# Main goals:
- To create a sign language search engine that enables users to easily find sign language content.(MVP - Minimal Viable Product)
- To create an interactive sign language tutoring system that effectively teaches users sign language.(Medium Viable Product)
- To create a machine translation system that accurately and efficiently translates between sign languages and spoken or written language, making communication more accessible for users.(Maximal Viable Product)
### Terms & Definitions
- Minimal Viable Product - The minimum set of features necessary to test the basic functionality of the sign language interface.
- Medium Viable Product - An expanded version of the MVP with additional features to improve usability and functionality.
- Maximal Viable Product - The final version of the product, with all the features and capabilities required for full functionality.


# The tasks can include

- Develop sign language generation and recognition system

- Develop a tool for collecting and labeling sign language data, and create a dataset using this tool

- Use the tool to mark up sign language data, such as videos or images, with linguistic and grammatical information, such as signs, movements, handshape, hand orientation, location, and facial expression

- Develop a sign language search engine that allows users to search for sign language content.

- Develop an interactive sign language tutoring system

- Continuously monitor and analyse the performance of the system to identify areas for improvement.

- Design a UI/UX interface that is easy to navigate and understand for sign language users.

### App task examples:

Data labeling
- Sign language data labeler uses the tool [youtube](https://youtu.be/NIa3q5zdT-U)
- Collection of sign language sentence at NGTU NETI [youtube](https://youtu.be/oLZsv8j_nJ4)

Sign language recognition
- Recognition of Russian fingerspelling [youtube](https://youtu.be/NxdVHfo_ZLo)
- Recognize hand configurations-orientations to present examples of words [youtube](https://youtu.be/VRlgWQFEUzA)
- Static one-handed gestures to present examples of words [youtube](https://youtu.be/qQwLTXNp9DY)
- In the context of the course 'Designing a Machine Learning System', a Telegram bot is demonstrated that is able to recognize the shape of the hand and then match it to the corresponding word in Russian Sign Language. [youtube](https://www.youtube.com/live/3pJSXQuBd-s?feature=share) (see 4:42:37-5:03:16)

UI/UX layout
- Random gesture selection [youtube](https://youtu.be/oOWatIspYwE)
- Search for gesture by word [youtube](https://youtu.be/V1XYH2L7Gfo)
- Sequential display of selected gesture parameters for gesture search [youtube](https://youtu.be/lryv_njvHtE)
- Search for gesture by photo with its performance [youtube](https://youtu.be/jcAkCfhPKls)
- AdaptisCon#2 in Novosibirsk - Presentation of the Russian sign language dictionary [youtube](https://www.youtube.com/live/oKyXMrA6ghs?feature=share) (see 1:48:10-2:22:14 of our speaker)

### Site, bot & mobile apps
- https://signlanguages.ru/
- https://t.me/slsru_bot (в разработке)
- iOS app "Signlanguage" [AppStore](https://apps.apple.com/ru/app/signlanguages/id1602656863)
-  Android app "Signlanguage" [PlayMarket](https://play.google.com/store/apps/details?id=com.nstu.rsl)


# Social media:
- [vk](https://vk.com/signlanguages)
- [telegram](https://t.me/slsru)
- [instagram](https://www.instagram.com/signlanguages.ru)

# About
Email: alexeyayaya@gmail.com - Alexey Prikhodko

- Alexey Prikhodko - Domain expert, full-stack developer  
- Julia Prikhodko - Sign language data labeler and informer
- Mark Belousov - Frontend-developer, system analyst
- Yana Kondratenko - ML developer

Sign Language Interface project aims to improve accessibility of technology for individuals who use sign languages by incorporating sign language recognition, generation, translation, and tutoring functionality into UI/UX design and AI systems.

Sign language interface

<p>Этот проект появился при прохождении курса Natural Language Processing course (stream 3, autumn 2022).</p><p>При изучении некоторых тем в начальных классах школ на предмете «Русский язык» случаются проблемы, что нет достаточного количества подготовленных материалов для учителей. Примером такой темы является «функциональные стили речи». Данная работа подразумевает под собой несколько логических этапов: сбор и разметка датасета, очистка и предобработка датасета, выбор на основе сравнительного анализа наилучшей модели решающей данную задачу. &nbsp;Для создания размеченного датасета использовались популярные источники информации: новостные сайты, литературные произведения, архив научных публикация и статей и т.д. В результате обучения моделей на собранном датасете получились итересные результаты. &nbsp;В данной работе было реализовано 2 модели, которые основаны на разных подходах: классическое машинной обучения и методы глубокого обучения.</p><p><a target="_blank" rel="noopener noreferrer" href="https://github.com/d3vyatk4ru/style-sentences-clf">Ссылка на репозиторий с проектом</a></p>

Andrew

Daniil

Predictions of functional styles of sentence speech in Russian language

The training models methodology for predicting the rate of cryptocurrency against the dollar two weeks ahead from the current date, so the models are rebuild on a daily basis. Model training uses the trends data from Yahoo Finance. List of cryptocurrencies: BTC, ETH, LTC, BNB, XMR, ATOM. But this list can be extended.
The training of model takes into account the news sentiment about cryptocurrency. Historical news are taken from the news sites and the actual news from the rss feeds.

The value of the cryptocurrency rate is predicted for the next 14 days. Data discretization - one day. Interval forecast, the range of acceptable values of the forecasted exchange rate is indicated.

