{"id":13715931,"url":"https://github.com/soobinseo/Tacotron-pytorch","last_synced_at":"2025-05-07T05:31:49.019Z","repository":{"id":63919743,"uuid":"111775026","full_name":"soobinseo/Tacotron-pytorch","owner":"soobinseo","description":"Pytorch implementation of Tacotron","archived":false,"fork":false,"pushed_at":"2018-11-01T14:58:32.000Z","size":1072,"stargazers_count":206,"open_issues_count":6,"forks_count":41,"subscribers_count":9,"default_branch":"master","last_synced_at":"2024-11-14T04:34:33.043Z","etag":null,"topics":["pytorch","tacotron","text-to-speech","tts"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/soobinseo.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2017-11-23T07:03:44.000Z","updated_at":"2024-11-05T08:30:09.000Z","dependencies_parsed_at":"2023-01-14T14:00:49.021Z","dependency_job_id":null,"html_url":"https://github.com/soobinseo/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/soobinseo%2FTacotron-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soobinseo%2FTacotron-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soobinseo%2FTacotron-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soobinseo%2FTacotron-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/soobinseo","download_url":"https://codeload.github.com/soobinseo/Tacotron-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252823017,"owners_count":21809700,"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":["pytorch","tacotron","text-to-speech","tts"],"created_at":"2024-08-03T00:01:05.162Z","updated_at":"2025-05-07T05:31:43.987Z","avatar_url":"https://github.com/soobinseo.png","language":"Python","funding_links":[],"categories":["Pytorch \u0026 related libraries｜Pytorch \u0026 相关库","Pytorch \u0026 related libraries"],"sub_categories":["NLP \u0026 Speech Processing｜自然语言处理 \u0026 语音处理:","NLP \u0026 Speech Processing:"],"readme":"# Tacotron-pytorch\n\nA pytorch implementation of [Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model](https://arxiv.org/abs/1703.10135).\n\n\u003cimg src=\"png/model.png\"\u003e\n\n## Requirements\n  * Install python 3\n  * Install pytorch == 0.2.0\n  * Install requirements:\n    ```\n   \tpip install -r requirements.txt\n   \t```\n\n## Data\nI used LJSpeech dataset which consists of pairs of text script and wav files. The complete dataset (13,100 pairs) can be downloaded [here](https://keithito.com/LJ-Speech-Dataset/). I referred https://github.com/keithito/tacotron for the preprocessing code.\n\n## File description\n  * `hyperparams.py` includes all hyper parameters that are needed.\n  * `data.py` loads training data and preprocess text to index and wav files to spectrogram. Preprocessing codes for text is in text/ directory.\n  * `module.py` contains all methods, including CBHG, highway, prenet, and so on.\n  * `network.py` contains networks including encoder, decoder and post-processing network.\n  * `train.py` is for training.\n  * `synthesis.py` is for generating TTS sample.\n\n## Training the network\n  * STEP 1. Download and extract LJSpeech data at any directory you want.\n  * STEP 2. Adjust hyperparameters in `hyperparams.py`, especially 'data_path' which is a directory that you extract files, and the others if necessary.\n  * STEP 3. Run `train.py`. \n\n## Generate TTS wav file\n  * STEP 1. Run `synthesis.py`. Make sure the restore step. \n\n## Samples\n  * You can check the generated samples in 'samples/' directory. Training step was only 60K, so the performance is not good yet.\n\n## Reference\n  * Keith ito: https://github.com/keithito/tacotron\n\n## Comments\n  * Any comments for the codes are always welcome.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsoobinseo%2FTacotron-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsoobinseo%2FTacotron-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsoobinseo%2FTacotron-pytorch/lists"}