aufklarer/central-bank-communications
Viewer • Updated • 284k • 4.42k • 6
Ivan PRO
aufklarer
AI & ML interests
GenAI
Recent Activity
updated a dataset about 12 hours ago
aufklarer/central-bank-communicationsOrganizations
updated a
dataset about 12 hours ago
Add Neural Engine-compatible forced-aligner decoder
#2 opened 1 day ago
by aufklarer
Add Neural Engine-compatible forced-aligner decoder
#2 opened 1 day ago
by aufklarer
liked a
Space 4 days ago
Add CPU-compatible decoder with Float32 normalization
#1 opened 4 days ago
by aufklarer
Add CPU-compatible decoder with Float32 normalization
#1 opened 4 days ago
by aufklarer
updated a
Space 5 days ago
replied to their post 13 days ago
Along actual tools names, also arguments detection is another problem.
reacted to their post with 😎 14 days ago
Post
3,262
We’ve published Soniqo’s voice-agent leaderboard and an article explaining what we measured.
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 aufklarer/P99-Turn-1-Mini-CoreML, aufklarer/VAP-OTO-CoreML and soniqo/VAP-OTO-ONNX exports. Both models have native Swift APIs; VAP also has C++ and Android support.
Explore the leaderboard aufklarer/full-duplex-leaderboard · Read the article https://soniqo.audio/blog/voice-agent-benchmarks
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 aufklarer/P99-Turn-1-Mini-CoreML, aufklarer/VAP-OTO-CoreML and soniqo/VAP-OTO-ONNX exports. Both models have native Swift APIs; VAP also has C++ and Android support.
Explore the leaderboard aufklarer/full-duplex-leaderboard · Read the article https://soniqo.audio/blog/voice-agent-benchmarks
- 5 replies
posted an update 14 days ago
Post
3,262
We’ve published Soniqo’s voice-agent leaderboard and an article explaining what we measured.
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 aufklarer/P99-Turn-1-Mini-CoreML, aufklarer/VAP-OTO-CoreML and soniqo/VAP-OTO-ONNX exports. Both models have native Swift APIs; VAP also has C++ and Android support.
Explore the leaderboard aufklarer/full-duplex-leaderboard · Read the article https://soniqo.audio/blog/voice-agent-benchmarks
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 aufklarer/P99-Turn-1-Mini-CoreML, aufklarer/VAP-OTO-CoreML and soniqo/VAP-OTO-ONNX exports. Both models have native Swift APIs; VAP also has C++ and Android support.
Explore the leaderboard aufklarer/full-duplex-leaderboard · Read the article https://soniqo.audio/blog/voice-agent-benchmarks
- 5 replies
updated 3
models 14 days ago
updated 2
collections 15 days ago
published 3
models 15 days ago
Document optimized Breeze Swift runtime performance
#1 opened 15 days ago
by aufklarer