How AI4Bharat Is Building an Open-Source Language AI for Indian Languages‍

August 4, 2023

AI4Bharat is a center at IIT Madras, India, with the mission to bring parity in AI technologies in Indian languages with respect to English with open-source technologies.

The canvas of AI technologies has been dominated by the towering presence of English, leaving many native languages in the shadows. AI4Bharat’s mission encompasses building state-of-the-art, open, foundational AI models across various tasks for all 22 regional Indian languages. 

You might have questioned whether AI could truly comprehend the complexities of Indian languages. The answer is a big yes. From language understanding to translation, from speech recognition to text-to-speech models, AI4Bharat leaves no stone unturned in ensuring that Indian languages are well understood and articulated by the very technology that empowers them. 

AI4Bharat collaborates with partners to design and deploy reference applications, showcasing the immense potential of open AI models. Whether it’s video subtitling for educational content or aiding the recognition of sign languages from around the world, they enable an innovation ecosystem that empowers researchers, startups, and the government to unlock the true magic of Indian language AI.

The Language Models

AI4Bharat is at the forefront of driving multilingual excellence with its revolutionary language models. These models are designed for user-friendliness, empowering users to harness AI’s potential for multilingual applications. They cater to a diverse range of tasks and languages, enabling seamless communication and understanding.

The Indic Speech-to-Text Conformer

A 30M parameter ASR model with a conformer-based architecture, built to support real-time transcription for Indian languages. Trained on ULCA, KathBath, Shrutilipi, and MUCS datasets, it can be effortlessly deployed on Android devices through WebSocket.

The Indic Transliterate

Simplifies script conversions for 21 Indic languages. It is a transformer-based multilingual transliteration model with approximately 11M parameters, enabling easy conversion between Roman script and native scripts for 21 Indic languages. Its training on the extensive Aksharantar dataset, featuring 26 million word pairs across 20 Indic languages, ensures its accuracy and effectiveness.

The Indic Natural Language Generation 

Empowers narrative creation across 11 Indian languages and English. It is a multilingual, sequence-to-sequence pre-trained model, built upon the mBART architecture. The model's versatility allows you to develop natural language generation applications for Indian languages through fine-tuning with supervised training data, encompassing tasks such as machine translation, summarization, and question generation.

The Indic Text-to-Speech

Synthesizes expressive voices, enhancing the TTS experience. It is focused on developing multi-speaker text-to-speech models for Indic languages. It involves two models - an acoustic model generates waveforms from text, while a vocoder model synthesizes voice. It revolutionizes our interaction with Indic languages, enhancing accessibility and user experience in voice assistants, audiobooks, language learning, and assistive technologies, fostering inclusivity and a richer digital ecosystem.

The Indic BERT 

Defies complexity myths, delivering top-notch performance. It is a multilingual ALBERT model trained on a vast corpora encompassing 12 major Indian languages - Assamese, Bengali, English, Gujarati, Hindi, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil, and Telugu. Despite having fewer parameters compared to models like mBERT and XLM-R, the Indic BERT achieves exceptional performance across various tasks, making it a powerful tool for natural language processing in Indian languages and advancing language-based applications.

The Indic Named Entity Recognition 

Guarantees accurate identification of entities in sentences for 11 languages, such as Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil, and Telugu. Through extensive fine-tuning on millions of sentences and thorough evaluation against human-annotated test sets and publicly available Indian NER datasets, it ensures dependable and precise entity recognition.

The Indic Speech2Speech (Experimental) 

Bridges language gaps, facilitating speech translation between different languages. Its interface offers effortless language translation by utilizing ASR, NMT, and TTS, enabling speech-to-speech conversion across different languages.

The Indic Translation v2

Enables uninterrupted translation between English and 12 major Indian languages, using the advanced Transformers v2 architecture.

The Indic Speech-to-Text with Numbers

Offers exceptional accuracy in recognizing and parsing Indic Speech, even in the presence of numbers, owing to its ASR Conformer Models.

The Indic Speech-to-Text Whisperer

Provides precise transcriptions of spoken Indian languages, catering to diverse applications using an ASR model with Whisperer architecture. 

AI4Bharat’s language models mark a significant leap in Indian language AI technology, enabling users to embrace linguistic diversity and explore limitless possibilities.

Areas of Impact

AI4Bharat’s strategic targets encompass four crucial aspects - data curation and creation for diverse tasks and 22 scheduled Indian languages; state-of-the-art AI model development across all 22 regional languages; design and deployment of reference applications in collaboration with partners; and fostering innovation through educational support for researchers, startups, and the government in Indian-language AI technology.

