This app performs spoken language identification (LID) on audio files using a pre-trained model. Current version uses OpenAI's Whisper model for LID.
General user instructions for CLAMS apps are available at CLAMS Apps documentation.
If CUDA device is available, the app will utilize it for faster processing. Otherwise, it will run on CPU.
For the full list of parameters, please refer to the app metadata from the CLAMS App Directory or the metadata.py file in this repository.