Encodec Based Neural Audio Waveform Reconstruction

via “neural vocoding with waveform reconstruction”

text-to-speech model by undefined. 17,45,116 downloads.

Unique: Uses a pre-trained, frozen neural vocoder rather than training vocoding jointly with TTS, enabling modular architecture where vocoder can be swapped without retraining the TTS model. Vocoder is optimized for mel-spectrogram inversion specifically, not general audio generation.

vs others: Faster and higher quality than Griffin-Lim phase reconstruction (traditional signal processing approach) but slower and less controllable than end-to-end neural waveform models like WaveNet or Glow-TTS that generate waveforms directly from text.