Independent publisher

Whit3rabbit

cowWhySo

Hobby

Models in Library1

Datasets in Library0

Models on Hugging Face21

Followers10

Compare the published evidence

This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.

Published tasks: Text to speech.

Reported licenses: apache-2.0. Open a record to review its specific license and conditions.

Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.

Models

Model · Text to speech

MegaTTS3-TurboSpark

Whit3rabbit

MegaTTS3 (ByteDance) converted to safetensors for TurboSpark's Rust runtime. Each component lives in its own folder (alignerlm/, diffusiontransformer/, durationlm/, wavvae/, g2p/); manifest.json lists every file's sha256. See NOTICE.md for the exact sources and their hashes. The WavVAE encoder's origin and license are unverified; read the notice before redistributing. Clone only voices you have the right to use.

Open weights apache-2.0

View model