marksverdhei/Qwen3-Voice-Embedding-12Hz-1.7B

Update README.md

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload config.json with huggingface_hub

Upload tokenizer_config.json with huggingface_hub

Upload tokenizer_ecapa_tdnn.py with huggingface_hub

docs: use AutoProcessor as primary API (cleaner than AutoFeatureExtractor)

docs: add AutoFeatureExtractor usage, document pipeline limitation

fix: add sampling_rate alias for HF pipeline compat

fix: update preprocessor config with feature extractor class

feat: add audio feature extractor for pipeline support

fix: add feature extractor for pipeline support

fix: add AutoModelForFeatureExtraction to auto_map for pipeline support

fix: mark as adapter of base model, not fine-tune

fix: update repo names in README

Initial release: ECAPA-TDNN speaker encoder from Qwen3-TTS 1.7B (2048-dim)

initial commit