voice-clone-vocoder / Readme.md
AJ50's picture
Add vocoder model with config and documentation
c0bd6fb verified

Vocoder Model

This directory contains the pre-trained vocoder model for converting mel-spectrograms to audio waveforms.

Model Details

  • File: vocoder.pt
  • Input: Mel-spectrograms
  • Output: Audio waveform

Usage

# Load the vocoder model
vocoder = torch.load('vocoder.pt')
vocoder.eval()

# Generate audio from mel-spectrogram
with torch.no_grad():
    audio = vocoder(mel_spectrogram)

Dependencies

  • PyTorch
  • NumPy
  • Audio processing libraries (for waveform handling)

Model Configuration

See config.json for model architecture and training parameters.