In their pursuit of advancing Indian language AI technology, they focus on several crucial areas, each geared towards empowering linguistic diversity and inclusivity. Through open-source initiatives, they curate and create datasets and models for neural machine translation, allowing integrated communication between English and 12 Indic languages. 

Additionally, they address transliteration challenges with benchmarks, applications, and models bridging Roman and scripts for over 20 Indic languages. With a strong emphasis on accessibility, they offer open-source models for speech recognition in 9 Indian languages and text-to-speech synthesis for 13 languages, supporting both female and male speakers. 

Their language understanding initiatives provide open-source language models, benchmarks, and entity recognizers for 10 Indian languages. They are working on sign languages as well, offering datasets and models for sign recognition in various sign languages worldwide. 

Through tools like Shoonya and Chitralekha, AI4Bharat provides AI-assisted language work and video subtitling, prioritizing educational and media content. Lastly, Anuvaaad, their open-source tool, facilitates document-level translation with NMT and transliteration support. These areas of focus align with their core mission of fostering innovation and enabling an inclusive innovation ecosystem for Indian languages.

AI4Bharat Researchers Raising Seed Funding 

Prepare for a transformative AI revolution as India's AI4Bharat secures $12 million in seed funding, backed by venture capital firms Peak XV and Lightspeed Venture. This substantial investment reflects the soaring interest in generative AI, inspired by OpenAI's ChatGPT success in human-like conversations. 

Their recent mobile assistant launch breaks language barriers, offering government scheme information in multiple languages, and promoting inclusivity. Peak XV's inaugural investment post-rebranding reinforces AI4Bharat's ambitious pursuit of a brighter, more inclusive AI future, shaping the landscape of innovation.

Pioneering Open-Source AI for India’s Future

AI4Bharat stands at the forefront of open-source innovation, wielding the power of AI to conquer India's pressing socio-economic and environmental challenges. Guided by visionaries Prof. Pratyush Kumar and Prof. Mitesh Khapra, AI4Bharat delves deep into language technology, empowering machines to understand and engage with human texts and speech. A trailblazer in the field, they have released the largest corpus of Indian language texts, amplifying the potential impact of AI in the lives of billions who communicate predominantly in their native languages. 

This novel project requires high-end GPUs and AI4Bharat has partnered with E2E Networks. E2E is equipped with the latest NVIDIA cards like the H100 and A100, which makes it an ideal choice.

Latest Blogs
This is a decorative image for: A Complete Guide To Customer Acquisition For Startups
October 18, 2022

A Complete Guide To Customer Acquisition For Startups

Any business is enlivened by its customers. Therefore, a strategy to constantly bring in new clients is an ongoing requirement. In this regard, having a proper customer acquisition strategy can be of great importance.

So, if you are just starting your business, or planning to expand it, read on to learn more about this concept.

The problem with customer acquisition

As an organization, when working in a diverse and competitive market like India, you need to have a well-defined customer acquisition strategy to attain success. However, this is where most startups struggle. Now, you may have a great product or service, but if you are not in the right place targeting the right demographic, you are not likely to get the results you want.

To resolve this, typically, companies invest, but if that is not channelized properly, it will be futile.

So, the best way out of this dilemma is to have a clear customer acquisition strategy in place.

How can you create the ideal customer acquisition strategy for your business?

  • Define what your goals are

You need to define your goals so that you can meet the revenue expectations you have for the current fiscal year. You need to find a value for the metrics –

  • MRR – Monthly recurring revenue, which tells you all the income that can be generated from all your income channels.
  • CLV – Customer lifetime value tells you how much a customer is willing to spend on your business during your mutual relationship duration.  
  • CAC – Customer acquisition costs, which tells how much your organization needs to spend to acquire customers constantly.
  • Churn rate – It tells you the rate at which customers stop doing business.

All these metrics tell you how well you will be able to grow your business and revenue.

  • Identify your ideal customers

You need to understand who your current customers are and who your target customers are. Once you are aware of your customer base, you can focus your energies in that direction and get the maximum sale of your products or services. You can also understand what your customers require through various analytics and markers and address them to leverage your products/services towards them.

  • Choose your channels for customer acquisition

How will you acquire customers who will eventually tell at what scale and at what rate you need to expand your business? You could market and sell your products on social media channels like Instagram, Facebook and YouTube, or invest in paid marketing like Google Ads. You need to develop a unique strategy for each of these channels. 

  • Communicate with your customers

If you know exactly what your customers have in mind, then you will be able to develop your customer strategy with a clear perspective in mind. You can do it through surveys or customer opinion forms, email contact forms, blog posts and social media posts. After that, you just need to measure the analytics, clearly understand the insights, and improve your strategy accordingly.

