{"id":13862277,"url":"https://github.com/mazzzystar/WaveGAN-pytorch","last_synced_at":"2025-07-14T11:33:15.860Z","repository":{"id":105064791,"uuid":"141133046","full_name":"mazzzystar/WaveGAN-pytorch","owner":"mazzzystar","description":"PyTorch implementation of \" Synthesizing Audio with Generative Adversarial Networks\"","archived":false,"fork":false,"pushed_at":"2020-06-08T12:37:57.000Z","size":450,"stargazers_count":64,"open_issues_count":4,"forks_count":15,"subscribers_count":6,"default_branch":"master","last_synced_at":"2024-11-20T18:53:47.155Z","etag":null,"topics":["ai-music","gan","generative-model","music-generation","wavegan","wavegan-pytorch"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1802.04208","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mazzzystar.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2018-07-16T12:03:08.000Z","updated_at":"2024-07-08T08:21:26.000Z","dependencies_parsed_at":null,"dependency_job_id":"d12a0223-309b-4bce-b6f9-09106c7350b2","html_url":"https://github.com/mazzzystar/WaveGAN-pytorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mazzzystar%2FWaveGAN-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mazzzystar%2FWaveGAN-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mazzzystar%2FWaveGAN-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mazzzystar%2FWaveGAN-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mazzzystar","download_url":"https://codeload.github.com/mazzzystar/WaveGAN-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225974402,"owners_count":17553944,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-music","gan","generative-model","music-generation","wavegan","wavegan-pytorch"],"created_at":"2024-08-05T06:01:40.987Z","updated_at":"2024-11-22T22:30:53.427Z","avatar_url":"https://github.com/mazzzystar.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# WaveGAN-pytorch\nPyTorch implementation of [Synthesizing Audio with Generative Adversarial Networks(Chris Donahue, Feb 2018)](https://arxiv.org/abs/1802.04208).\n\nBefor running, make sure you have the `sc09` dataset, and put that dataset under your current filepath.\n\n## Quick Start:\n1. Installation\n```\nsudo apt-get install libav-tools\n```\n\n2. Download dataset\n* `sc09`: [sc09 raw WAV files](http://deepyeti.ucsd.edu/cdonahue/sc09.tar.gz), utterances of spoken english words '0'-'9'\n* `piano`: [Piano raw WAV files](http://deepyeti.ucsd.edu/cdonahue/mancini_piano.tar.gz)\n\n3. Run\n\nFor `sc09` task, **make sure `sc09` dataset under your current project filepath befor run your code.**\n```\n$ python train.py\n```\n\n#### Training time\n* For `SC09` dataset, 4 X Tesla P40 takes nearly 2 days to get reasonable result.\n* For `piano` piano dataset, 2 X Tesla P40 takes 3-6 hours to get reasonable result.\n* Increase the `BATCH_SIZE` from 10 to 32 or 64 can acquire shorter per-epoch time on multiple-GPU but slower gradient descent learning rate.\n\n## Results\nGenerated \"0-9\": https://soundcloud.com/mazzzystar/sets/dcgan-sc09\n\nGenerated piano: https://soundcloud.com/mazzzystar/sets/wavegan-piano\n\nLoss curve:\n\n![](imgs/loss_curve.png)\n\n## Architecture\n![](imgs/archi.png)\n\n## TODO\n* [ ] Add some evaluation experiments, eg. inception score.\n\n## Contributions\nThis repo is based on [chrisdonahue's](https://github.com/chrisdonahue/wavegan) and [jtcramer's](https://github.com/jtcramer/wavegan) implementation.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmazzzystar%2FWaveGAN-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmazzzystar%2FWaveGAN-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmazzzystar%2FWaveGAN-pytorch/lists"}