5B-MLX-8bit-full

Text-to-Speech • Updated Jul 6 • 84

aufklarer/CosyVoice3-0.5B-MLX-bf16

Text-to-Speech • Updated Jul 6 • 569

aufklarer/Whisper-Large-v3-Turbo-CoreML

Automatic Speech Recognition • Updated Jul 1 • 875 • 3

aufklarer/Fish-Audio-S2-Pro-MLX-fp16

Text-to-Speech • 5B • Updated Jun 29 • 70 • 1

aufklarer/Silero-VAD-v6.2.1-MLX

Audio Classification • 309k • Updated Jun 28 • 10.7k • 1

aufklarer/WavLM-Base-Plus-MLX-fp16

Feature Extraction • 94.4M • Updated Jun 27 • 33

aufklarer/CosyVoice3-0.5B-MLX-8bit

Text-to-Speech • Updated Jun 27 • 221

aufklarer/Silero-VAD-v6.2.1-CoreML

Voice Activity Detection • Updated Jun 27 • 1.41k • 2

aufklarer/Indic-Mio-MLX-fp16

Text-to-Speech • 0.6B • Updated Jun 26 • 83 • 1

aufklarer/Chatterbox-Multilingual-hi-MLX-fp16

Text-to-Speech • 0.6B • Updated Jun 25 • 16 • 1

aufklarer/gemma-4-E2B-it-MLX-2bit

Text Generation • 5B • Updated Jun 25 • 17

aufklarer/gemma-4-E2B-it-MLX-4bit

Text Generation • 5B • Updated Jun 25 • 16

aufklarer/gemma-4-E4B-it-MLX-2bit

Text Generation • 7B • Updated Jun 25 • 33

aufklarer/gemma-4-E4B-it-MLX-4bit

Text Generation • 7B • Updated Jun 25 • 30 • 1

aufklarer/OmniVoice-MLX-int8

Text-to-Speech • 0.6B • Updated Jun 25 • 38 • 1

aufklarer/Supertonic-3-CoreML

Text-to-Speech • Updated Jun 24 • 4.64k

aufklarer/Supertonic-3-CoreML-FP16

Text-to-Speech • Updated Jun 24 • 1.51k • 1

aufklarer/Qwen3-4B-Instruct-2507-MLX-5bit

Text Generation • 4B • Updated Jun 24 • 21

aufklarer/Qwen3-4B-Instruct-2507-MLX-4bit

Text Generation • 4B • Updated Jun 24 • 270 • 1

aufklarer/OmniVoice-MLX-fp16

Text-to-Speech • 0.6B • Updated Jun 24 • 47

aufklarer/Chatterbox-Multilingual-MLX-fp16

Text-to-Speech • 0.6B • Updated Jun 23 • 1.18k • 1

aufklarer/Qwen3-ForcedAligner-0.6B-CoreML-INT8

Audio Classification • Updated Jun 23 • 167 • 2

aufklarer/Qwen3-ForcedAligner-0.6B-CoreML-FP16

Audio Classification • Updated Jun 23 • 85

aufklarer/Qwen3-ASR-1.7B-MLX-5bit

1.0B • Updated Jun 21 • 338