{"id":13934895,"url":"https://github.com/r9y9/tacotron_pytorch","last_synced_at":"2025-04-09T18:19:14.366Z","repository":{"id":54476584,"uuid":"103650686","full_name":"r9y9/tacotron_pytorch","owner":"r9y9","description":"PyTorch implementation of Tacotron speech synthesis model.","archived":false,"fork":false,"pushed_at":"2019-07-12T04:37:27.000Z","size":21701,"stargazers_count":309,"open_issues_count":2,"forks_count":78,"subscribers_count":15,"default_branch":"master","last_synced_at":"2025-04-09T18:19:07.973Z","etag":null,"topics":["python","pytorch","speech","speech-synthesis","tacotron"],"latest_commit_sha":null,"homepage":"http://nbviewer.jupyter.org/github/r9y9/tacotron_pytorch/blob/master/notebooks/Test%20Tacotron.ipynb","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/r9y9.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2017-09-15T11:42:38.000Z","updated_at":"2025-03-15T16:18:03.000Z","dependencies_parsed_at":"2022-08-13T17:00:50.493Z","dependency_job_id":null,"html_url":"https://github.com/r9y9/tacotron_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/r9y9%2Ftacotron_pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r9y9%2Ftacotron_pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r9y9%2Ftacotron_pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r9y9%2Ftacotron_pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/r9y9","download_url":"https://codeload.github.com/r9y9/tacotron_pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248085325,"owners_count":21045139,"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":["python","pytorch","speech","speech-synthesis","tacotron"],"created_at":"2024-08-07T23:01:17.981Z","updated_at":"2025-04-09T18:19:14.346Z","avatar_url":"https://github.com/r9y9.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook","Paper implementations｜论文实现","Paper implementations"],"sub_categories":["Other libraries｜其他库:","Other libraries:"],"readme":"# tacotron_pytorch\n\n[![Build Status](https://travis-ci.org/r9y9/tacotron_pytorch.svg?branch=master)](https://travis-ci.org/r9y9/tacotron_pytorch)\n\nPyTorch implementation of [Tacotron](https://arxiv.org/abs/1703.10135) speech synthesis model.\n\nInspired from [keithito/tacotron](https://github.com/keithito/tacotron). Currently not as much good speech quality as [keithito/tacotron](https://github.com/keithito/tacotron) can generate, but it seems to be basically working. You can find some generated speech examples trained on [LJ Speech Dataset](https://keithito.com/LJ-Speech-Dataset/) at [here](http://nbviewer.jupyter.org/github/r9y9/tacotron_pytorch/blob/master/notebooks/Test%20Tacotron.ipynb).\n\nIf you are comfortable working with TensorFlow, I'd recommend you to try\nhttps://github.com/keithito/tacotron instead. The reason to rewrite it in PyTorch is that it's easier to debug and extend (multi-speaker architecture, etc) at least to me.\n\n## Requirements\n\n- PyTorch\n- TensorFlow (if you want to run the training script. This definitely can be optional, but for now required.)\n\n## Installation\n\n```\ngit clone --recursive https://github.com/r9y9/tacotron_pytorch\npip install -e . # or python setup.py develop\n```\n\nIf you want to run the training script, then you need to install additional dependencies.\n\n```\npip install -e \".[train]\"\n```\n\n## Training\n\nThe package relis on [keithito/tacotron](https://github.com/keithito/tacotron) for text processing, audio preprocessing and audio reconstruction (added as a submodule). Please follows the quick start section at https://github.com/keithito/tacotron and prepare your dataset accordingly.\n\nIf you have your data prepared, assuming your data is in `\"~/tacotron/training\"` (which is the default), then you can train your model by:\n\n```\npython train.py\n```\n\nAlignment, predicted spectrogram, target spectrogram, predicted waveform and checkpoint (model and optimizer states) are saved per 1000 global step in `checkpoints` directory. Training progress can be monitored by:\n\n```\ntensorboard --logdir=log\n```\n\n## Testing model\n\nOpen the notebook in `notebooks` directory and change `checkpoint_path` to your model.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fr9y9%2Ftacotron_pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fr9y9%2Ftacotron_pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fr9y9%2Ftacotron_pytorch/lists"}