ComfyUI nodes for Qwen3-ASR (0.6B/1.7B) and ForcedAligner. Supports high-accuracy ASR and language identification for 52 languages/dialects, including 22 Chinese dialects and various English accents. Features word-level timestamps, long audio transcription, and VRAM-optimized inference.
https://github.com/kaushiknishchay/ComfyUI-Qwen3-ASR
git clone https://github.com/kaushiknishchay/ComfyUI-Qwen3-ASR
comfy node install ComfyUI-Qwen3-ASR