<p>The public part of the project is a telegram bot @cryptonitto_bot<strong> (https://t.me/cryptonitto_bot)</strong></p><p>The bot menu is shown on the figure below.</p><figure class="image"><img src="https://storage.yandexcloud.net/ds-ods/files/content/2023/01/13/1eabd43c/bot_menu.jpg"></figure>

<p>We are developing a unique forecasting method using the combination of time series prediction with news sentiment analysis.</p><p>A special service for collecting news of the cryptomarket has been developed.</p><p>The news structure is shown on the picture below.</p><figure class="image"><img src="https://storage.yandexcloud.net/ds-ods/files/content/2023/01/13/7a25dab2/news_infrastructure.jpg"></figure><p>The view of news parser is shown on the picture below.<img src="https://storage.yandexcloud.net/ds-ods/files/content/2023/01/13/7017bed9/feed_parser.png">he picture</p><p>&nbsp;</p>

<p>the Prophet library has been used in the pilot version of the predictive model .</p>

<p>The project appeared on the ML System Design Course by <a href="ODS.ai">ODS.ai</a></p><p>Git repository&nbsp;<a href="github.com/lunaplush/crypto/"> </a><a target="_blank" rel="noopener noreferrer" href="https://github.com/lunaplush/crypto/">https://github.com/lunaplush/crypto/</a></p><p>Team &nbsp;Aleksandra Maksimova and &nbsp;Dmitry Kotsarev</p><p>The Donbass Data Science community &nbsp;<a href="vk.com/DonbassDataScience ">vk.com/DonbassDataScience </a>we are supported by</p><p>Project support on <a href="dondata.ru">dondata.ru</a></p><p>Email: maximova.alexandra@mail.ru</p>

Cryptonitto is an assistance analytic system for a forecasting of crypto currency price movement on a daily time frames

Cryptocurrency rate forecasting

<p>Manifold aware <code>pytorch.optim</code>.</p>

<p>Unofficial implementation for <a href="https://openreview.net/forum?id=r1eiqi09K7" rel="noopener noreferrer" target="_blank">&quot;Riemannian Adaptive Optimization&nbsp;</a><a href="https://openreview.net/forum?id=r1eiqi09K7" rel="noopener noreferrer" target="_blank">Methods&quot;</a>&nbsp;at ICLR2019 and more.</p>

<p>Guthub page: <a href="https://github.com/geoopt/geoopt" rel="noopener noreferrer" target="_blank">https://github.com/geoopt/geoopt</a></p>

<h2>Installation</h2>

<ol>
<li>GitHub (preferred so far) due to active development
<pre>
<code>pip install git+https://github.com/geoopt/geoopt.git</code></pre>
</li>
<li>pypi (this might be significantly behind master branch)
<pre>
<code>pip install geopt</code></pre>

<ol>
</ol>
</li>
</ol>

<p>The preferred way to install geoopt will change once stable project stage is achieved.&nbsp;Now, pypi is behind master as we actively develop and implement new features.</p>

<h2>PyTorch Support</h2>

<p>Geoopt officially supports <strong>2 latest stable versions</strong> of pytorch upstream or the latest major release.</p>

<h2>What is done so far?</h2>

<p>Work is in progress but you can already use this. Note that API might&nbsp;change in future releases.</p>

<h4>Tensors</h4>

<ul>
<li>
<p><code>geoopt.ManifoldTensor</code> -- just as torch.Tensor with additional <code>manifold</code> keyword argument.</p>
</li>
<li>
<p><code>geoopt.ManifoldParameter</code>&nbsp;-- same as above, recognized in torch.nn.Module.parameters as correctly subclassed.</p>
</li>
</ul>

<p>All above containers have special methods to work with them as with&nbsp;points on a certain manifold</p>

<ul>
<li><code>.proj_()</code>&nbsp;--&nbsp;inplace projection on the manifold.</li>
<li><code>.proju(u)</code>&nbsp;--&nbsp;project vector <code>u</code> on the tangent space. You need&nbsp;to project all vectors for all methods below.</li>
<li><code>.egrad2rgrad(u)</code>&nbsp;--&nbsp;project gradient <code>u</code> on Riemannian manifold</li>
<li><code>.inner(u, v=None)</code>--&nbsp;inner product at this point for two&nbsp;<strong>tangent</strong> vectors at this point. The passed vectors are not<br />
&nbsp; projected, they are assumed to be already projected.</li>
<li><code>.retr(u)</code>--&nbsp;retraction map following vector <code>u</code></li>
<li><code>.expmap(u)</code>--&nbsp;exponential map following vector <code>u</code> (if expmap is not available in closed form, best approximation is used)</li>
<li><code>.transp(v,u)</code>--&nbsp;transport vector <code>v</code> &nbsp;with direction <code>u</code></li>
<li><code>.retr_transp(v,u)</code>--&nbsp;transport <code>self</code>, vector <code>v&nbsp;</code>(and possibly more vectors) with direction <code>u</code>&nbsp;(returns are plain tensors)</li>
</ul>

