Optimize overlap working-memory audio preprocessing

README.md

@@ -1300,6 +1300,13 @@ phase artifact rather than general evidence for better recent semantics.
 
 Run a 24-second L20 smoke test first:
 
+The sliding 2-second recap otherwise invokes Whisper's model-maximum audio
+padding 120 times. Run log-Mel extraction on the model GPU and set explicit
+right padding to zero. Every EasyCom 0.2-second increment contains 3200 samples
+at 16 kHz and is already divisible by Whisper's 160-sample hop, so no external
+silence is needed. This preserves the feature extractor's own STFT boundary
+handling while avoiding repeated processing of tens of seconds of zeros.
+
 ```bash
 mkdir -p features/easycom_overlap_working_8s_smoke
 
@@ -1317,6 +1324,8 @@ python streaming_turn_model_directly.py \
   --working-memory-seconds 2 \
   --video-fps 2 \
   --frame-cache-size 128 \
+  --audio-feature-device model \
+  --audio-right-padding-samples 0 \
   --decoder decord \
   --decoder-threads 1 \
   --max-open-readers 1 \
@@ -1366,6 +1375,8 @@ python streaming_turn_model_directly.py \
   --working-memory-seconds 2 \
   --video-fps 2 \
   --frame-cache-size 128 \
+  --audio-feature-device model \
+  --audio-right-padding-samples 0 \
   --decoder decord \
   --decoder-threads 1 \
   --max-open-readers 1 \