Documentation and Resources
Web demos for ASR, MT and TTS have been developed for public usage. Using these existing endpoints, the Speech-to-Speech and Video-to-Video demos have been built.
API access information elaborating on utilizing the models deployed by the lab. Requests from python and cURL are well supported.
Details of the several models developed and being built, along with the download access to the same.
Access to data collected and hosted by Speech Lab, IITM.
Last update: August
2024
Created: March 24, 2023
Created: March 24, 2023