Mel-FullSubNet + Vocos training

Audio-WestlakeU / FullSubNet

PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."

https://fullsubnet.readthedocs.io/en/latest/

MIT License

553 stars 157 forks source link

Mel-FullSubNet + Vocos training #71

Open JBloodless opened 2 months ago

JBloodless commented 2 months ago

Is there any chance that you will share how did you merge Mel-FullSubNet and Vocos and what modifications did you make for Vocos? And also - what was the target for joint training? Vocos gets FSN output and target clean waveform?