Upload README.md with huggingface_hub

README.md

@@ -12,17 +12,20 @@ tags:
 Released checkpoints for [wavepainter](https://github.com/pujariaditya/wavepainter),
 a masked-span speech editor.
 
-On the English `full` split of Ming-Freeform-Audio-Edit, against Ren et al.
-([arXiv:2602.00560](https://arxiv.org/abs/2602.00560), the row with GRPO):
+`phase2-hubert-child` is the released model and the artifact of record: phase two
+as trained, and the checkpoint every number in the paper comes from. On the
+English `full` split of Ming-Freeform-Audio-Edit, against Ren et al.
+([arXiv:2602.00560](https://arxiv.org/abs/2602.00560), the row with GRPO), scored
+with oracle edit spans taken from the transcript diff:
 
-| edit type | metric | Ren et al. | wavepainter (a=0.85) | wavepainter (a=0.70) |
-|---|---|---|---|---|
-| substitution | WER | 4.41 | **3.063** | 3.381 |
-| insertion | WER | 4.97 | 4.128 | **3.817** |
-| deletion | WER | **6.88** | 9.136 | 9.525 |
-| substitution | SIM | 0.78 | **0.943** | **0.943** |
-| insertion | SIM | 0.82 | **0.961** | 0.960 |
-| deletion | SIM | 0.78 | **0.918** | **0.918** |
+| edit type | metric | Ren et al. | wavepainter |
+|---|---|---|---|
+| substitution | WER | 4.41 | **3.479** |
+| insertion | WER | 4.97 | **4.400** |
+| deletion | WER | **6.88** | 9.697 |
+| substitution | SIM | 0.78 | **0.943** |
+| insertion | SIM | 0.82 | **0.961** |
+| deletion | SIM | 0.78 | **0.918** |
 
 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
@@ -31,26 +34,34 @@ 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
+benchmark. Over the audio the edit does not touch, PESQ is 4.090 / 4.083 / 4.079
 for substitution / insertion / deletion, against 4.351 for copy-synthesis with no
 edit at all.
 
-### Which checkpoint to use
+### The interpolated variants
 
-`phase2-hubert-a085` is the released model and the artifact of record.
-`phase2-hubert-a070` is the same phase-2 child interpolated back toward the
-phase-1 base at a lower coefficient: it is better on insertion (3.82 vs 4.13
-WER) and worse on substitution and deletion. The interpolation coefficient has
-no single optimum across edit types, so both are published rather than one
-being presented as strictly better. Speaker similarity is identical between
-them -- the coefficient moves only the diffusion denoiser.
+Two earlier releases interpolate the phase-two child back toward the phase-1 base,
+which moves the diffusion denoiser only. They are published because the paper's
+first version reported them and anyone who fetched them should keep working; the
+paper no longer reports either.
+
+| | substitution | insertion | deletion |
+|---|---|---|---|
+| `phase2-hubert-child` (released) | **3.479** | 4.400 | **9.697** |
+| `phase2-hubert-a085` | 3.063 | 4.128 | 9.136 |
+| `phase2-hubert-a070` | 3.381 | **3.817** | 9.525 |
+
+WER, lower is better. The coefficient has no single optimum across edit types, so
+both variants are kept rather than one being presented as strictly better.
+Speaker similarity is 0.943 / 0.961 / 0.918 for all three except insertion at
+a=0.70, which is 0.960.
 
 ## Files
 
-- `phase1-base/` — the phase-1 editor. Start here to re-run phase 2 (~1 GPU-hour).
-- `phase2-hubert-a085/` — the released model, and the artifact of record.
-- `phase2-hubert-a070/` — the same child at a lower interpolation coefficient;
-  better insertion, worse substitution and deletion.
+- `phase1-base/` -- the phase-1 editor. Start here to re-run phase 2 (~1 GPU-hour).
+- `phase2-hubert-child/` -- the released model, and the artifact of record.
+- `phase2-hubert-a085/` -- an earlier release, interpolated at 0.85.
+- `phase2-hubert-a070/` -- the same, at 0.70.
 
 ## Use