<h3>Manifolds</h3>

<ul>
<li><code>geoopt.Euclidean</code> -- unconstrained manifold in <code>R</code> with&nbsp;Euclidean metric</li>
<li><code>geoopt.Stiefel</code> --&nbsp;Stiefel manifold on matrices&nbsp;&nbsp;<code>A in R^{n x p} : A^t A=I, n &gt;= p</code></li>
<li><code>geoopt.Sphere</code> -- Sphere manifold <code>||x||=1</code></li>
<li><code>geoopt.BirkhoffPolytope</code> --&nbsp;manifold of Doubly Stochastic matrices</li>
<li><code>geoopt.Stereographic</code> --&nbsp;Constant curvature stereographic projection model</li>
<li><code>geoopt.SphereProjection</code> --&nbsp;Sphere stereographic projection model</li>
<li><code>geoopt.PoincareBall</code> --&nbsp;<a href="https://en.wikipedia.org/wiki/Poincar%C3%A9_disk_model" rel="noopener noreferrer" target="_blank">Poincare ball model</a></li>
<li><code>geoopt.Lorentz</code> --&nbsp;<a href="https://en.wikipedia.org/wiki/Hyperboloid_model" rel="noopener noreferrer" target="_blank">Hyperboloid model</a></li>
<li><code>geoopt.ProductManifold</code> --&nbsp;Product manifold constructor</li>
<li><code>geoopt.Scaled</code> --&nbsp;Scaled version of the manifold. Similar to <a href="https://openreview.net/forum?id=HJxeWnCcF7" rel="noopener noreferrer" target="_blank">Learning Mixed-Curvature Representations in Product Spaces</a> if combined with <code>ProductManifold</code></li>
<li><code>geoopt.SymmetricPositiveDefinite</code> --&nbsp;SPD matrix manifold</li>
<li><code>geoopt.UpperHalf</code> --&nbsp;Siegel Upper half manifold. Supports Riemannian and Finsler metrics, as in <a href="https://arxiv.org/abs/2106.04941" rel="noopener noreferrer" target="_blank">Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach</a></li>
<li><code>geoopt.BoundedDomain</code> --&nbsp;Siegel Bounded domain manifold. Supports Riemannian and Finsler metrics.</li>
</ul>

<p>All manifolds implement methods necessary to manipulate tensors on manifolds and&nbsp;tangent vectors to be used in general purpose. See more in `documentation`.</p>

<h2>Optimizers</h2>

<ul>
<li><code>geoopt.optim.RiemannianSGD</code> --&nbsp;a subclass of <code>torch.optim.SGD</code>&nbsp;with the same API and a Sparse version</li>
<li><code>geoopt.optim.RiemannianAdam&nbsp;</code>--&nbsp;a subclass of <code>torch.optim.Adam</code> and a Sparse version</li>
</ul>

<h2>Samplers</h2>

<ul>
<li><code>geoopt.samplers.RSGLD</code> -- Riemannian Stochastic Gradient Langevin&nbsp;Dynamics</li>
<li><code>geoopt.samplers.RHMC</code> --&nbsp;Riemannian Hamiltonian Monte-Carlo</li>
<li><code>geoopt.samplers.SGRHMC</code> --&nbsp;Stochastic Gradient Riemannian&nbsp;Hamiltonian Monte-Carlo</li>
</ul>

<h2><br />
Citing Geoopt</h2>

<p>If you find this project useful in your research, please kindly add this bibtex entry in references and cite.</p>

<pre>
<code>@misc{geoopt2020kochurov,</code>
<code>    title={Geoopt: Riemannian Optimization in PyTorch},</code>
<code>    author={Max Kochurov and Rasul Karimov and Serge Kozlukov},</code>
<code>    year={2020},</code>
<code>    eprint={2005.02819},</code>
<code>    archivePrefix={arXiv},</code>
<code>    primaryClass={cs.CG}</code>
<code>}</code></pre>

Maxim Kochurov

PyTorch framework for Riemannian Deep Learning

Geoopt

<h2><code>Optimum Transformers</code></h2><p><code>Accelerated NLP pipelines for fast inference&nbsp;</code></p><figure class="image image_resized" style="width:20px;"><img src="https://emoji.discourse-cdn.com/apple/rocket.png?v=12" alt=":rocket:"></figure><p><code>on CPU and GPU. Built with&nbsp;</code></p><figure class="image image_resized" style="width:20px;"><img src="https://emoji.discourse-cdn.com/apple/hugs.png?v=12" alt=":hugs:"></figure><p><code>Transformers, Optimum and ONNX runtime.</code></p><figure class="image"><img src="https://img.shields.io/github/stars/AlekseyKorshuk/optimum-transformers?style=social" alt="GitHub stars"></figure><h2><code>Disclaimer</code></h2><p><code>This project is my inspiration of </code><a target="_blank" rel="noopener noreferrer" href="https://huggingface.co/infinity"><code>Huggingface Infinity 3</code></a><code>. And first step done by </code><a target="_blank" rel="noopener noreferrer" href="https://twitter.com/psuraj28"><code>Suraj Patil</code></a><code>.</code></p><blockquote><p><a target="_blank" rel="noopener noreferrer" href="https://twitter.com/huggingface"><code>@huggingface</code></a><code>’s pipeline API is awesome!</code></p><figure class="image image_resized" style="width:20px;"><img src="https://emoji.discourse-cdn.com/apple/star_struck.png?v=12" alt=":star_struck:"></figure><p><code>, right? And onnxruntime is super fast !</code></p><figure class="image image_resized" style="width:20px;"><img src="https://emoji.discourse-cdn.com/apple/rocket.png?v=12" alt=":rocket:"></figure><p><code>. Wouldn’t it be great to combine these two?</code><br><code><i>– Tweet by Suraj Patil</i></code></p></blockquote><p><code>It was under this slogan that I started doing this project!</code></p><blockquote><p><code>And the main goal was to show myself to get into <strong>@huggingface</strong> team</code></p><figure class="image image_resized" style="width:20px;"><img src="https://emoji.discourse-cdn.com/apple/hugs.png?v=12" alt=":hugs:"></figure></blockquote><h2><code>How to use</code></h2><h3><code>Quick start</code></h3><p><code>The usage is exactly the same as original pipelines, except minor improves:</code></p><pre><code class="language-bash">from optimum_transformers import pipeline

