MOSS-Audio-Tokenizer (TinyPine mirror)

MOSS-Audio-Tokenizer, the audio codec of MOSS-VoiceGenerator, by the OpenMOSS team, unmodified, mirrored so TinyPine Studio's installer does not depend on third-party download links. TinyPine did not train or change the model. Upstream: OpenMOSS-Team/MOSS-Audio-Tokenizer. Licence: apache-2.0 (LICENSE, the licence text; the upstream model card states the licence).

SHA-256 of the large files:

  • images/arch.png 6a7108429fc230ead608a22837a27615aae3458f86e5e47d12fd3bd5d95c7058
  • images/pesq-nb.png 107c2f8fb91247264497b50f0bb42f34390ce4593eed28ce4dfea47b88a36797
  • images/pesq-wb.png ae7b264b13e8570c292d8843ce83fcf21e96360e2900c8e19a8ff837be3c90fd
  • images/sim.png 79c6340a32e1229ab89fdc71447aa0addf91f146d250b1c3416707c5aacee75d
  • images/stoi.png 86d2a427d213fbd8913052d0d16e87c2384a6643f26458314c8771b95eab89c4
  • model-00001-of-00002.safetensors 037f441ed30a0ab59f6049de83b824a1b3bd6feb7dbd46c3fbca41fc2f649f28
  • model-00002-of-00002.safetensors a187d73d2cda1c2d0676586d9d03c09c0a5813450266af32029c871493fc9582
Downloads last month
-
Safetensors
Model size
2B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support