ASTRAL-quantization / README.md
rtikw's picture
Unmodified mirror of Plachta/ASTRAL-quantization (GPL-3.0), taken 2026-08-26
3e2e9e3 verified
|
Raw
History Blame Contribute Delete
962 Bytes
metadata
license: gpl-3.0
pipeline_tag: automatic-speech-recognition
language:
  - en
  - zh
  - ja
  - kr
  - ru
  - ta
  - es
  - fr
  - de
  - it
  - pt
  - kn
  - nl

ASTRAL-quantization (mirror)

An unmodified, file-for-file mirror of Plachta/ASTRAL-quantization, taken 2026-08-26. All credit to Plachta; GPL-3.0 as licensed upstream (full text in LICENSE).

From the original card: "This is a speech linguistic content quantizer [that] operates on Hubert-large features. It is trained with explicit ASR supervision to preserve more linguistic content while discarding more speaker traits."

Contents: the bsq32 and bsq2048 quantizers (full pytorch_model.bin + *_light.pth + configs). The light checkpoints are the content extractors of Seed-VC V2.

Mirrored for use in a local macOS music app — archival insurance against the original (a personal account) going away; the app downloads from the original while it exists.