pipe = pipeline("text-classification", use_onnx=True, optimize=True)
pipe("This restaurant is awesome")
# [{'label': 'POSITIVE', 'score': 0.9998743534088135}]
</code></pre><ul><li><code><strong>use_onnx</strong>- converts default model to ONNX graph</code></li><li><code><strong>optimize</strong> - optimizes converted ONNX graph with </code><a target="_blank" rel="noopener noreferrer" href="https://huggingface.co/docs/optimum/index"><code>Optimum 8</code></a></li></ul><h3><code>Optimum config</code></h3><p><code>Read </code><a target="_blank" rel="noopener noreferrer" href="https://huggingface.co/docs/optimum/index"><code>Optimum 8</code></a><code> documentation for more details</code></p><pre><code class="language-bash">from optimum_transformers import pipeline
from optimum.onnxruntime import ORTConfig

ort_config = ORTConfig(quantization_approach="dynamic")
pipe = pipeline("text-classification", use_onnx=True, optimize=True, ort_config=ort_config)
pipe("This restaurant is awesome")
# [{'label': 'POSITIVE', 'score': 0.9998743534088135}]
</code></pre><h2><code>Benchmark</code></h2><h3><code>With notebook</code></h3><p><code>You can benchmark pipelines easier with </code><a target="_blank" rel="noopener noreferrer" href="https://github.com/AlekseyKorshuk/optimum-transformers/blob/master/notebooks/benchmark_pipelines.ipynb"><code>benchmark_pipelines 3</code></a><code> notebook.</code></p><h3><code>With own script</code></h3><pre><code class="language-bash">from optimum_transformers import Benchmark

task = "sentiment-analysis"
model_name = "philschmid/MiniLM-L6-H384-uncased-sst2"
num_tests = 100

benchmark = Benchmark(task, model_name)
results = benchmark(num_tests, plot=True)
</code></pre><h3><code>Results</code></h3><blockquote><p><code>Note: These results were collected on my local machine. So if you have high performance machine to benchmark, please contact me</code></p><figure class="image image_resized" style="width:20px;"><img src="https://emoji.discourse-cdn.com/apple/hugs.png?v=12" alt=":hugs:"></figure></blockquote><h4><code><strong>sentiment-analysis</strong></code></h4><p><code>Almost the same as in </code><a target="_blank" rel="noopener noreferrer" href="https://www.youtube.com/watch?v=jiftCAhOYQA"><code>Inifinity launch</code></a><code> video</code></p><figure class="image image_resized" style="width:20px;"><img src="https://emoji.discourse-cdn.com/apple/hugs.png?v=12" alt=":hugs:"></figure><p><code>AWS VM: g4dn.xlarge</code><br><code>GPU: NVIDIA T4</code><br><code>128 tokens</code><br><code>2.6 ms</code></p><p>&nbsp;</p><figure class="image"><img src="https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/optimized/2X/b/b0bbebce9d8186be0d20ecdbbc34ca3e327cb9fb_2_666x500.jpeg" alt="Resulting plot" srcset="https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/optimized/2X/b/b0bbebce9d8186be0d20ecdbbc34ca3e327cb9fb_2_666x500.jpeg, https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/optimized/2X/b/b0bbebce9d8186be0d20ecdbbc34ca3e327cb9fb_2_999x750.jpeg 1.5x, https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/original/2X/b/b0bbebce9d8186be0d20ecdbbc34ca3e327cb9fb.jpeg 2x" sizes="100vw" width="666"></figure><p>&nbsp;</p><h4><code><strong>zero-shot-classification</strong></code></h4><p><code>With typeform/distilbert-base-uncased-mnli</code></p><p>&nbsp;</p><figure class="image"><img src="https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/optimized/2X/d/d673c795ad1e6547cf92c5e4951371d8c61eb8bd_2_666x500.jpeg" alt="Resulting plot" srcset="https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/optimized/2X/d/d673c795ad1e6547cf92c5e4951371d8c61eb8bd_2_666x500.jpeg, https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/optimized/2X/d/d673c795ad1e6547cf92c5e4951371d8c61eb8bd_2_999x750.jpeg 1.5x, https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/original/2X/d/d673c795ad1e6547cf92c5e4951371d8c61eb8bd.jpeg 2x" sizes="100vw" width="666"></figure><p>&nbsp;</p><h4><code><strong>token-classification</strong></code></h4><p>&nbsp;</p><figure class="image"><img src="https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/optimized/2X/e/e66b1027e2c2b9af57be5e376402fb3d37cd3a43_2_666x500.jpeg" alt="Resulting plot" srcset="https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/optimized/2X/e/e66b1027e2c2b9af57be5e376402fb3d37cd3a43_2_666x500.jpeg, https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/optimized/2X/e/e66b1027e2c2b9af57be5e376402fb3d37cd3a43_2_999x750.jpeg 1.5x, https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/original/2X/e/e66b1027e2c2b9af57be5e376402fb3d37cd3a43.jpeg 2x" sizes="100vw" width="666"></figure><p>&nbsp;</p><p>&nbsp;</p><figure class="image"><img src="https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/optimized/2X/0/0c4ee5c9d3d4c65cda80668164f1520548a950d7_2_666x500.jpeg" alt="Resulting plot" srcset="https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/optimized/2X/0/0c4ee5c9d3d4c65cda80668164f1520548a950d7_2_666x500.jpeg, https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/optimized/2X/0/0c4ee5c9d3d4c65cda80668164f1520548a950d7_2_999x750.jpeg 1.5x, https://aws1.discourse-cdn.com/standard14/uploads/hellohellohello/original/2X/0/0c4ee5c9d3d4c65cda80668164f1520548a950d7.jpeg 2x" sizes="100vw" width="666"></figure><p>&nbsp;</p><p><code>More results are available in project repository: </code><a target="_blank" rel="noopener noreferrer" href="https://github.com/AlekseyKorshuk/optimum-transformers"><code>GitHub 13</code></a><code>.</code></p><p><br><br>&nbsp;</p><p>&nbsp;</p><p>&nbsp;</p>

