marksverdhei/Qwen3-Voice-Embedding-12Hz-1.7B
Same weights, repacked (fewer layers) vs Qwen/Qwen3-TTS-12Hz-1.7B-Base. marksverdhei/Qwen3-Voice-Embedding-12Hz-1.7B matches part of Qwen/Qwen3-TTS-12Hz-1.7B-Base (76 of its 480 tensors; the rest of Qwen/Qwen3-TTS-12Hz-1.7B-Base has no counterpart). On the shared part: Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: other 0/76