{"id":13861568,"url":"https://github.com/mozilla/DSAlign","last_synced_at":"2025-07-14T09:32:26.919Z","repository":{"id":47603700,"uuid":"192935229","full_name":"mozilla/DSAlign","owner":"mozilla","description":"DeepSpeech based forced alignment tool","archived":false,"fork":false,"pushed_at":"2020-12-12T08:45:52.000Z","size":234,"stargazers_count":234,"open_issues_count":8,"forks_count":33,"subscribers_count":22,"default_branch":"master","last_synced_at":"2024-11-18T21:42:00.463Z","etag":null,"topics":["deepspeech","forced-alignment"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mpl-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mozilla.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-06-20T14:31:02.000Z","updated_at":"2024-11-14T09:09:49.000Z","dependencies_parsed_at":"2022-09-10T09:20:16.766Z","dependency_job_id":null,"html_url":"https://github.com/mozilla/DSAlign","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/mozilla%2FDSAlign","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mozilla%2FDSAlign/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mozilla%2FDSAlign/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mozilla%2FDSAlign/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mozilla","download_url":"https://codeload.github.com/mozilla/DSAlign/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225741010,"owners_count":17516896,"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":["deepspeech","forced-alignment"],"created_at":"2024-08-05T06:01:25.278Z","updated_at":"2024-11-22T21:30:49.515Z","avatar_url":"https://github.com/mozilla.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# DSAlign\nDeepSpeech based forced alignment tool\n\n## Installation\n\nIt is recommended to use this tool from within a virtual environment.\nAfter cloning and changing to the root of the project,\nthere is a script for creating one with all requirements in the git-ignored dir `venv`:\n\n```shell script\n$ bin/createenv.sh\n$ ls venv\nbin  include  lib  lib64  pyvenv.cfg  share\n```\n\n`bin/align.sh` will automatically use it.\n\nInternally DSAlign uses the [DeepSpeech](https://github.com/mozilla/DeepSpeech/) STT engine.\nFor it to be able to function, it requires a couple of files that are specific to \nthe language of the speech data you want to align.\nIf you want to align English, there is already a helper script that will download and prepare\nall required data:\n\n```shell script\n$ bin/getmodel.sh \n[...]\n$ ls models/en/\nalphabet.txt  lm.binary  output_graph.pb  output_graph.pbmm  output_graph.tflite  trie\n```\n\n## Overview and documentation\n\nA typical application of the aligner is done in three phases: \n\n 1. __Preparing__ the data. Albeit most of this has to be done individually,\n    there are some [tools for data preparation, statistics and maintenance](doc/tools.md).\n    All involved file formats are described [here](doc/files.md).\n 2. __Aligning__ the data using [the alignment tool and it algorithm](doc/algo.md).\n 3. __Exporting__ aligned data using [the data-set exporter](doc/export.md).\n\n## Quickstart example\n\n### Example data\n\nThere is a script for downloading and preparing some public domain speech and transcript data.\nIt requires `ffmpeg` for some sample conversion.\n\n```shell script\n$ bin/gettestdata.sh\n$ ls data\ntest1  test2\n```\n\n### Alignment using example data\n\nNow the aligner can be called either \"manually\" (specifying all involved files directly):\n\n```shell script\n$ bin/align.sh --audio data/test1/audio.wav --script data/test1/transcript.txt --aligned data/test1/aligned.json --tlog data/test1/transcript.log\n```\n\nOr \"automatically\" by specifying a so-called catalog file that bundles all involved paths:\n\n```shell script\n$ bin/align.sh --catalog data/test1.catalog\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmozilla%2FDSAlign","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmozilla%2FDSAlign","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmozilla%2FDSAlign/lists"}