{"id":20756536,"url":"https://github.com/dragoncomputer/dragonfire-raspberrypi","last_synced_at":"2025-04-28T20:00:00.762Z","repository":{"id":68966040,"uuid":"56639856","full_name":"DragonComputer/Dragonfire-RaspberryPi","owner":"DragonComputer","description":"Dragonfire is an open source virtual assistant project for RaspberryPi OSMC/Kodi","archived":false,"fork":false,"pushed_at":"2017-05-18T11:53:26.000Z","size":8286,"stargazers_count":17,"open_issues_count":0,"forks_count":3,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-28T19:59:52.657Z","etag":null,"topics":["aiml","assistant","assistant-chat-bots","assistant-personnel","kodi","linux","minipc","mobile","osmc","raspberry-pi","raspberrypi","stereo-vision","stereoscopy","ubuntu"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DragonComputer.png","metadata":{"files":{"readme":"README","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2016-04-19T23:37:57.000Z","updated_at":"2023-05-29T21:07:55.000Z","dependencies_parsed_at":"2024-01-23T21:34:23.888Z","dependency_job_id":null,"html_url":"https://github.com/DragonComputer/Dragonfire-RaspberryPi","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/DragonComputer%2FDragonfire-RaspberryPi","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DragonComputer%2FDragonfire-RaspberryPi/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DragonComputer%2FDragonfire-RaspberryPi/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DragonComputer%2FDragonfire-RaspberryPi/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DragonComputer","download_url":"https://codeload.github.com/DragonComputer/Dragonfire-RaspberryPi/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251380914,"owners_count":21580338,"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":["aiml","assistant","assistant-chat-bots","assistant-personnel","kodi","linux","minipc","mobile","osmc","raspberry-pi","raspberrypi","stereo-vision","stereoscopy","ubuntu"],"created_at":"2024-11-17T09:33:00.620Z","updated_at":"2025-04-28T20:00:00.739Z","avatar_url":"https://github.com/DragonComputer.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"Example Grammar for Julius\n---------------------------------\n\nIn order to use VoxForge's acoustic models with Julius, you have to tell it\nwhat words you want it to recognize and it what context each of those can\nbe found. You can do this by writting two files, a .grammar and a .term one,\nand generating .dfa and .dict files out of those. This file will explain you\nbriefly how to achieve this.\n\n== QUICK START ==\n\nFirst, copy the example files to a directory where you can write, like your\nhome folder, and uncompress the gziped files:\n\n  mkdir ~/julius-grammar\n  cp /usr/share/doc/julius-voxforge/examples/* ~/julius-grammar\n  cd ~/julius-grammar\n  gunzip * 2\u003e\u00261 | grep -v ignored\n\nNow let's run the following command (available from package \"julius\"):\n\n  mkdfa sample\n\nThis will generate the files \"sample.dfa\", \"sample.dict\" and \"sample.term\" out\nof the \"sample.grammar\" and \"sample.voca\" files. Once we have those, we can run\nJulius with the following command to try the example grammar out:\n\n  julius -input mic -C julian.jconf\n\nNote that only some sentences are recognized, like for example \"DIAL ONE TWO\"\nor \"PHONE STEVE\". See the next part to learn how to add more words.\n\nIn case your recognition rate is near zero, try replacing \"mic\" in the\ncommand above with \"oss\", \"alsa\" or \"esd\".\n\n== CREATING OUR OWN GRAMMAR ==\n\nNow open up the files \"sample.voca\" and \"sample.grammar\" and have a look at\nthem. The first one defines some categories (lines starting with \"%\") and lists\nsome words, together with their phonetic representation. The .grammar file,\nwhich may look a bit more confusing, defines the context in which each word\ncategory can appear.\n\nFeel free to add new words to the existing categories in sample.voca or even\ncreate new ones (adding at least one rule mentioning them to sample.grammar),\nbut don't forget to write their phonetic representation next to them. You can\nget a list of English words and their corresponding phonetic representation\nfrom ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/dictionaries/beep.tar.gz.\n\nAbout the .grammar file, you need to understand that the lines starting with\n\"S :\" are those which define the possible sentences and that they are formed\nby one or more category or variables names, between \"NS_B \" and \" NS_E\" (which\nmost be defined in sample.voca and represent the silence at the end and at the\nstart of the sentence). Variables, like we called them previously, are just\nanother line in the .grammar file which list a sequence of categories or\nother variables, and, as you see in the sample file, they can have many\ndifferent definitions.\n\nOnce you finish playing with the files, you can generate their equivalents in\nJulian's native format again, by running the same command as in the quick start:\n\n  mkdfa sample\n\nThen, run julius as showed above and if everything is right it should recognize\nyour new vocabulary now. In the case you get an error about missing phonemes,\nyou'll have to remove the words about which it complains, as the available\nacoustic models don't support them.\n\n== PRACTICAL UTILITY ==\n\nAs you will probably notice, the VoxForge acoustic model is still far away from\nbeing suitable for dictation applications and the like, so its utility right\nnow is basically restricted to \"command and control\" applications. For an\nexample of how to write a simple one in Python, look at the file command.py\nin /usr/share/doc/julius-voxforge/examples/controlapp/.\n\n== CONTRIBUTE ==\n\nIf you want to help contributing speech corpora for your language, see the\nproject's main page at http://www.voxforge.org/.\n\n -- Siegfried-A. Gevatter \u003crainct@ubuntu.com\u003e. 19/06/2009\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdragoncomputer%2Fdragonfire-raspberrypi","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdragoncomputer%2Fdragonfire-raspberrypi","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdragoncomputer%2Fdragonfire-raspberrypi/lists"}