{ "info": { "author": "Colin Prepscius", "author_email": "colinprepscius@gmail.com", "bugtrack_url": null, "classifiers": [ "License :: OSI Approved :: MIT License", "Operating System :: OS Independent", "Programming Language :: Python :: 3" ], "description": "# TIMIT\n\nThe TIMIT database, in brief, contains audio recordings of sentences spoken\nby a set of people. It also includes word and phoneme transcriptions, along with\ntheir exact positions, as ranges, within the audio files.\n\nAs such, it is an interesting target for ML: we are given high-grade audio recordings as well as real-time phoneme and word transcriptions (or guesses at them, anyway).\n\nThe actual TIMIT database is NOT included, and is not free. Get it here:\nhttps://catalog.ldc.upenn.edu/LDC93S1. This library merely adds\nconvenience, parsing, sampling, drawing, etc.\n\n![alt text](https://github.com/colinator/timit_utils/blob/master/advert.png \"Example output\")\n\n\n\n# timit_utils\n\nThe code herein can lazily load, parse, and expose the TIMIT database\nof spoken audio, word and phoneme transcriptions. The layout of the TIMIT file system looks like this:\n\n![alt text](https://github.com/colinator/timit_utils/blob/master/timitfiles.png \"Your file system should look like this\")\n\nThis library models the data with several classes:\n\n* Corpus (such as '../TIMIT', contains two SubCorpuses: train and test)\n* SubCorpus (such as 'train'|'test', contains several Regions)\n* Region (such as 'DR1', contains several Persons)\n* Person (such as 'Name:CJF0,Female')\n* Sentence (such as 'SA1', contains audio, word, and phoneme transcriptions as numpy arrays)\n\nAll the above give many ways to index, iterate, parse, search, and expose the data as pandas Dataframes.\n\n* various audio sampling, padding routines, mel filterbank frequency extractions, and a quick display system\n\n\n# Installation\n\n`pip install timit_utils`\n\ntimit_utils requires numpy, pandas, matplotlib, scipy, python_speech_features, and SoundFile.\n\n\n\n# Example usage (i.e. in jupyter)\n\n```code\n%matplotlib inline\nimport timit_utils as tu\nimport timit_utils.audio_utils as au\nimport timit_utils.drawing_utils as du\n\ncorpus = tu.Corpus('../TIMIT')\nsentence = corpus.train.sentences_by_phone_df('aa').sentence[0]\ndu.DrawVerticalPanels([du.AudioPanel(sentence.raw_audio, show_x_axis=True),\n du.WordsPanel(sentence.words_df, sentence.raw_audio.shape[0], show_x_axis=True),\n du.PhonesPanel(sentence.phones_df, sentence.raw_audio.shape[0])\n ])\n```\n\nFull usage here:\nhttps://github.com/colinator/timit_utils/blob/master/timit_utils_demonst.ipynb\n\n\n", "description_content_type": "text/markdown", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/colinator/timit_utils", "keywords": "", "license": "", "maintainer": "", "maintainer_email": "", "name": "timit-utils", "package_url": "https://pypi.org/project/timit-utils/", "platform": "", "project_url": "https://pypi.org/project/timit-utils/", "project_urls": { "Homepage": "https://github.com/colinator/timit_utils" }, "release_url": "https://pypi.org/project/timit-utils/0.9.0/", "requires_dist": [ "numpy", "pandas", "scipy", "matplotlib", "python-speech-features", "SoundFile (>=0.8.0)" ], "requires_python": "", "summary": "A convenience python wrapper for the TIMIT database.", "version": "0.9.0" }, "last_serial": 4530113, "releases": { "0.9.0": [ { "comment_text": "", "digests": { "md5": "814fabd4f6e3db7ab399ceb0e65a51cc", "sha256": "dc3e95efa50a6920e644cbbc730298c131e3d76d32c60530b47d8ca59dd4ef36" }, "downloads": -1, "filename": "timit_utils-0.9.0-py3-none-any.whl", "has_sig": false, "md5_digest": "814fabd4f6e3db7ab399ceb0e65a51cc", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 11925, "upload_time": "2018-11-26T15:50:24", "url": "https://files.pythonhosted.org/packages/22/32/0c98f7f44386947b9e4080f54f09a7380c390e0b8337ab0b87050d49c43a/timit_utils-0.9.0-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "9e5c043e3b23d6f369ad17925f472c29", "sha256": "081a37ee60ffe6a057b34825e0f062b557e195eea4b54af8cba300e445bd7768" }, "downloads": -1, "filename": "timit_utils-0.9.0.tar.gz", "has_sig": false, "md5_digest": "9e5c043e3b23d6f369ad17925f472c29", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 10563, "upload_time": "2018-11-26T15:50:26", "url": "https://files.pythonhosted.org/packages/77/4a/b0d0e204aa6771f6e0e2370484902d9751c81d58451ea97480eee9628c94/timit_utils-0.9.0.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "814fabd4f6e3db7ab399ceb0e65a51cc", "sha256": "dc3e95efa50a6920e644cbbc730298c131e3d76d32c60530b47d8ca59dd4ef36" }, "downloads": -1, "filename": "timit_utils-0.9.0-py3-none-any.whl", "has_sig": false, "md5_digest": "814fabd4f6e3db7ab399ceb0e65a51cc", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 11925, "upload_time": "2018-11-26T15:50:24", "url": "https://files.pythonhosted.org/packages/22/32/0c98f7f44386947b9e4080f54f09a7380c390e0b8337ab0b87050d49c43a/timit_utils-0.9.0-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "9e5c043e3b23d6f369ad17925f472c29", "sha256": "081a37ee60ffe6a057b34825e0f062b557e195eea4b54af8cba300e445bd7768" }, "downloads": -1, "filename": "timit_utils-0.9.0.tar.gz", "has_sig": false, "md5_digest": "9e5c043e3b23d6f369ad17925f472c29", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 10563, "upload_time": "2018-11-26T15:50:26", "url": "https://files.pythonhosted.org/packages/77/4a/b0d0e204aa6771f6e0e2370484902d9751c81d58451ea97480eee9628c94/timit_utils-0.9.0.tar.gz" } ] }