Downloads · 30 days
79
100% of all-time downloads
dune_codec
Respair/dune_codec
dune_codec is a machine learning model from Respair. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-4.0.
Dune (doo-neh دونه as I like to call it, or just the english dune) is a fast and compact 12.5hz speech tokenizer trained on tens of thousands of hours of multilingual data. <br
All-time downloads
79
Public
Repo size
1.4 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pth1.4 GB · 100%
At a glance
- License
- cc-by-4.0
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 16, 2026
- SHA
- 69ac3c44
Spaces
Model card
From the Hugging Face model README
Details
Dune (doo-neh دونه as I like to call it, or just the english dune) is a fast and compact 12.5hz speech tokenizer trained on tens of thousands of hours of multilingual data. <br>
the encoder is based on nvidia's nano codec architecture that compresses your audio to 22khz FSQ tokens; the decoder, using a different design then reconstructs your input to high quality 44.1khz.
Batched Extraction / Inference
fill in the path to your data in dune_extraction.py, then run it. <br><br>
~$ python dune_extraction.py
Important note
this is strictly a speech tokenizer, trained only on human speech; it won't do well with music.
- License
- cc-by-4.0
- Languages
- fa, ru, en, ja, ar
- Created
- Sep 3, 2026
- Updated
- Sep 16, 2026