Refactor README and streaming_turn_model.py to clarify fixed-grid frame ownership and update documentation. Remove merge conflict markers and enhance explanations regarding session launching conditions and audio slicing behavior.

This commit is contained in:
Xin Wang
2026-08-17 22:59:02 +08:00
parent a6dea1529a
commit d815b59def
2 changed files with 0 additions and 16 deletions

View File

@@ -584,17 +584,11 @@ python streaming_turn_model.py \
--output features/Session_1_first_4s_check.pt
```
<<<<<<< HEAD
Do not launch all sessions unless `cache_replay` cosine is nearly 1. For
`open-stream-replay`, a materially lower `continuous_window_semantics` cosine
means that the custom payload stitching is not equivalent to one continuous
Qwen input; it must not be dismissed as a media-turn-boundary effect because
this mode intentionally keeps a single media turn open.
=======
Do not launch all sessions unless `cache_replay` cosine is nearly 1. The
`continuous_window_semantics` cosine answers a different question and may be
lower because blockwise media preprocessing changes the representation.
>>>>>>> 8145be410866dd0675038d92347aea34d24b84d5
Video can be sampled at 2 FPS while predictions remain at 5 Hz. Audio and the
causal boundary update every 200 ms; consecutive prediction times may use the