{"id":20526551,"url":"https://github.com/tugstugi/pytorch-dc-tts","last_synced_at":"2025-04-07T12:06:27.687Z","repository":{"id":48616709,"uuid":"144312657","full_name":"tugstugi/pytorch-dc-tts","owner":"tugstugi","description":"Text to Speech with PyTorch (English and Mongolian)","archived":false,"fork":false,"pushed_at":"2024-09-24T09:37:49.000Z","size":5984,"stargazers_count":185,"open_issues_count":6,"forks_count":81,"subscribers_count":10,"default_branch":"master","last_synced_at":"2025-03-28T03:08:48.924Z","etag":null,"topics":["convolutional-neural-networks","deep-learning","mongolian","python","pytorch","speech-synthesis","text-to-speech","tts"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/tugstugi.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-08-10T17:05:24.000Z","updated_at":"2024-12-16T02:45:47.000Z","dependencies_parsed_at":"2025-01-15T03:53:57.966Z","dependency_job_id":"18f9c9c5-b872-4430-b1b6-0136fb19a6d8","html_url":"https://github.com/tugstugi/pytorch-dc-tts","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/tugstugi%2Fpytorch-dc-tts","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tugstugi%2Fpytorch-dc-tts/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tugstugi%2Fpytorch-dc-tts/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tugstugi%2Fpytorch-dc-tts/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tugstugi","download_url":"https://codeload.github.com/tugstugi/pytorch-dc-tts/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247648977,"owners_count":20972945,"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":["convolutional-neural-networks","deep-learning","mongolian","python","pytorch","speech-synthesis","text-to-speech","tts"],"created_at":"2024-11-15T23:14:43.028Z","updated_at":"2025-04-07T12:06:27.629Z","avatar_url":"https://github.com/tugstugi.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"PyTorch implementation of\n[Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention](https://arxiv.org/abs/1710.08969)\nbased partially on the following projects:\n* https://github.com/Kyubyong/dc_tts (audio pre processing)\n* https://github.com/r9y9/deepvoice3_pytorch (data loader sampler)\n\n## Online Text-To-Speech Demo\nThe following notebooks are executable on [https://colab.research.google.com ](https://colab.research.google.com):\n* [Mongolian Male Voice TTS Demo](https://colab.research.google.com/github/tugstugi/pytorch-dc-tts/blob/master/notebooks/MongolianTTS.ipynb)\n* [English Female Voice TTS Demo (LJ-Speech)](https://colab.research.google.com/github/tugstugi/pytorch-dc-tts/blob/master/notebooks/EnglishTTS.ipynb)\n\nFor audio samples and pretrained models, visit the above notebook links.\n\n## Training/Synthesizing English Text-To-Speech\nThe English TTS uses the [LJ-Speech](https://keithito.com/LJ-Speech-Dataset/) dataset.\n1. Download the dataset: `python dl_and_preprop_dataset.py --dataset=ljspeech`\n2. Train the Text2Mel model: `python train-text2mel.py --dataset=ljspeech`\n3. Train the SSRN model: `python train-ssrn.py --dataset=ljspeech`\n4. Synthesize sentences: `python synthesize.py --dataset=ljspeech`\n   * The WAV files are saved in the `samples` folder.\n\n## Training/Synthesizing Mongolian Text-To-Speech\nThe Mongolian text-to-speech uses 5 hours audio from the [Mongolian Bible](https://www.bible.com/mn/versions/1590-2013-ariun-bibli-2013).\n1. Download the dataset: `python dl_and_preprop_dataset.py --dataset=mbspeech`\n2. Train the Text2Mel model: `python train-text2mel.py --dataset=mbspeech`\n3. Train the SSRN model: `python train-ssrn.py --dataset=mbspeech`\n4. Synthesize sentences: `python synthesize.py --dataset=mbspeech`\n   * The WAV files are saved in the `samples` folder.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftugstugi%2Fpytorch-dc-tts","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftugstugi%2Fpytorch-dc-tts","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftugstugi%2Fpytorch-dc-tts/lists"}