{"id":18973891,"url":"https://github.com/josefalbers/e2tts-mlx","last_synced_at":"2026-03-06T07:02:14.864Z","repository":{"id":257811934,"uuid":"868317772","full_name":"JosefAlbers/e2tts-mlx","owner":"JosefAlbers","description":"Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS (E2 TTS) in MLX","archived":false,"fork":false,"pushed_at":"2024-10-15T12:21:33.000Z","size":3006,"stargazers_count":27,"open_issues_count":0,"forks_count":5,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-09-27T20:11:35.199Z","etag":null,"topics":["e2-tts","flow-matching","mlx","multistream","text-to-speech","transformer","tts"],"latest_commit_sha":null,"homepage":"","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/JosefAlbers.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,"zenodo":null}},"created_at":"2024-10-06T04:06:15.000Z","updated_at":"2025-03-14T06:59:12.000Z","dependencies_parsed_at":null,"dependency_job_id":"3f5f3549-fc6a-49aa-afee-091b137fac4a","html_url":"https://github.com/JosefAlbers/e2tts-mlx","commit_stats":null,"previous_names":["josefalbers/e2tts-mlx"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/JosefAlbers/e2tts-mlx","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JosefAlbers%2Fe2tts-mlx","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JosefAlbers%2Fe2tts-mlx/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JosefAlbers%2Fe2tts-mlx/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JosefAlbers%2Fe2tts-mlx/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JosefAlbers","download_url":"https://codeload.github.com/JosefAlbers/e2tts-mlx/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JosefAlbers%2Fe2tts-mlx/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30164895,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-06T04:43:31.446Z","status":"ssl_error","status_checked_at":"2026-03-06T04:40:30.133Z","response_time":250,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["e2-tts","flow-matching","mlx","multistream","text-to-speech","transformer","tts"],"created_at":"2024-11-08T15:13:30.376Z","updated_at":"2026-03-06T07:02:14.840Z","avatar_url":"https://github.com/JosefAlbers.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# e2tts-mlx: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS in MLX\n\nA lightweight implementation of [Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS](https://arxiv.org/abs/2406.18009) model using MLX, with minimal dependencies and efficient computation on Apple Silicon.\n\n## Quick Start\n\n### Install\n\n```zsh\n# Quick install (note: PyPI version may not always be up to date)\npip install e2tts-mlx\n\n# For the latest version, you can install directly from the repository:\n# git clone https://github.com/JosefAlbers/e2tts-mlx.git\n# cd e2tts-mlx\n# pip install -e .\n```\n\n### Usage\n\nTo use a pre-trained model for text-to-speech:\n\n```zsh\ne2tts 'We must achieve our own salvation.'\n```\n\nThis will write `tts_0.wav` to the current directory, which you can then play.\n\nhttps://github.com/user-attachments/assets/89265113-0785-42f1-b867-c38c886acbef\n\nTo train a new model with default settings:\n\n```zsh\ne2tts\n```\n\n![e2tts](https://raw.githubusercontent.com/JosefAlbers/e2tts-mlx/main/assets/e2tts.png)\n\nTo train with custom options:\n\n```zsh\ne2tts --batch_size=16 --n_epoch=100 --lr=1e-4 --depth=8 --n_ode=32\n```\n\nSelect training options:\n\n- `--batch_size`: Set the batch size (default: 32)\n- `--n_epoch`: Set the number of epochs (default: 10)\n- `--lr`: Set the learning rate (default: 2e-4)\n- `--depth`: Set the model depth (default: 8)\n- `--n_ode`: Set the number of steps for sampling (default: 1)\n- `--more_ds` parameter: Implements [two-set training](https://arxiv.org/pdf/2410.07041) (default: 'JosefAlbers/lj-speech')\n\n## Acknowledgements\n\nSpecial thanks to [lucidrains](https://github.com/lucidrains/e2-tts-pytorch)' fantastic code that inspired this project, and to [lucasnewman](https://github.com/lucasnewman/vocos-mlx)'s the Vocos implementation that made this possible.\n\n## License\n\nApache License 2.0\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjosefalbers%2Fe2tts-mlx","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjosefalbers%2Fe2tts-mlx","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjosefalbers%2Fe2tts-mlx/lists"}