Aleksey Korshuk

Accelerated NLP pipelines for fast inference on CPU and GPU

Optimum Transformers

<h3>Wait, what?</h3>

<p>The project <a href="https://github.com/alexeyev/gardiner2unicode" rel="noopener noreferrer" target="_blank">gardiner2unicode</a> is a simple Python package providing easy access to the mapping between the &quot;special IDs&quot;&nbsp;of the common Egyptian hieroglyphs and their Unicode table numbers. These &#39;special IDs&#39; are usually called the &quot;<a href="https://en.wikipedia.org/wiki/Gardiner%27s_sign_list " rel="noopener noreferrer" target="_blank">Gardiner&rsquo;s sign list</a>&quot;. This registry is named after Sir Alan Henderson Gardiner, one of the greatest Egyptologists ever, who compiled this list in one of his works.&nbsp;</p>

<figure class="image image_resized" style="width:85.47%;"><img src="https://storage.yandexcloud.net/datasouls-ods/files/16d2efc9/%D0%B8%D0%B7%D0%BE%D0%B1%D1%80%D0%B0%D0%B6%D0%B5%D0%BD%D0%B8%D0%B5.png" />
<figcaption>Hieroglyphs from the Pyramid of Unas with the corresponding Gardiner codes.</figcaption>
</figure>

<p>Another additional function of the package is the generation of hieroglyphs as *.PNG images using the provided font.&nbsp;</p>

<figure class="image image_resized" style="width:90.34%;"><img src="https://storage.yandexcloud.net/datasouls-ods/files/8414fc08/%D0%B8%D0%B7%D0%BE%D0%B1%D1%80%D0%B0%D0%B6%D0%B5%D0%BD%D0%B8%D0%B5.png" />
<figcaption>Getting the Unicode ID. Generating the image.</figcaption>
</figure>

<p>By default, the library uses the <a href="https://mjn.host.cs.st-andrews.ac.uk/egyptian/fonts/newgardiner.html" rel="noopener noreferrer" target="_blank">NewGardiner</a> font (license: <a href="https://opensource.org/licenses/OFL-1.1" rel="noopener noreferrer" target="_blank">OFL 1.1</a>).</p>

<h3>But&hellip; why?</h3>

<p><br />
Those working with ancient texts or those working on various hieroglyph recognition tasks may benefit from this project. Recent examples of cases for possible applications are the tasks solved with <a href="https://artsexperiments.withgoogle.com/fabricius/en" rel="noopener noreferrer" target="_blank">Fabricius</a>, <a href="https://ieeexplore.ieee.org/document/9528382" rel="noopener noreferrer" target="_blank">Glyphnet</a>, etc.<br />
<br />
The project has been published very recently, in late November 2021, so it needs to be tested more thoroughly. It would be great if this tool saves someone time, which could instead be used to focus on more important parts of the Ancient Egypt-related projects.</p>

Anton Alekseev

A helper tool for drawing Egyptian hieroglyphs and mapping’ their IDs

Gardiner2Unicode: Mapping Egyptian Hieroglyphs

<h2><strong>HuggingArtists - Train a model to generate lyrics</strong></h2>

<h3>Create AI-Artist in just 5 minutes!&nbsp;</h3>

<figure class="image"><a href="https://github.com/AlekseyKorshuk/huggingartists" rel="noopener noreferrer" target="_blank"><img src="https://img.shields.io/github/stars/AlekseyKorshuk/huggingartists?style=social" /></a></figure>

<h4><a href="https://colab.research.google.com/github/AlekseyKorshuk/huggingartists/blob/master/huggingartists-demo.ipynb" rel="noopener noreferrer" target="_blank">🚀 Run the demo notebook to train</a></h4>