Combining these strategies with your long-term business plan will bring results. However, there will be challenges on the way, where you need to adapt as per the requirements to make the most of it. At the same time, introducing new technologies like AI and ML can also solve such issues easily. To learn more about the use of AI and ML and how they are transforming businesses, keep referring to the blog section of E2E Networks.

Reference Links

This is a decorative image for: Constructing 3D objects through Deep Learning
October 18, 2022

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

3D reconstruction is one of the most complex issues of deep learning systems. There have been multiple types of research in this field, and almost everything has been tried on it — computer vision, computer graphics and machine learning, but to no avail. However, that has resulted in CNN or convolutional neural networks foraying into this field, which has yielded some success.

The Main Objective of the 3D Object Reconstruction

Developing this deep learning technology aims to infer the shape of 3D objects from 2D images. So, to conduct the experiment, you need the following:

  • Highly calibrated cameras that take a photograph of the image from various angles.
  • Large training datasets can predict the geometry of the object whose 3D image reconstruction needs to be done. These datasets can be collected from a database of images, or they can be collected and sampled from a video.

By using the apparatus and datasets, you will be able to proceed with the 3D reconstruction from 2D datasets.

State-of-the-art Technology Used by the Datasets for the Reconstruction of 3D Objects

The technology used for this purpose needs to stick to the following parameters:

  • Input

Training with the help of one or multiple RGB images, where the segmentation of the 3D ground truth needs to be done. It could be one image, multiple images or even a video stream.

The testing will also be done on the same parameters, which will also help to create a uniform, cluttered background, or both.

  • Output

The volumetric output will be done in both high and low resolution, and the surface output will be generated through parameterisation, template deformation and point cloud. Moreover, the direct and intermediate outputs will be calculated this way.

  • Network architecture used

The architecture used in training is 3D-VAE-GAN, which has an encoder and a decoder, with TL-Net and conditional GAN. At the same time, the testing architecture is 3D-VAE, which has an encoder and a decoder.

  • Training used

The degree of supervision used in 2D vs 3D supervision, weak supervision along with loss functions have to be included in this system. The training procedure is adversarial training with joint 2D and 3D embeddings. Also, the network architecture is extremely important for the speed and processing quality of the output images.

  • Practical applications and use cases

Volumetric representations and surface representations can do the reconstruction. Powerful computer systems need to be used for reconstruction.

Given below are some of the places where 3D Object Reconstruction Deep Learning Systems are used:

  • 3D reconstruction technology can be used in the Police Department for drawing the faces of criminals whose images have been procured from a crime site where their faces are not completely revealed.
  • It can be used for re-modelling ruins at ancient architectural sites. The rubble or the debris stubs of structures can be used to recreate the entire building structure and get an idea of how it looked in the past.
  • They can be used in plastic surgery where the organs, face, limbs or any other portion of the body has been damaged and needs to be rebuilt.
  • It can be used in airport security, where concealed shapes can be used for guessing whether a person is armed or is carrying explosives or not.
  • It can also help in completing DNA sequences.

So, if you are planning to implement this technology, then you can rent the required infrastructure from E2E Networks and avoid investing in it. And if you plan to learn more about such topics, then keep a tab on the blog section of the website

Reference Links

This is a decorative image for: Comprehensive Guide to Deep Q-Learning for Data Science Enthusiasts
October 18, 2022

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

For all data science enthusiasts who would love to dig deep, we have composed a write-up about Q-Learning specifically for you all. Deep Q-Learning and Reinforcement learning (RL) are extremely popular these days. These two data science methodologies use Python libraries like TensorFlow 2 and openAI’s Gym environment.

So, read on to know more.

What is Deep Q-Learning?

Deep Q-Learning utilizes the principles of Q-learning, but instead of using the Q-table, it uses the neural network. The algorithm of deep Q-Learning uses the states as input and the optimal Q-value of every action possible as the output. The agent gathers and stores all the previous experiences in the memory of the trained tuple in the following order:

State> Next state> Action> Reward

The neural network training stability increases using a random batch of previous data by using the experience replay. Experience replay also means the previous experiences stocking, and the target network uses it for training and calculation of the Q-network and the predicted Q-Value. This neural network uses openAI Gym, which is provided by taxi-v3 environments.

Now, any understanding of Deep Q-Learning   is incomplete without talking about Reinforcement Learning.

What is Reinforcement Learning?

Reinforcement is a subsection of ML. This part of ML is related to the action in which an environmental agent participates in a reward-based system and uses Reinforcement Learning to maximize the rewards. Reinforcement Learning is a different technique from unsupervised learning or supervised learning because it does not require a supervised input/output pair. The number of corrections is also less, so it is a highly efficient technique.

