LeeSangHoon/WaveGen
archived · low-signalmodel
WaveGen (Fine-tuned with v-spec losses) is the recommended model for inference and the default in the source repository. License: cc-by-nc-4.0. Vendor-reported: "WaveGen achieves state-of-the-art performance among TTS models trained on the Emilia dataset."
- Vendor-reported: WaveGen achieves state-of-the-art performance among TTS models trained on the Emilia dataset.
- Org
- LeeSangHoon
- Released
- 2026-11-07
- Status
- archived · low-signal
- License
- cc-by-nc-4.0 (restricted)
- Task
- text-to-speech · audio
- Signal
- 4 HF likes · 79 downloads
- Archived
- 2026-11-14 (low-signal: aged out below threshold; stats as last seen)
Links
First published here 2026-11-07 · updated 2026-11-15 · markdown · JSON