MOSS-Audio-Tokenizer-v2 (TinyPine mirror)

MOSS-Audio-Tokenizer-v2, the 48 kHz audio codec of MOSS-TTS v1.5, 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-v2. Licence: apache-2.0 (LICENSE, the licence text; the upstream model card states the licence).

SHA-256 of the large files:

  • demo/demo_gt.wav 631608f5c8b931ece1d45adc7f40a3b3b0ae2ec056a8a08a3565b04cc5750a4b
  • images/arch.png 6a7108429fc230ead608a22837a27615aae3458f86e5e47d12fd3bd5d95c7058
  • images/metric.png 8908818d76057ed665f2e2406c6fc2e8e62eb75e8f63e2d189847a608396ca91
  • model-00001-of-00003.safetensors 2d9f9182f17b143a23937feb87c63c08221bd28e685e4bc2fa55dcdce17fcde7
  • model-00002-of-00003.safetensors d4e48106d0254fe3b00ea0707e88fc6aee076993825e108dd9cef847f9db236e
  • model-00003-of-00003.safetensors d0449fe1b0ef1f6045946867148d8166b9a91a58d0feca4a18b641494d0b22da
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