Promote verified live Alpha comparison demo

MANIFEST.json

@@ -8,8 +8,8 @@
     "bytes": 1452
   },
   "README.md": {
-    "sha256": "ba521f65bf1aa59e1b393ceeda3fa1388c42cb34d00b6b2b7cb2453342d09d4e",
-    "bytes": 7907
+    "sha256": "a79d953d24d4ac445f967532e1772952f5bcdb3e9ebb01ace4f965f969a541d0",
+    "bytes": 8197
   },
   "TRAINING.md": {
     "sha256": "ec1704737915a41eeb866453f17a23e6f8c3ac395adf7c067996b5408ef5f81e",

README.md

@@ -24,12 +24,16 @@ text-to-speech. This release adds the completed 1,452-update RL adapter to
 [Humaneness Voice Large 1.3 Alpha](https://huggingface.co/laion/Humaneness-Voice-Large-1.3-Alpha).
 It is not a standalone model and does not duplicate the base weights.
 
-The new
-[Alpha comparison Space](https://laion-humaneness-voice-large-alpha-comparisons.static.hf.space/)
-is being updated for this release and its continuation. Meanwhile the
-[original verified comparison](https://laion-humaneness-voice-large-1-2-alpha-listening.static.hf.space/listening.html)
-contains the same 70 completed RL examples in the green FINAL RL column.
-That column's historical “1.3 + RL” label refers to the adapter released here.
+**[Open the live Alpha comparison demo](https://laion-humaneness-voice-large-alpha-comparisons.static.hf.space/)**
+to hear the same 70 cases from the 1.2 SFT baseline, 1.3 SFT baseline and this
+completed RL adapter side by side, with aggregate quality and emotion tables.
+All 215 players, including five speaker references, are publicly accessible.
+
+The [legacy comparison](https://laion-humaneness-voice-large-1-2-alpha-listening.static.hf.space/listening.html)
+is retained as a secondary link. Its historical “1.3 + RL” / green FINAL RL
+column refers to the adapter released here. The separately planned 20/40/40
+continuation will be an additional comparison column after completion, not a
+silent replacement of these released weights.
 
 ## What changed?