Skip to content

Latest commit

 

History

History
executable file
·
63 lines (42 loc) · 1.69 KB

README.md

File metadata and controls

executable file
·
63 lines (42 loc) · 1.69 KB
Raw

SiD-Waveflow

This work is the implemention of SiD-Waveflow.

Visit our website for audio samples.

Setup

  1. Clone our repo and initialize submodule

    git clone https://github.com/NVIDIA/waveglow.git
cd waveglow
git submodule init
git submodule update

  2. Install requirements pip3 install -r requirements.txt

  3. Install Apex

Train your own model

  1. Download CSMSC. In this example it's in ~/BBdata/

  2. Train

    mkdir checkpoints
python train.py -c config.json

    For mixed precision training set "fp16_run": true on config.json.

  3. Make test set mel-spectrograms

    python mel2samp.py -f traintestset_chn/test_files_copy.txt -o ./inferaudio/chn_mel -c config.json

  4. Do inference with your network

    ls inferaudio/chn_mel/*.pt > mel_files.txt
python3 inference.py -f mel_files.txt -w checkpoints/test1_chn_model -o ./inferaudio --is_fp16 -s 0.6