Realtime-Venus local preparation commited on
Commit
4ef2e83
·
1 Parent(s): ca3e9c9

Refine public model documentation

Browse files
Files changed (2) hide show
  1. README.md +1 -1
  2. README_zh.md +1 -1
README.md CHANGED
@@ -687,7 +687,7 @@ print("Saved generated speech to output/audio_full_duplex.wav")
687
 
688
  ## 9. Data
689
 
690
- [HEARTBEAT Challenge](./data/HEARTBEAT_Challenge/README.md) contains audio and video task data; see the data README for partitions, formats, and loading instructions.
691
 
692
  ## 10. 📝 Citation
693
 
 
687
 
688
  ## 9. Data
689
 
690
+ HEARTBEAT Challenge evaluates when to respond and what to say in continuous audio or audio-visual interaction, covering reciprocal audio turn-taking and streaming proactive understanding. The challenge grew out of Realtime-Venus; see the [data README](./data/HEARTBEAT_Challenge/README.md) for task details, data organization, and loading instructions.
691
 
692
  ## 10. 📝 Citation
693
 
README_zh.md CHANGED
@@ -596,7 +596,7 @@ print("Saved generated speech to output/audio_full_duplex.wav")
596
 
597
  ## 9. Data
598
 
599
- [HEARTBEAT Challenge](./data/HEARTBEAT_Challenge/README_zh.md) 包含音频与视频任务数据,数据分区、格式和读取方式请参阅数据说明。
600
 
601
  ## 10. 📝 引用
602
 
 
596
 
597
  ## 9. Data
598
 
599
+ HEARTBEAT Challenge 评测系统在连续音频或音视频输入中判断何时回应、说什么的能力,涵盖双向音频轮次交互与流式主动理解两个赛道。该挑战赛由 Realtime-Venus 发展而来,具体任务、数据组织和读取方法见[数据 README](./data/HEARTBEAT_Challenge/README_zh.md)。
600
 
601
  ## 10. 📝 引用
602