Directory
Published directory entries matching your search.
MeTA is a modern C++ data sciences toolkit. It provides text tokenization including deep semantic features like parse trees, inverted and forward indexes with compression and caching strategies, ranking functions for searching indexes, topic models, classification algorithms, graph algorithms, language models, a CRF implementation for POS-tagging and shallow parsing, and wrappers for liblinear and libsvm.
A guide to film locations worldwide, listed by film title. Entries give particulars of a film's locations, where they appear, photographs and basic visitor travel information. The site can also be searched by place, actor or director, and includes extra features such as lists of notable London filming sites.
Alternative Telegram client with extra interface features and messaging customization options.
nlp.js is a JavaScript library for building chatbots and bots, developed by AXA Group. It includes features such as entity extraction, sentiment analysis, and automatic language identification. The library is open-source and hosted on GitHub.
Paper Digest - ChatGPT is a curated resource page from Paper Digest that collects recent ChatGPT-related academic papers. The Paper Digest team extracts relevant papers, generates associated features for each entry, and sorts the results by relevance and date. The static page is updated bi-weekly, and a more frequently updated online version is also available. The page includes a brief overview of ChatGPT as OpenAI's November 2022 launched generative chatbot built on the GPT-3 family of large language models, fine-tuned with supervised and reinforcement learning techniques.
Paper2Audio is a free text-to-speech service designed for reading digital documents aloud. It supports PDFs, EPUBs, web articles, and other common document formats, uses natural AI voices for accurate reading, and includes no ads or paywalled voice features. The tool correctly processes figures, tables, and mathematical content, and skips extraneous page elements like inline references and endnotes to focus on relevant content.
Short Trip is a hand-drawn interactive work by Alexander Perrin focused on a tram driver, with elements including mountains and cloaked cats. A free web version is available, and a standalone purchasable release launches on Steam on December 11, 2024, adding a new scheduled mode and extra bonus features. The work supports optional audio toggles.
Slope Plus is a modded version of the game Slope with extra features and a smoother framerate, available to download or play in browser. It includes seeded runs and custom games with custom maps and a custom starting speed.
SmoredBoard is a free soundboard and realtime voice changer for Windows. It offers unlimited sound slots, drag-and-drop loading of audio files and a built-in sound editor for trims and cuts. Sounds and voices are stored locally and work offline without an account. A Pro tier is mentioned as offering extra features.
textacy is a Python library for natural language processing tasks built on the spaCy library. It focuses on tasks before and after spaCy processing, with tokenization, part-of-speech tagging and dependency parsing delegated to that library. Features include cleaning and normalizing raw text, extracting n-grams, entities, acronyms and keyterms, similarity metrics, and training topic models.
TextBlob is a Python library for processing textual data. It offers a simple API for natural language processing tasks including part-of-speech tagging, noun phrase extraction, sentiment analysis, classification, and tokenization. The documentation lists features such as word and phrase frequencies, parsing n-grams, lemmatization, spelling correction, and WordNet integration. It builds on NLTK and pattern, and new models or languages can be added through extensions.
An unofficial Telegram client based on Telegram Desktop that adds extra features. It provides 64-bit builds for Windows, Linux and macOS. Source code is available, and a discussion group exists. It was formerly named Telegram Desktop x64.
The Data Engineering Show is a podcast for data engineering and BI practitioners. It features discussions with tech influencers about practical day-to-day data challenges and solutions. Episodes are available on platforms including Apple Podcasts, Spotify and Pocket Casts.
Python library for automatic extraction of relevant features from time series.
Upgini is an open-source data search and enrichment library for Machine Learning and AI pipelines. It enables users to find and add relevant features from hundreds of public and premium external data sources, including open and commercial large language models.
Video Express Converter is a browser-based video conversion service. Users upload a source video, choose a section to extract, apply additional features, select an output format, and download the result. Described uses include converting between formats, resizing video, extracting audio, removing or replacing audio, and adding subtitles. The service states it is not intended to replace professional video editing software.
Vulgarlang is a constructed language (conlang) generator for fantasy writers and role players. It models the rules, irregularities and quirks of real languages, from grammar to sounds to vocabulary. A demo version offers a 200 word output, and a signup provides a 4000 word vocabulary and extra features.
XAudioPro is an online audio station for real-time editing and transcoding, using WebAudio and WebAssembly for front-end processing. It also offers spectrum-subtraction denoising, RNN neural network noise removal, and voice removal to extract background music. The site states the tool is not long online and its functions are limited, with more features in development.
