I am dealing with conversations containing both English and Spanish, and Spanish is the primary language here. The situation is that English is interweaving with Spanish in some parts of the conversation, and I would like to tell them apart. I know that we will pass in a model name as a parameter, but I feel like Watson does not support me to indicate a second language as another parameter.
The Watson Speech to Text models are language specific, so you would need to pass the audio through two models via two separate API calls.