jik876/hifi-gan
A GAN-based deep learning model for efficient and high-fidelity text-to-speech synthesis.
Not currently ranked — collecting fresh signals.
star history
HiFi-GAN is a generative adversarial network architecture for speech synthesis that achieves high fidelity audio generation by modeling periodic patterns in audio signals. The model generates 22.05 kHz audio at 167.9x real-time on a single V100 GPU, with a CPU-optimized variant achieving 13.4x real-time performance. It supports mel-spectrogram inversion for arbitrary speakers and can be used as an end-to-end vocoder in larger text-to-speech pipelines.
Frequently asked
- What is jik876/hifi-gan?
- A GAN-based deep learning model for efficient and high-fidelity text-to-speech synthesis.
- Is hifi-gan open source?
- Yes — jik876/hifi-gan is open source, released under the MIT license.
- What language is hifi-gan written in?
- jik876/hifi-gan is primarily written in Python.
- How popular is hifi-gan?
- jik876/hifi-gan has 2.4k stars on GitHub.
- Where can I find hifi-gan?
- jik876/hifi-gan is on GitHub at https://github.com/jik876/hifi-gan.