Now, the understanding of reinforcement learning is incomplete without knowing about Markov Decision Process (MDP). MDP is involved with each state that has been presented in the results of the environment, derived from the state previously there. The information which composes both states is gathered and transferred to the decision process. The task of the chosen agent is to maximize the awards. The MDP optimizes the actions and helps construct the optimal policy.

For developing the MDP, you need to follow the Q-Learning Algorithm, which is an extremely important part of data science and machine learning.

What is Q-Learning Algorithm?

The process of Q-Learning is important for understanding the data from scratch. It involves defining the parameters, choosing the actions from the current state and also choosing the actions from the previous state and then developing a Q-table for maximizing the results or output rewards.

The 4 steps that are involved in Q-Learning:

  1. Initializing parameters – The RL (reinforcement learning) model learns the set of actions that the agent requires in the state, environment and time.
  2. Identifying current state – The model stores the prior records for optimal action definition for maximizing the results. For acting in the present state, the state needs to be identified and perform an action combination for it.
  3. Choosing the optimal action set and gaining the relevant experience – A Q-table is generated from the data with a set of specific states and actions, and the weight of this data is calculated for updating the Q-Table to the following step.
  4. Updating Q-table rewards and next state determination – After the relevant experience is gained and agents start getting environmental records. The reward amplitude helps to present the subsequent step.  

In case the Q-table size is huge, then the generation of the model is a time-consuming process. This situation requires Deep Q-learning.

Hopefully, this write-up has provided an outline of Deep Q-Learning and its related concepts. If you wish to learn more about such topics, then keep a tab on the blog section of the E2E Networks website.

Reference Links

This is a decorative image for: GAUDI: A Neural Architect for Immersive 3D Scene Generation
October 13, 2022

GAUDI: A Neural Architect for Immersive 3D Scene Generation

The evolution of artificial intelligence in the past decade has been staggering, and now the focus is shifting towards AI and ML systems to understand and generate 3D spaces. As a result, there has been extensive research on manipulating 3D generative models. In this regard, Apple’s AI and ML scientists have developed GAUDI, a method specifically for this job.

An introduction to GAUDI

The GAUDI 3D immersive technique founders named it after the famous architect Antoni Gaudi. This AI model takes the help of a camera pose decoder, which enables it to guess the possible camera angles of a scene. Hence, the decoder then makes it possible to predict the 3D canvas from almost every angle.

What does GAUDI do?

GAUDI can perform multiple functions –

  • The extensions of these generative models have a tremendous effect on ML and computer vision. Pragmatically, such models are highly useful. They are applied in model-based reinforcement learning and planning world models, SLAM is s, or 3D content creation.
  • Generative modelling for 3D objects has been used for generating scenes using graf, pigan, and gsn, which incorporate a GAN (Generative Adversarial Network). The generator codes radiance fields exclusively. Using the 3D space in the scene along with the camera pose generates the 3D image from that point. This point has a density scalar and RGB value for that specific point in 3D space. This can be done from a 2D camera view. It does this by imposing 3D datasets on those 2D shots. It isolates various objects and scenes and combines them to render a new scene altogether.
  • GAUDI also removes GANs pathologies like mode collapse and improved GAN.
  • GAUDI also uses this to train data on a canonical coordinate system. You can compare it by looking at the trajectory of the scenes.

How is GAUDI applied to the content?

The steps of application for GAUDI have been given below:

  • Each trajectory is created, which consists of a sequence of posed images (These images are from a 3D scene) encoded into a latent representation. This representation which has a radiance field or what we refer to as the 3D scene and the camera path is created in a disentangled way. The results are interpreted as free parameters. The problem is optimized by and formulation of a reconstruction objective.
  • This simple training process is then scaled to trajectories, thousands of them creating a large number of views. The model samples the radiance fields totally from the previous distribution that the model has learned.
  • The scenes are thus synthesized by interpolation within the hidden space.
  • The scaling of 3D scenes generates many scenes that contain thousands of images. During training, there is no issue related to canonical orientation or mode collapse.
  • A novel de-noising optimization technique is used to find hidden representations that collaborate in modelling the camera poses and the radiance field to create multiple datasets with state-of-the-art performance in generating 3D scenes by building a setup that uses images and text.

To conclude, GAUDI has more capabilities and can also be used for sampling various images and video datasets. Furthermore, this will make a foray into AR (augmented reality) and VR (virtual reality). With GAUDI in hand, the sky is only the limit in the field of media creation. So, if you enjoy reading about the latest development in the field of AI and ML, then keep a tab on the blog section of the E2E Networks website.

Reference Links

Build on the most powerful infrastructure cloud

A vector illustration of a tech city using latest cloud technologies & infrastructure