Update model card with official links, citation, and paper information

README.md

@@ -1,12 +1,12 @@
 ---
+datasets:
+- zhifeixie/StreamAudio-2M
 language:
 - en
 - zh
-license: apache-2.0
 library_name: transformers
+license: apache-2.0
 pipeline_tag: audio-text-to-text
-datasets:
-- zhifeixie/StreamAudio-2M
 tags:
 - speech-language-model
 - streaming
@@ -14,13 +14,14 @@ tags:
 - multimodal
 - qwen2.5-omni
 ---
+
 # Audio-Interaction: Streaming Audio-In, Text-Out Conversational Model
 
-[**Code**](https://github.com/xzf-thu/Audio-Interaction) | [**Model**](https://huggingface.co/zhifeixie/Audio-Interaction) | [**Dataset**](https://huggingface.co/datasets/zhifeixie/Audio-Interaction-Data) <!-- TODO: confirm code repo URL and dataset repo id -->
+[**Project Page**](https://xzf-thu.github.io/Audio-Interaction/) | [**Code**](https://github.com/xzf-thu/Audio-Interaction) | [**Model**](https://huggingface.co/zhifeixie/Audio-Interaction) | [**Dataset**](https://huggingface.co/datasets/zhifeixie/StreamAudio-2M) | [**Paper**](https://huggingface.co/papers/2606.05121)
 
-Audio-Interaction is a streaming speech-language model that listens to audio in real time and decides, at each audio chunk, whether to keep listening or to start replying with text. The model alternates between a **LISTENING** state, where it consumes one encoder-output chunk per step and emits either `KEEP_SILENCE` or `TEXT_BEGIN`, and a **SPEAKING** state, where it autoregressively generates a text turn until `TEXT_END` and then returns to listening for the next chunk.
+Audio-Interaction is a unified streaming model that listens to audio in real time and decides, at each audio chunk, whether to keep listening or to start replying with text. It formalizes the "perceive-decide-respond" loop, allowing the model to handle conventional offline tasks (ASR, S2TT) while adding online capabilities like proactive intervention and real-time voice chatting.
 
-This design lets the model handle both spoken questions ("answer it") and ambient sounds ("decide based on the sound whether help is needed") within a single streaming session, without an external VAD or turn-taking heuristic.
+The model alternates between a **LISTENING** state, where it consumes one encoder-output chunk per step and emits either `KEEP_SILENCE` or `TEXT_BEGIN`, and a **SPEAKING** state, where it autoregressively generates a text turn until `TEXT_END` and then returns to listening for the next chunk.
 
 ## Model Details
 
@@ -54,14 +55,14 @@ Audio-Interaction/
 
 ## Intended Use
 
-Audio-Interaction is intended for streaming conversational agents that need to react to audio as it arrives — for example, voice assistants that may interject mid-utterance, alarms that respond to ambient sound, or low-latency dialogue systems where waiting for a full utterance before replying is too slow. The model is not a transcription system; it produces a conversational reply (or silence) rather than a verbatim transcript.
+Audio-Interaction is intended for streaming conversational agents that need to react to audio as it arrives — for example, voice assistants that may interject mid-utterance, alarms that respond to ambient sound, or low-latency dialogue systems where waiting for a full utterance before replying is too slow. 
 
 ## Quick Start
 
 ### Installation
 
 ```bash
-git clone https://github.com/xzf-thu/Audio-Interaction.git  # TODO: confirm repo URL
+git clone https://github.com/xzf-thu/Audio-Interaction.git
 cd Audio-Interaction
 conda create -n Audio-Interaction python=3.10 -y
 conda activate Audio-Interaction
@@ -78,7 +79,7 @@ from huggingface_hub import snapshot_download
 snapshot_download(repo_id="zhifeixie/Audio-Interaction", local_dir="checkpoints")
 ```
 
-`snapshot_download` is the recommended path — it pulls every file, resumes on interruption, and is the only way the download counter on this page advances. Please avoid `git clone` of the HF repo or the web "Download" button if you want your run reflected in the stats.
+`snapshot_download` is the recommended path — it pulls every file and resumes on interruption.
 
 ### Python Usage
 
@@ -92,12 +93,6 @@ run_inference(
 )
 ```
 
-For interactive use, omit `audio_paths` and `run_inference` will prompt for an audio path each round:
-
-```python
-run_inference(checkpoint_dir="checkpoints", rounds=5, device="cuda:0")
-```
-
 ## Streaming Protocol
 
 A single session looks like:
@@ -117,43 +112,24 @@ A single session looks like:
 
 The model is trained to emit at most one `TEXT_BEGIN` per audio chunk. Each assistant turn begins with `TEXT_BEGIN`, followed by an emotion token, the reply tokens, and `TEXT_END`. Turns starting with `KEEP_SILENCE` indicate the model chose not to respond to that chunk.
 
-## Training Summary
-
-<!-- TODO: fill in once details are public.
-Suggested fields:
-- Pretraining base
-- SFT / instruction-tuning data
-- Streaming-objective data construction (how KEEP_SILENCE / TEXT_BEGIN supervision was generated)
-- Total tokens / hours of audio
-- Hardware and duration
--->
-
-## Evaluation
-
-<!-- TODO: fill in once benchmarks are decided.
-Candidate metrics:
-- Spoken-QA accuracy on held-out audio prompts
-- False-trigger rate on ambient / non-speech audio (lower is better)
-- Response-onset latency in encoder chunks from end of question
-- Text quality of replies (e.g. GPT-judge or human preference)
--->
-
 ## Limitations
 
 - The model produces text, not speech. Pair it with a TTS system for end-to-end voice interaction.
-- Audio must be 16 kHz mono; non-conforming inputs are resampled by `whisper.load_audio` and padded to 0.4-second boundaries before encoding.
+- Audio must be 16 kHz mono; non-conforming inputs are resampled and padded to 0.4-second boundaries.
 - Decisions are made at 0.4-second granularity (one encoder chunk), which sets a floor on response-onset latency.
 - Trailing partial audio chunks shorter than 10 encoder frames are dropped before generation.
 
 ## Citation
 
-<!-- TODO: replace with the real arxiv id and year once published. -->
 ```bibtex
-@misc{xie_miniomni3,
-  title  = {Audio-Interaction: Streaming Audio-In, Text-Out Conversational Modeling},
-  author = {Zhifei Xie and collaborators},
-  year   = {2026},
-  note   = {Preprint in preparation}
+@misc{xie2026audiointeractionmodel,
+      title={Audio Interaction Model}, 
+      author={Zhifei Xie and Zihang Liu and Ze An and Xiaobin Hu and Yue Liao and Ziyang Ma and Dongchao Yang and Mingbao Lin and Deheng Ye and Shuicheng Yan and Chunyan Miao},
+      year={2026},
+      eprint={2606.05121},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD},
+      url={https://arxiv.org/abs/2606.05121}, 
 }
 ```