In our recent paper, we propose WaveGlow: a flow-based network capable of generating high quality speech from mel-spectrograms. WaveGlow combines insights from Glow and WaveNet in order to provide fast, efficient and high-quality audio synthesis, without the need for auto-regression. WaveGlow is implemented using only a single network, trained using only a single cost function: maximizing the likelihood of the training data, which makes the training procedure simple and stable.
pip3 install -r requirements.txt
Download and extract the LJ Speech dataset in the current directory;
$ python3 train.py -c config.json
Warning: DDP & AMP(mixed precision training set
"fp16_run": true
onconfig.json
)
$ python3 distributed.py -c config.json
Card Type | Single Card | 8 Cards |
---|---|---|
BI | 196.845 | 1440.233 |
Card Type | Single Card | 8 Cards |
---|---|---|
BI | 351.040 | 2400.745 |
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》