{"id":13486487,"url":"https://github.com/fatchord/WaveRNN","last_synced_at":"2025-03-27T20:33:30.632Z","repository":{"id":37601856,"uuid":"125524069","full_name":"fatchord/WaveRNN","owner":"fatchord","description":"WaveRNN Vocoder + TTS","archived":false,"fork":false,"pushed_at":"2022-07-02T14:21:35.000Z","size":247941,"stargazers_count":2155,"open_issues_count":107,"forks_count":698,"subscribers_count":87,"default_branch":"master","last_synced_at":"2025-03-24T06:22:36.505Z","etag":null,"topics":["neural-vocoder","pytorch","speech-synthesis","tacotron","text-to-speech","tts","wavernn"],"latest_commit_sha":null,"homepage":"https://fatchord.github.io/model_outputs/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/fatchord.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2018-03-16T14:03:52.000Z","updated_at":"2025-03-22T11:18:52.000Z","dependencies_parsed_at":"2022-07-19T01:33:09.710Z","dependency_job_id":null,"html_url":"https://github.com/fatchord/WaveRNN","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/fatchord%2FWaveRNN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fatchord%2FWaveRNN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fatchord%2FWaveRNN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fatchord%2FWaveRNN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fatchord","download_url":"https://codeload.github.com/fatchord/WaveRNN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245920849,"owners_count":20694176,"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":["neural-vocoder","pytorch","speech-synthesis","tacotron","text-to-speech","tts","wavernn"],"created_at":"2024-07-31T18:00:47.037Z","updated_at":"2025-03-27T20:33:30.626Z","avatar_url":"https://github.com/fatchord.png","language":"Python","funding_links":[],"categories":["Uncategorized","Python","语音合成"],"sub_categories":["Uncategorized","网络服务_其他"],"readme":"# WaveRNN\n\n##### (Update: Vanilla Tacotron One TTS system just implemented - more coming soon!)\n\n![Tacotron with WaveRNN diagrams](assets/tacotron_wavernn.png)\n\nPytorch implementation of Deepmind's WaveRNN model from [Efficient Neural Audio Synthesis](https://arxiv.org/abs/1802.08435v1)\n\n# Installation\n\nEnsure you have:\n\n* Python \u003e= 3.6\n* [Pytorch 1 with CUDA](https://pytorch.org/)\n\nThen install the rest with pip:\n\n\u003e pip install -r requirements.txt\n\n# How to Use\n\n### Quick Start\n\nIf you want to use TTS functionality immediately you can simply use:\n\n\u003e python quick_start.py\n\nThis will generate everything in the default sentences.txt file and output to a new 'quick_start' folder where you can playback the wav files and take a look at the attention plots\n\nYou can also use that script to generate custom tts sentences and/or use '-u' to generate unbatched (better audio quality):\n\n\u003e python quick_start.py -u --input_text \"What will happen if I run this command?\"\n\n\n### Training your own Models\n![Attenion and Mel Training GIF](assets/training_viz.gif)\n\nDownload the [LJSpeech](https://keithito.com/LJ-Speech-Dataset/) Dataset.\n\nEdit **hparams.py**, point **wav_path** to your dataset and run:\n\n\u003e python preprocess.py\n\nor use preprocess.py --path to point directly to the dataset\n___\n\nHere's my recommendation on what order to run things:\n\n1 - Train Tacotron with:\n\n\u003e python train_tacotron.py\n\n2 - You can leave that finish training or at any point you can use:\n\n\u003e python train_tacotron.py --force_gta\n\nthis will force tactron to create a GTA dataset even if it hasn't finish training.\n\n3 - Train WaveRNN with:\n\n\u003e python train_wavernn.py --gta\n\nNB: You can always just run train_wavernn.py without --gta if you're not interested in TTS.\n\n4 - Generate Sentences with both models using:\n\n\u003e python gen_tacotron.py wavernn\n\nthis will generate default sentences. If you want generate custom sentences you can use\n\n\u003e python gen_tacotron.py --input_text \"this is whatever you want it to be\" wavernn\n\nAnd finally, you can always use --help on any of those scripts to see what options are available :)\n\n\n\n# Samples\n\n[Can be found here.](https://fatchord.github.io/model_outputs/)\n\n# Pretrained Models\n\nCurrently there are two pretrained models available in the /pretrained/ folder':\n\nBoth are trained on LJSpeech\n\n* WaveRNN (Mixture of Logistics output) trained to 800k steps\n* Tacotron trained to 180k steps\n\n____\n\n### References\n\n* [Efficient Neural Audio Synthesis](https://arxiv.org/abs/1802.08435v1)\n* [Tacotron: Towards End-to-End Speech Synthesis](https://arxiv.org/abs/1703.10135)\n* [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://arxiv.org/abs/1712.05884)\n\n### Acknowlegements\n\n* [https://github.com/keithito/tacotron](https://github.com/keithito/tacotron)\n* [https://github.com/r9y9/wavenet_vocoder](https://github.com/r9y9/wavenet_vocoder)\n* Special thanks to github users [G-Wang](https://github.com/G-Wang), [geneing](https://github.com/geneing) \u0026 [erogol](https://github.com/erogol)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffatchord%2FWaveRNN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffatchord%2FWaveRNN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffatchord%2FWaveRNN/lists"}