Gradium open-sources Phonon, a 31M-parameter on-device TTS model
Original title: Gradium Open-Sources Phonon, a 31M-Parameter On-Device TTS Model Under Apache 2.0
The release is licensed under Apache 2.0; the article body was not available beyond the title.
Gradium has open-sourced Phonon, described as a 31-million-parameter text-to-speech model intended to run on device. The stated license is Apache 2.0. No benchmarks, languages, hardware targets, or release date beyond the publication listing were available in the captured text.
Unconfirmed: Only the headline was available; model details beyond size, on-device use, and the Apache 2.0 license are not confirmed.
- Phonon is described as a 31M-parameter model.
- The stated license is Apache 2.0.
- It is positioned as on-device text-to-speech.
From the original article
14 min read at marktechpost.com
Gradium has open-sourced Phonon, a family of on-device text-to-speech models. The English Phonon 31m ships under Apache 2. 0, fits in 64.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.