Upload README.md

README.md

@@ -14,15 +14,18 @@ datasets:
 
 These are hardware-agnostic FP32 generator state dictionaries for
 `DiffusionDITNetPartsFixedExpressions2PostNormInteraction2`. They were retrained
-on BEAT2 English with classifier-free condition dropout and selected with the
-released StreamTalk generation protocol plus the official EMAGE/PantoMatrix
-AESK FGD metric.
+on BEAT2 English with classifier-free condition dropout and selected with an
+accelerated H200 implementation of the StreamTalk generation procedure plus
+the official EMAGE/PantoMatrix AESK FGD metric.
 
 | File | Intended role | Epoch | CFG | Speaker2 FGD | All FGD |
 | --- | --- | ---: | ---: | ---: | ---: |
 | `streamtalk_speaker2_combined_e0946_cfg3.pt` | Speaker2 and combined | 946 | 3 | 0.378879 | 0.250287 |
 | `streamtalk_speaker_all_e0940_cfg3.pt` | All speakers | 940 | 3 | 0.424477 | 0.217672 |
 
+The combined selection score is
+`max(Speaker2 FGD / 0.383, All FGD / 0.293)`.
+
 The checkpoints contain 407 CPU FP32 tensors and 71,167,501 parameters. Both
 load strictly into the originally released StreamTalk model schema. H200,
 BF16, CUDA Graphs, and four-GPU execution were training/evaluation
@@ -34,6 +37,11 @@ was selected for engineering comparisons, but the final CFG=3 values have not
 been accepted against a direct B=1/M=1/full-window oracle. BC and DIV have not
 been re-evaluated for these retrained checkpoints.
 
+The published inference NPZ bytes were independently re-scored with the
+released scorer (metric batch 16): Speaker 2 `0.3788789702354345`; all speakers
+`0.21764184426140076`. These differ from the selection-time values by about
+`7e-15` and `2.97e-5`, respectively.
+
 Verify downloads before loading:
 
 ```bash