Chitralekha is an open source platform for video subtitling across various Indic languages, using ML model support (ASR for Transcription, NMT for Translation and TTS for Voice Over). Chitralekha offers support for multiple input sources (Ex: Youtube, local etc), transcription generation process (Ex: Models, Source captions, Custom subtitle files etc) and voice over(Ex: mp3 for audio only, mp4 for audio-video combination, etc)
Chitralekha is purely built on technologies supported by Python. This offers wide variety of tech stack to be easily integrated. The cloud agnostic stack also provides the flexibility to host in any on-prem or cloud platforms.
The heavy lifting is done in the background. The UI is designed to be as simple as possible, but not compromising on any of the features. Easy to submit the documents for digitization, translation, review, workflow management, job monitoring etc.
Chitralekha provides many plug-and-play features that are ready to execute your digitization & translation tasks using any of the available models. This makes Chitralekha easy to apply to current infrastructure and extend to next-gen technologies.
Anyone with basic knowledge in language can be onboarded to Chitralekha. It does not limit the scope of your tasks; you can use it to build pipelines to generate the final translated version of the submitted documents.
Wherever you want to share your improvement you can do this by opening a PR. It's simple as that, no barriers, no prolonged procedures. Chitralekha has many active users who willingly share their experiences. Have any questions? Reach out to us via github or email
We are working with NPTEL to help their language contributors provide transcriptions for NPTEL's videos on higher education in various Indian languages.
We are working with Project BIRD from IIM Ahmedabad to provide same language subtitling for improving literacy in Indian languages.