{"id":13958556,"url":"https://github.com/thuhcsi/VAENAR-TTS","last_synced_at":"2025-07-21T00:31:12.929Z","repository":{"id":42200500,"uuid":"377317369","full_name":"thuhcsi/VAENAR-TTS","owner":"thuhcsi","description":"The official implementation of VAENAR-TTS, a VAE based non-autoregressive TTS model.","archived":false,"fork":false,"pushed_at":"2021-07-08T01:43:31.000Z","size":48,"stargazers_count":144,"open_issues_count":6,"forks_count":20,"subscribers_count":8,"default_branch":"main","last_synced_at":"2024-11-28T02:34:49.867Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/thuhcsi.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":"2021-06-15T23:27:24.000Z","updated_at":"2024-10-22T13:58:59.000Z","dependencies_parsed_at":"2022-09-21T18:00:17.418Z","dependency_job_id":null,"html_url":"https://github.com/thuhcsi/VAENAR-TTS","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/thuhcsi/VAENAR-TTS","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thuhcsi%2FVAENAR-TTS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thuhcsi%2FVAENAR-TTS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thuhcsi%2FVAENAR-TTS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thuhcsi%2FVAENAR-TTS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/thuhcsi","download_url":"https://codeload.github.com/thuhcsi/VAENAR-TTS/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thuhcsi%2FVAENAR-TTS/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266221259,"owners_count":23894965,"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":[],"created_at":"2024-08-08T13:01:43.743Z","updated_at":"2025-07-21T00:31:12.551Z","avatar_url":"https://github.com/thuhcsi.png","language":"Python","funding_links":[],"categories":["语音合成"],"sub_categories":["网络服务_其他"],"readme":"# VAENAR-TTS\nThis repo contains code accompanying the paper \"VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis\".\n\n##  [Samples](https://light1726.github.io/vaenar-tts/) | [Paper](https://arxiv.org/abs/2107.03298) | [Pretrained Models](https://drive.google.com/drive/folders/1Xe9v_XfMUgqC0ztIW0evsUq9SNx3GLlS?usp=sharing)\n\n## Usage\n\n### 0. Dataset\n1. English: [LJSpeech](https://keithito.com/LJ-Speech-Dataset/)\n2. Mandarin: [DataBaker(标贝)](https://www.data-baker.com/data/index/source/)\n\n### 1. Environment setup\n```bash\nconda env create -f environment.yml\nconda activate vaenartts-env\n```\n\n### 2. Data pre-processing\n\nFor English using LJSpeech:\n```bash\nCUDA_VISIBLE_DEVICES= python preprocess.py --dataset ljspeech --data_dir /path/to/extracted/LJSpeech-1.1 --save_dir ./ljspeech\n```\nFor Mandarin using Databaker(标贝):\n```bash\nCUDA_VISIBLE_DEVICES= python preprocess.py --dataset databaker --data_dir /path/to/extracted/biaobei --save_dir ./databaker\n```\n\n### 3. Training\nFor English using LJSpeech:\n```bash\nCUDA_VISIBLE_DEVICES=0 TF_FORCE_GPU_ALLOW_GROWTH=true python train.py --dataset ljspeech --log_dir ./lj-log_dir --test_dir ./lj-test_dir --data_dir ./ljspeech/tfrecords/ --model_dir ./lj-model_dir\n```\nFor Mandarin using Databaker(标贝):\n```bash\nCUDA_VISIBLE_DEVICES=0 TF_FORCE_GPU_ALLOW_GROWTH=true python train.py --dataset databaker --log_dir ./db-log_dir --test_dir ./db-test_dir --data_dir ./databaker/tfrecords/ --model_dir ./db-model_dir\n```\n\n### 4. Inference (synthesize speech for the whole test set)\nFor English using LJSpeech:\n```bash\nCUDA_VISIBLE_DEVICES=0 TF_FORCE_GPU_ALLOW_GROWTH=true python inference.py --dataset ljspeech --test_dir ./lj-test-2000 --data_dir ./ljspeech/tfrecords/ --batch_size 16 --write_wavs true --draw_alignments true --ckpt_path ./lj-model_dir/ckpt-2000\n```\nFor Mandarin using Databaker(标贝):\n```bash\nCUDA_VISIBLE_DEVICES=0 TF_FORCE_GPU_ALLOW_GROWTH=true python inference.py --dataset databaker --test_dir ./db-test-2000 --data_dir ./databaker/tfrecords/ --batch_size 16 --write_wavs true --draw_alignments true --ckpt_path ./db-model_dir/ckpt-2000\n```\n\n## Reference\n1. [XuezheMax/flowseq](https://github.com/XuezheMax/flowseq)\n2. [keithito/tacotron](https://github.com/keithito/tacotron)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthuhcsi%2FVAENAR-TTS","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthuhcsi%2FVAENAR-TTS","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthuhcsi%2FVAENAR-TTS/lists"}