How to finetune audio duplex ability?

This work and demo is very impressive. 😎 👍 👍

I'm interest in fine-tuning the model, particularly for improving speech duplex interaction (simultaneous listening and speaking) and interruption handling. However, it would be important to avoid catastrophic forgetting that might degrade these capabilities.

I would appreciate some clarification about the training design:

1. Interruption training
   How is the "barge-in" trained in this model? Is it implemented in a way similar to Moshi-style streaming speech interaction, or FLM-Audio style duplex conversational modeling?

2. Duplex interaction (listen while speaking)
   How is the model trained to listen while speaking? Does the training data contain overlapping speech segments or a special interaction format that enables duplex behavior and monologue generation?

3. About Some finetuning details
   If we want to fine-tune data to keep duplex capabilities, How to input data to model? ( I assume the training data might follow a format similar to the Hugging Face chat template. However, I'm not sure how barge-in events or interruption labels are encoded in the dataset)

Thank you very much 😍

The issue names no specific file, test, or entry point. Start by locating the project's fine-tuning and audio-training documentation, then compare the referenced Moshi-style and FLM-Audio approaches with the expected chat-template data format. Done means documenting how interruption and duplex behavior are represented and how fine-tuning can preserve those capabilities.