GitHub - ksw0306/FloWaveNet: A Pytorch implementation of "FloWaveNet: A Gen...
source link: https://github.com/ksw0306/FloWaveNet
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
README.md
FloWaveNet : A Generative Flow for Raw Audio
This is a PyTorch implementation of our work "FloWaveNet : A Generative Flow for Raw Audio".
For a purpose of parallel sampling, we propose FloWaveNet, a flow-based generative model for raw audio synthesis. FloWaveNet can generate audio samples as fast as ClariNet and Parallel WaveNet, while the training procedure is really easy and stable with a single-stage pipeline. Our generated audio samples are available at http://bit.ly/2zpsElV. Also, our implementation of ClariNet (Gaussian WaveNet and Gaussian IAF) is available at https://github.com/ksw0306/ClariNet
Requirements
- PyTorch 0.4.1
- Python 3.6
- Librosa
Examples
Step 1. Download Dataset
- LJSpeech : https://keithito.com/LJ-Speech-Dataset/
Step 2. Preprocessing (Preparing Mel Spectrogram)
python preprocessing.py --in_dir ljspeech --out_dir DATASETS/ljspeech
Step 3. Train
python train.py --model_name flowavenet --batch_size 8 --n_block 8 --n_flow 6 --n_layer 2 --causal no
Step 4. Synthesize
--load_step CHECKPOINT
: the # of the pre-trained model's global training step (also depicted in the trained weight file)
--temp
: Temperature (standard deviation) value implemented as z ~ N(0, 1 * TEMPERATURE)
ex) python synthesize.py --model_name flowavenet --n_block 8 --n_flow 6 --n_layer 2 --causal no --load_step 100000 --temp 0.7 --num_samples 10
Sample Link
Sample Link : http://bit.ly/2zpsElV
Our implementation of ClariNet (Gaussian WaveNet, Gaussian IAF) : https://github.com/ksw0306/ClariNet
-
Results 1 : Model Comparisons (WaveNet (MoL, Gaussian), ClariNet and FloWaveNet)
-
Results 2 : Temperature effect on Audio Quality Trade-off (Temperature T : 0.0 ~ 1.0, Model : Gaussian IAF and FloWaveNet)
-
Results 3 : Analysis of ClariNet Loss Terms (Loss functions : 1. KLD + Frame Loss 2. Only KL 3. Only Frame)
-
Results 4 : Context Block and Long term Dependency (FloWaveNet : 8 Context Blocks, FloWaveNet_small : 6 Context Blocks)
-
Results 5 : Causality of WaveNet Dilated Convolutions (FloWaveNet : Non-causal WaveNet Affine Coupling Layers, FloWaveNet_causal : Causal WaveNet Affine Coupling Layers)
Reference
- WaveNet vocoder : https://github.com/r9y9/wavenet_vocoder
- glow-pytorch : https://github.com/rosinality/glow-pytorch
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK