{"data":{"slug":"kan-bayashi-parallelwavegan","name":"ParallelWaveGAN","tagline":"Unofficial Parallel WaveGAN (+ variants) with Pytorch for speech synthesis","github_url":"https://github.com/kan-bayashi/ParallelWaveGAN","owner":"kan-bayashi","repo":"ParallelWaveGAN","owner_avatar_url":"https://avatars.githubusercontent.com/u/22779813?v=4","primary_language":"Jupyter Notebook","stars":1644,"forks":352,"topics":["hifigan","melgan","neural-vocoder","parallel-wavenet","pytorch","realtime","speech-synthesis","style-melgan","text-to-speech","tts","vocoder","wavenet"],"archived":false,"github_pushed_at":"2024-04-22T02:36:29+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/kan-bayashi-parallelwavegan","markdown_url":"https://www.graphcanon.com/tools/kan-bayashi-parallelwavegan.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/kan-bayashi-parallelwavegan","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=kan-bayashi-parallelwavegan","description":"Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch","homepage_url":"https://kan-bayashi.github.io/ParallelWaveGAN/","license":"MIT","open_issues":43,"watchers":45,"ai_summary":"Repository containing implementations of various neural vocoders such as MelGAN, Multi-band MelGAN, HiFi-GAN, and StyleMelGAN using PyTorch.","readme_excerpt":"## Requirements\n\nThis repository is tested on Ubuntu 20.04 with a GPU Titan V.\n\n- Python 3.8+\n- Cuda 11.0+\n- CuDNN 8+\n- NCCL 2+ (for distributed multi-gpu training)\n- libsndfile (you can install via `sudo apt install libsndfile-dev` in ubuntu)\n- jq (you can install via `sudo apt install jq` in ubuntu)\n- sox (you can install via `sudo apt install sox` in ubuntu)\n\nDifferent cuda version should be working but not explicitly tested.  \nAll of the codes are tested on Pytorch 1.8.1, 1.9, 1.10.2, 1.11.0, 1.12.1, 1.13.1, 2.0.1 and 2.1.0.\n\n---\n\n# If you want to use distributed training, please install\n\n---\n\n# command to install apex.\n$ make apex\n```\n\nNote that we specify cuda version used to compile pytorch wheel.  \nIf you want to use different cuda version, please check `tools/Makefile` to change the pytorch wheel to be installed.\n\n---\n\n# If not, please install via pip\n$ pip install parallel_wavegan\n\n---\n\n# Please install this repository in ESPnet conda (or virtualenv) environment\n$ . ./path.sh && pip install -U parallel_wavegan","github_created_at":"2019-10-29T02:32:35+00:00","created_at":"2026-07-11T12:10:12.393832+00:00","updated_at":"2026-07-11T23:04:06.630974+00:00","categories":[{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"parallel-wavenet","name":"parallel-wavenet"},{"slug":"style-melgan","name":"style-melgan"},{"slug":"realtime","name":"realtime"},{"slug":"hifigan","name":"hifigan"},{"slug":"pytorch","name":"pytorch"},{"slug":"speech-synthesis","name":"speech-synthesis"},{"slug":"melgan","name":"melgan"},{"slug":"neural-vocoder","name":"neural-vocoder"}],"trust":{"provenance":{"is_fork":false,"github_id":218188149,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T12:10:13.029Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":810,"last_release_at":"2023-11-13T01:53:16Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:10:15.706Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T23:04:06.532Z"},"languages":{"value":["jupyter notebook"],"source":"github.language","observed_at":"2026-07-11T23:04:06.532Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-11T23:04:06.532Z"}}}}