<h4><a href="https://huggingface.co/spaces/AlekseyKorshuk/huggingartists" rel="noopener noreferrer" target="_blank">🚀 Run the GUI demo to test</a>&nbsp;</h4>

<h4><a href="https://github.com/AlekseyKorshuk/huggingartist" rel="noopener noreferrer" target="_blank">🚀 Source code</a></h4>

<h3>How to use</h3>

<p>Just to generate without training, use <a href="https://huggingface.co/spaces/AlekseyKorshuk/huggingartists" rel="noopener noreferrer" target="_blank">Spaces with Streamlit</a>.</p>

<figure class="image"><a href="https://huggingface.co/spaces/AlekseyKorshuk/huggingartists" rel="noopener noreferrer" target="_blank"><img src="https://static.streamlit.io/badges/streamlit_badge_black_white.svg" /></a></figure>

<figure class="image image_resized" style="width:100%;"><a href="https://huggingface.co/spaces/AlekseyKorshuk/huggingartists" rel="noopener noreferrer" target="_blank"><img src="https://raw.githubusercontent.com/AlekseyKorshuk/huggingartists/ed579456656b3c8b1876a8ebf3422da9930bb0e2/img/spaces-demo.png" /></a></figure>

<p>To train with the demo, click on the below link and share your results!</p>

<figure class="image"><a href="https://colab.research.google.com/github/AlekseyKorshuk/huggingartists/blob/master/huggingartists-demo.ipynb" rel="noopener noreferrer" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" /></a></figure>

<p>You can also use it locally by installing the dependencies with <code>pipenv</code> or <code>pip</code> and use <a href="https://github.com/AlekseyKorshuk/huggingartists/blob/master/huggingartists-demo.ipynb" rel="noopener noreferrer" target="_blank">huggingartists-demo.ipynb</a>.</p>

<h3>Results</h3>

<p>There are some interesting lyrics. Contact me to add your results.</p>

<h4><strong>Eminem</strong>:<br />
<code>I am a bit of a nutter</code><br />
<code>Like a fucking crazy nut</code><br />
<code>But I just wanted to break and get a little more serious, so be patient</code><br />
<code>I dont think I need no medical attention</code><br />
<code>But I do know that these niggas gonna be in my prayers</code><br />
<code>And they say Im a nutter</code><br />
<code>Like a fucking crazy nut</code><br />
<code>But I love you</code><br />
<code>I am a nutter</code><br />
<code>Like a fuckin nutter</code><br />
<code>But I feel like the greatest that I can be</code><br />
<code>With your body and your spirits</code><br />
<code>But I dont know how I will act</code><br />
<code>When I finally get out</code><br />
<code>And I get pissed off</code><br />
<code>Ill be right back at ya with the first one on the floor</code><br />
<code>But I aint ever gonna get the respect youve been getting</code><br />
<code>And Im a nutter...</code><br />
<br />
<code>I am bipolar while I&rsquo;m rhyming, bipolar while I am hate</code><br />
<code>When I&rsquo;m rhyming, I may seem a little bit crazy</code><br />
<code>But the thing&rsquo;s with these rhymes that I pick</code><br />
<code>I stick to the syllable &ccedil; unless it&rsquo;s on a syllable</code><br />
<code>Bread is full of charmin I am thinkin all of the garbage</code><br />
<code>Hear the bass line and ya hear the bass line</code><br />
<code>But hip hop is what makes&rsquo;em songs</code><br />
<code>I try to describe how I&rsquo;m gettin&rsquo; em all, but I&rsquo;m lazy</code><br />
<code>When I&rsquo;m rapin on a song, I&rsquo;m just making it</code><br />
<code>If I don&rsquo;t got the right, In my mind...</code><br />
&nbsp;</h4>

<h4><strong>Drake:</strong><br />
<code>I am never livin the life that I never lived</code><br />
<code>I walk around with my Glock 9</code><br />
<code>And lay down with my feet up</code><br />
<code>This is my house, bitch</code><br />
<code>Welcome to Detroit, this is my city</code><br />
<code>Ive made it all my people proud</code><br />
<code>I even sold my house down</code><br />
<code>To get a possible placement as a burnt pit</code><br />
<code>My little girl, she should ntroller</code><br />
<code>Wanna flip sometimes on the upside</code><br />
<code>But its hard to hold a grudge, I dont bite</code><br />
<code>I say my wholehearted, prayer is my heart</code><br />
<code>I pray for you when Im gone, but I gotta leave you in peace</code><br />
<code>That we did not plan to be seeing each other, well</code><br />
<code>We did plan to be seeing each other, well</code><br />
<code>And if you ever need anything, I...</code></h4>

<h3>Check existing</h3>

<ul>
<li><a href="https://huggingface.co/models?filter=huggingartists" rel="noopener noreferrer" target="_blank">Models</a></li>
<li><a href="https://huggingface.co/datasets?search=huggingartists" rel="noopener noreferrer" target="_blank">Datasets</a></li>
</ul>

<h3>Features</h3>

<ul>
<li>Generate lyrics by a specific artist</li>
<li>Automatically upload models and datasets to <a href="https://huggingface.co/huggingartists" rel="noopener noreferrer" target="_blank">HuggingFace Profile</a> after each run</li>
<li>Parse dataset once and use it next time without spending time</li>
<li>Each next run by any person will resume training from the last checkpoint</li>
<li>Training and results are automatically logged into <a href="https://docs.wandb.com" rel="noopener noreferrer" target="_blank">W&amp;B</a> through the <a href="https://docs.wandb.com/huggingface" rel="noopener noreferrer" target="_blank">HuggingFace integration</a></li>
</ul>

