Home/Models/marksverdhei/Qwen3-Voice-Embedding-12Hz-1.7B
Qwen3-Voice-Embedding-12Hz-1.7B
marksverdhei/Qwen3-Voice-Embedding-12Hz-1.7B
- kind
- original
- quant
- bf16 (16-bit)
- family
- qwen
- modality
- feature-extraction
- root model
- Qwen/Qwen3-TTS-12Hz-1.7B-Base
- provider
- marksverdhei
- license
- apache-2.0
- language
- —
- context
- —
- library
- transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 17,341
- likes
- 27
- created
- —
- last modified
- 2026-02-23T09:13:03+00:00 (2026)
- huggingface
- https://huggingface.co/marksverdhei/Qwen3-Voice-Embedding-12Hz-1.7B
- tags
- transformerssafetensorsecapa_tdnn_speaker_encoderfeature-extractiontext-to-audioaudio-to-audioaudio-classificationspeaker-embeddingecapa-tdnnx-vectorqwen3-ttscustom_codearxiv:2005.07143arxiv:2601.15621base_model:Qwen/Qwen3-TTS-12Hz-1.7B-Basebase_model:adapter:Qwen/Qwen3-TTS-12Hz-1.7B-Baselicense:apache-2.0region:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.