Open kqkq opened 1 year ago
The current workflow involves selecting the language model once on the editor side and then using it on the packaged side. But your idea is great, as it allows for dynamic language model selection at runtime based on user preferences, thank you! I'll implement it at some point.
It's a common practice to use a tiny model for the streaming process. And use a larger model to get an accurate result when the full audio is received.
Can we add an option to choose the model when we create a recognizer? Then we can use 2 recognizers with different models to finish the job above.