<h2>In future</h2>

<ul>
<li>combine all models and generate lyrics just by choosing the style</li>
<li>we can integrate this project with Video and Music generation so we can create our AI-Artist :)</li>
</ul>

<h3>Resources</h3>

<ul>
<li><a href="https://wandb.ai/huggingartists/huggingartists/reportlist" rel="noopener noreferrer" target="_blank">Explore the W&amp;B report</a> to understand how the model works</li>
<li><a href="https://docs.wandb.com/library/integrations/huggingface" rel="noopener noreferrer" target="_blank">HuggingFace and W&amp;B integration documentation</a></li>
</ul>

<h3>About</h3>

<p><i>Built by Aleksey Korshuk</i></p>

<figure class="image"><a href="https://github.com/AlekseyKorshuk" rel="noopener noreferrer" target="_blank"><img src="https://img.shields.io/github/followers/AlekseyKorshuk?style=social" /></a></figure>

<p>🚀 If you want to contribute to this project or create something cool together &mdash; contact me: <a href="https://github.com/AlekseyKorshuk" rel="noopener noreferrer" target="_blank">link</a></p>

<p><strong>Star project repository:</strong></p>

<figure class="image"><a href="https://github.com/AlekseyKorshuk/huggingartists" rel="noopener noreferrer" target="_blank"><img src="https://img.shields.io/github/stars/AlekseyKorshuk/huggingartists?style=social" /></a></figure>

Train a model to generate lyrics with Transformer

Hugging Artists: train a model to generate lyrics

<p>FEDOT is an open-source framework for automated modeling and machine learning (AutoML). The main idea of the FEDOT is to provide open, modular, extendable, and flexible instruments to the community to solve non-standard modeling tasks.</p><p>&nbsp;</p><p>It can build composite modeling pipelines for different real-world processes in an automated way using an evolutionary approach. FEDOT supports classification (binary and multiclass), regression, and time series prediction tasks, as well as different data types and multi-modal cases. Also, sensitivity analysis of the pipelines, custom pipelines design as the initial assumption of optimization, domain-specific objective functions and models, and other interesting features are implemented. FEDOT can be evaluated with both CPU and GPU.</p><p>&nbsp;</p><p>Current plans for the project development are:</p><ul><li>Support for the time series classification, hierarchical time series forecasting, etc;</li><li>Better support of the multi-modal AutoML;</li><li>Support for meta-AutoML to as initial stage for composing;</li><li>Controllability and interpretability features;</li><li>Additional benchmarking for different tasks and datasets;</li><li>Implementation of reinforcement learning and hybrid evolutionary optimization;</li><li>Integration with MLFlow and other MLOps tools;</li><li>Automated design for other types of models using the core of FEDOT (PDEs, bayesian networks, etc) and a lot of other ideas.</li></ul><p>FEDOT is maintained by the Natural Systems Simulation Lab of ITMO University, Russian. Also, any external software developers or AI researchers can use FEDOT or contribute to it. We are open to any feedback.</p><p>&nbsp;</p><ul><li>Github: <a target="_blank" rel="noopener noreferrer" href="https://github.com/nccr-itmo/FEDOT">https://github.com/nccr-itmo/FEDOT</a></li><li>Paper: <a target="_blank" rel="noopener noreferrer" href="https://www.sciencedirect.com/science/article/pii/S0167739X21003307">https://www.sciencedirect.com/science/article/pii/S0167739X21003307</a></li><li>Helpdesk: <a target="_blank" rel="noopener noreferrer" href="https://t.me/FEDOT_helpdesk">https://t.me/FEDOT_helpdesk</a></li></ul><p>Also, several posts on towardsdatascience if you want to go deeper:</p><ul><li><a target="_blank" rel="noopener noreferrer" href="https://towardsdatascience.com/how-automl-helps-to-create-composite-ai-f09e05287563">How AutoML helps to create composite AI?</a></li><li><a target="_blank" rel="noopener noreferrer" href="https://towardsdatascience.com/automl-for-time-series-definitely-a-good-idea-c51d39b2b3f">AutoML for time series: definitely a good idea</a></li><li><a target="_blank" rel="noopener noreferrer" href="https://towardsdatascience.com/automl-for-time-series-advanced-approaches-with-fedot-framework-4f9d8ea3382c">AutoML for time series: advanced approaches with FEDOT framework</a></li></ul>

Nikolay Nikitin

Mikhail Sarafanov

Maksimov Gleb

AutoML framework for the composite pipelines

FEDOT

<h1>Overview</h1>

<p><a href="https://github.com/SergeyShk/ruTS">ruTS</a> is a library that allows extracting statistics from texts in Russian. It provides the following functionality:</p>

