Learning path

AI for Bharat

Build AI that works in Indian languages: text, speech and translation.

13 lessons · 79 min left

Start path → What a large language model does

FoundationsLesson 2: What a large language model doesAn LLM is autocomplete that swallowed a library. Understanding that one sentence explains most of its strengths and every one of its weaknesses.Beginner4 min read🧪 Lab📝 TestUp next
Build an LLMLesson 37: Step 1 · The tokenizerBefore a model sees language, something must chop text into pieces. Get this wrong and everything downstream is quietly worse.Middle6 min read🧪 Lab📝 Test
AI for Indian languagesLesson 234: Why Indian languages are hard for AIIndia has 22 scheduled languages and hundreds of languages and dialects overall. Here is why AI often works less well in them, and what builders can do.Middle6 min read🧪 Lab📝 Test
AI for Indian languagesLesson 235: Tokens, scripts and the cost of Indic textTokenizers trained mostly on English often split Indian-language text into more pieces. That means higher cost and less room in the context window. Measure it yourself.Middle6 min read🧪 Lab📝 Test
AI for Indian languagesLesson 236: Datasets and open projects for Indian languagesYou do not have to start from zero. Learn about open projects such as AI4Bharat and Bhashini, where to find datasets, and why you must always check the licence.Middle6 min read🧪 Lab📝 Test
AI for Indian languagesLesson 237: Speech recognition for Indian languagesTurning speech into text is hard with accents, noise and mixed languages. Learn how word error rate works, write it in Python, and test fairly.Middle7 min read🧪 Lab📝 Test
AI for Indian languagesLesson 238: Text-to-speech and voice for Indian languagesMaking a computer speak an Indian language naturally is about more than sound quality. Names, numbers, consent for voices and misuse of voice clones all matter.Middle6 min read🧪 Lab📝 Test
AI for Indian languagesLesson 239: Machine translation and how to judge itMachine translation is useful and imperfect. Learn to judge it with people, with back-translation and with metrics like BLEU and chrF, and know the limits of each.Middle6 min read🧪 Lab📝 Test
AI for Indian languagesLesson 240: Code-mixing: Hinglish and friendsPeople often mix languages in one sentence and type them in Roman letters. Learn how to handle mixed input, normalise it carefully, and test with real phrases.Middle6 min read🧪 Lab📝 Test
AI for Indian languagesLesson 241: Collecting language data ethicallyLanguage data comes from people. Learn how to collect text and speech with real consent, fair pay, privacy and fair representation, and how to give back.Middle6 min read🧪 Lab📝 Test
RAG and search engineeringLesson 207: Why retrieval beats retrainingA model only knows what it saw in training. Retrieval lets it read your fresh and private documents at answer time, and show where each answer came from.Middle6 min read🧪 Lab📝 Test
RAG and search engineeringLesson 208: Embeddings and similarity searchAn embedding turns text into a list of numbers, so that texts with similar meaning land close together. Learn how similarity is measured and how search stays fast.Middle6 min read🧪 Lab📝 Test
RAG and search engineeringLesson 209: Chunking documents wellSearch finds chunks, not whole documents. How you cut the text decides what can be found. Learn size, overlap, splitting by headings and useful metadata.Middle8 min read🧪 Lab📝 Test