Upload README.md with huggingface_hub

README.md

@@ -23,13 +23,17 @@ On the English `full` split of Ming-Freeform-Audio-Edit, against Ren et al.
 | substitution | SIM | 0.78 | **0.943** | **0.943** |
 | insertion | SIM | 0.82 | **0.961** | 0.960 |
 | deletion | SIM | 0.78 | **0.918** | **0.918** |
-| substitution | DNSMOS | **3.11** | 2.931 | 2.925 |
-| insertion | DNSMOS | **3.18** | 2.905 | 2.908 |
-| deletion | DNSMOS | **3.09** | 2.938 | 2.935 |
 
-Five of the nine numbers they report improve on theirs: substitution and
-insertion WER, and speaker similarity on all three edit types. We do not beat
-them on deletion WER or on DNSMOS anywhere -- see the repository's Limitations.
+Five of the six compared numbers improve on theirs: substitution and insertion
+WER, and speaker similarity on all three edit types. We do not beat them on
+deletion WER -- see the repository's Limitations, which also locates most of that
+gap with a ground-truth waveform splice.
+
+Signal quality is reported full-reference, since a no-reference MOS estimator
+rates the untouched original recordings below synthesised output on this
+benchmark. Over the audio the edit does not touch, PESQ is 4.089 / 4.083 / 4.076
+for substitution / insertion / deletion, against 4.351 for copy-synthesis with no
+edit at all.
 
 ### Which checkpoint to use