<ul>
	<li><strong>Object extraction</strong> - creating tools for sentence and word extraction from a text, which can be further employed for counting statistics</li>
	<li><strong>Basic statistics</strong> - extracting basic linguistic statistics from a text (the number of complex words, syllables, letters, etc)</li>
	<li><strong>Readability metrics</strong> - counting readability metrics for a text (SMOG Index, Flesch-Kincaid Grade Level, etc)</li>
	<li><strong>Lexical diversity metrics</strong> - counting lexical diversity metrics for a text (Hapax Legomena Index, Type-Token Ratio, etc)</li>
	<li><strong>Morphological statistics</strong> - extracting morphological features from a text (part of speech, gender, transitivity, etc)</li>
	<li><strong>Datasets</strong> - working with a number of preprocessed datasets (soviet reading-books for literature classes, the collected works of Stalin)</li>
	<li><strong>Visualization</strong> - visualizing text with the help of graphs (Zipf&#39;s law, Literature Fingerprinting, Word Tree)</li>
	<li><strong>Components</strong> - adding the library&#39;s classes to spaCy pipelines</li>
	<li><strong>API</strong> - using functions via RESTful interface</li>
</ul>

<h1>Installation</h1>

<p>ruTS requires Python 3.7 or higher. To install the latest stable version from PyPI:</p>

<pre>
<code class="language-bash">$ pip install ruts</code></pre>

<h1>Usage</h1>

<pre>
<code class="language-python">from ruts import ReadabilityStats
text = "Ног нет, а хожу, рта нет, а скажу: когда спать, когда вставать, когда работу начинать"
rs = ReadabilityStats(text)
rs.get_stats()

    {'automated_readability_index': 0.2941666666666656,
    'coleman_liau_index': 0.2941666666666656,
    'flesch_kincaid_grade': 3.4133333333333304,
    'flesch_reading_easy': 83.16166666666666,
    'lix': 48.333333333333336,
    'smog_index': 0.05}

rs.print_stats()

                    Метрика                 | Значение 
    --------------------------------------------------
    Тест Флеша-Кинкайда                     |   3.41   
    Индекс удобочитаемости Флеша            |  83.16   
    Индекс Колман-Лиау                      |   0.29   
    Индекс SMOG                             |   0.05   
    Автоматический индекс удобочитаемости   |   0.29   
    Индекс удобочитаемости LIX              |  48.33  </code></pre>

<h1>Links</h1>

<ul>
	<li><a href="https://github.com/SergeyShk/ruTS" rel="noopener noreferrer" target="_blank">GitHub Repository</a>&nbsp;(with more examples)</li>
	<li><a href="https://sergeyshk.github.io/ruTS/" rel="noopener noreferrer" target="_blank">Documentation</a></li>
	<li><a href="https://ruts-api.herokuapp.com/docs" rel="noopener noreferrer" target="_blank">API</a></li>
	<li><a href="https://pypi.org/project/ruts/" rel="noopener noreferrer" target="_blank">PyPi</a></li>
	<li><a href="https://spacy.io/universe/project/ruts" rel="noopener noreferrer" target="_blank">spaCy Universe</a></li>
</ul>

Sergey Shkarin

Library for statistics extraction from texts in Russian

ruTS

<h1><b>About</b></h1>

<p>We are building an ML application for forecast and anomaly detection in air particles pollution data in Moscow. Existing applications mostly display data from monitoring stations and city-level forecast, but our goal is to provide street-level forecast and anomaly detection. We hope this will provide a more detailed understanding of air quality and helps in identifying sources of air pollution.</p>

<p>Project repository (with contribution guid):&nbsp;<a href="https://github.com/aerubanov/Proj_Air_Quality" rel="noopener noreferrer" target="_blank">https://github.com/aerubanov/Proj_Air_Quality</a></p>

<h1><strong>Data sources</strong></h1>

<p>We use data from three sources:</p>

<ul>
	<li>Community air quality monitoring network &ndash;&nbsp;<a href="https://luftdaten.info/" rel="noopener noreferrer" target="_blank">https://luftdaten.info/</a>&nbsp;&ndash;&nbsp;particles concentration (PM2.5 and PM10) data;</li>
	<li>Historical meteorology data and weather forecast &ndash;&nbsp;<a href="https://rp5.ru/" rel="noopener noreferrer" target="_blank">https://rp5.ru/</a></li>
	<li>Location feature (distance to road, park, industry, etc.) &ndash;&nbsp;<a href="https://www.openstreetmap.org/" rel="noopener noreferrer" target="_blank">https://www.openstreetmap.org/</a></li>
</ul>

<h1><strong>Model</strong></h1>

<p>We selected the bayesian model with the Gaussian process prior. The advantage of this type of model is the prediction of the target variable distribution, rather than a point estimate. It is important for anomaly detection and can be used for selecting locations for new monitoring stations.</p>

<p>In constructing the model, we rely on these articles:</p>

<ul>
	<li><a href="https://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/viewFile/9712/9309" rel="noopener noreferrer" target="_blank">https://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/viewFile/9712/9309</a></li>
	<li><a href="https://papers.nips.cc/paper/2017/file/f31b20466ae89669f9741e047487eb37-Paper.pdf" rel="noopener noreferrer" target="_blank">https://papers.nips.cc/paper/2017/file/f31b20466ae89669f9741e047487eb37-Paper.pdf</a></li>
</ul>

<h1><strong>Current state</strong></h1>

<p>Now the dataset is assembled and the main work is directly related to the construction of the model. After that, we plan to wrap the model in API and visualize the results on a web page.</p>

Anatolii

Air quality data analysis and forecast (in Moscow)

Projects

All Projects