Upload README.md with huggingface_hub

README.md

@@ -78,7 +78,7 @@ TurnWave beats the VAD baseline on every metric the harness reports.
 | `audio_eot_v2.onnx` | apache-2.0 | trained on smart-turn conversational clips |
 | `audio_eot.onnx` | cc-by-4.0 | Phase 4; trained on semantic-vad-eot (CC BY 4.0) |
 | `text_eot.int8.onnx` | cc-by-nc-sa-4.0 | trained on DailyDialog (CC BY-NC-SA 4.0) — non-commercial |
-| `fusion_eot.onnx` | cc-by-nc-sa-4.0 | contains the text branch, so it inherits the same terms |
+| `fusion_eot_v2.onnx` | cc-by-nc-sa-4.0 | fusion head retrained on conversational clips; contains the DailyDialog text branch, so it inherits its terms |
 
 Each model's licence follows its training data, so they differ. `audio_eot_v2` is
 the one the benchmark above measures and the one to use.
@@ -102,7 +102,7 @@ sits 0.2 s into the pause — where a live agent decides, and where eot-bench sc
 | audio_eot_v2 | fp32 | 4.81 ms | 14.0 MB |
 | audio_eot | fp32 | 4.52 ms | 14.0 MB |
 | text_eot | int8 | 5.02 ms | 7.2 MB |
-| fusion_eot | fp32 | 9.35 ms | 42.4 MB |
+| fusion_eot_v2 | fp32 | 38.19 ms | 42.4 MB |
 
 INT8 is not applied blindly: dynamic quantization rewrites MatMul, so it speeds up
 the transformer and *slows down* the conv-heavy branches. Each model ships whichever
@@ -129,9 +129,12 @@ not build could.
 - **Behind the production models**, and not a fair comparison: SmartTurn starts from
   a pretrained Whisper encoder, LiveKit's is a fine-tuned 0.5B LLM distilled from a
   7B teacher. This is 3.49M parameters from random initialisation.
-- **The fusion model is stale.** It was trained on the read-speech corpus, which the
-  benchmark showed to be the wrong task. The conversational corpus has no
-  transcripts, so retraining fusion needs ASR first.
+- **Fusion wins in-domain, not on the benchmark — measured, not guessed.** The
+  fused model reaches AP 0.959 vs 0.905 audio-only on held-out conversational
+  clips (Whisper transcripts), but on eot-bench the text branch scores AUC 0.485 —
+  chance — on real human-agent speech, so fusion there is the audio branch diluted
+  by noise (AUC 0.751 vs 0.770). Until a text branch trained on real spoken
+  dialogue exists, `audio_eot_v2` is the model to deploy.
 - **Non-commercial models included.** The text and fusion models derive from
   DailyDialog (CC BY-NC-SA 4.0). Only the audio branches are permissively licensed.