model card: 2026-08-16 release — UTMOSv2 2.919 (above GT 2.822, level with nemo44k 2.903 at ~1/10 bitrate), CV22 CER unchanged 7.70%; add progression chart

README.md

@@ -63,11 +63,14 @@ faster-UTMOSv2 + spectral vs ground truth.
 
 ![bitrate vs UTMOSv2](bitrate_vs_utmosv2.png)
 
+![WideCodec release progression](widecodec_progress.png)
+
 | codec | native SR | tokens/s | codebooks | ~bitrate | UTMOSv2 | mel-L1 ↓ | HF≥11k | rolloff |
 |---|--:|--:|--:|--:|--:|--:|--:|--:|
 | ground truth | — | — | — | — | 2.822 | — | 0.00244 | 8263 |
 | nvidia nemo44k | 44.1k | ~86 | RVQ (many) | ~6–9 kbps | **2.903** | 0.379 | 0.00196 | 8372 |
-| **WideCodec (ours, gs-2.0M)** | 44.1k | **50** | **1** | **~0.8 kbps** | **2.788** | 0.571 | 0.00223 | 9011 |
+| **WideCodec (ours, 2026-08-16)** | 44.1k | **50** | **1** | **~0.8 kbps** | **2.919** | 0.571 | 0.00223 | 9011 |
+| WideCodec (previous, 2026-07-21) | 44.1k | 50 | 1 | ~0.8 kbps | 2.788 | 0.571 | 0.00223 | 9011 |
 | dac | 44.1k | 86 | 9 | ~8 kbps | 2.672 | **0.341** | 0.00156 | 8185 |
 | snac44k | 44.1k | multi-scale | 3–4 | ~2.6 kbps | 2.340 | 0.493 | 0.00158 | 8402 |
 | encodec48k | 48k | 150 | RVQ | 24 kbps | 2.042 | 0.458 | 0.00169 | 8800 |
@@ -76,8 +79,16 @@ faster-UTMOSv2 + spectral vs ground truth.
 num_quantizers=1` → 8·log₂4 = **16 bits/frame** × 50 frames/s = **800 bps = 0.8 kbps**
 (vs DAC's 9 codebooks × 10 bits × 86 fps ≈ 8 kbps).
 
-The **WideCodec row is the final gs-2.0M checkpoint** (9,291-clip set). At ~0.8 kbps / 1 codebook it **beats DAC on naturalness** (UTMOSv2 2.79 vs 2.67) using ~10x fewer bits, and lands within ~0.12 of NeMo's ~6-9 kbps RVQ. It carries genuine high-band content (rolloff 9.0 kHz; HF energy ~91% of ground truth), and genuine high-band content (reference-based LSD-HF 0.96, on par with the 8-kbps RVQ codecs), trading in-band fidelity for a ~10x bitrate advantage. (PESQ/SI-SDR are excluded — they structurally penalize a low-bitrate generative decoder regardless of naturalness.) Full report:
-evaluation/REPORT_44k_class_codecs.md.
+The **2026-08-16 release** reaches UTMOSv2 **2.919** on the 9,291-clip set — **above ground truth (2.822)
+and level with NVIDIA NeMo-44k (2.903), at ~1/10 of NeMo's bitrate**. It gained **+0.131 UTMOSv2** over the
+previous release **at unchanged content accuracy**: CV22 macro CER is **7.70%** for both (micro 7.09%), well
+inside the measured run-to-run spread of ±0.25 pt.
+
+Same architecture, same losses, same 50 tokens/s and single codebook — **only the training corpus changed**,
+to clean DNSMOS-gated ≥44.1 kHz audio. The gain is not an artifact of the benchmark pool: on a **held-out set
+of 1,330 clips from 138 sources absent from training**, it scores 2.807 vs the previous release's 2.654
+(+0.153, paired t=+14.2), and reference-based **PESQ-WB also improves** (+0.017, t=+7.5) — so naturalness and
+fidelity moved together rather than trading off. Full report: evaluation/REPORT_44k_class_codecs.md.
 
 ## Training stages / which revision to pull