Unverified50% confidenceFactExact time
Marimba proposes using a frozen Qwen3-ASR 0.6B feature extractor as the backbone, paired with lightweight task-specific readout layers, to handle multiple speech decision tasks in a unified way.
1
Sources
50%
Confidence
Long-term
Relevance
11/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe voice stack consists of four core components: Qwen 3.6 35B (a mixture-of-experts model), Whisper, Breeze TTS2 (3.5B parameters), and Celery VAD.70% similarUnverifiedNari has launched two speech models based on Qwen3: a text-to-speech (TTS) model and an automatic speech recognition (ASR) model66% similarUnverifiedThis local voice assistant system is fully self-hosted, with voice detection and recognition running on the CPU, the LLM (Gemma 4 E4B, QAT q4_0 quantization, based on llama.cpp) responsible for generating answers, and the TTS (Qwen3-TTS 1.7B) synthesizing speech sentence by sentence.66% similarUnverifiedQwen-Audio-3.1 consists of five models, covering all stages of audio processing including understanding, generation, interaction, and creation.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1173838API
curl https://kongchang.com/api/v1/knowledge/claims/1173838MCP
get_claim(id=1173838)