Add Audio-JEPA results and link the Transformers release

README.md

@@ -25,7 +25,7 @@ repository is needed.
 ## X-ARES results
 
 Scores on [X-ARES](https://arxiv.org/abs/2505.16369) (0–100, higher is better).
-BEST-RQ (Conformer), BEST-RQ (ViT),
+Audio-JEPA, BEST-RQ (Conformer), BEST-RQ (ViT),
 and all BEST-RQ-2 variants reported below are trained on the **same AudioSet
 split for 200,000 steps**. The pretrained baselines are shown for comparison.
 
@@ -34,6 +34,7 @@ split for 200,000 steps**. The pretrained baselines are shown for comparison.
 | data2vec | 50.62 | 23.24 | 15.41 | 37.83 | 29.76 | [facebook/data2vec-audio-base](https://huggingface.co/facebook/data2vec-audio-base) |
 | wav2vec 2.0 | 41.79 | 34.94 | 29.52 | 37.84 | 35.42 | [facebook/wav2vec2-large-100k-voxpopuli](https://huggingface.co/facebook/wav2vec2-large-100k-voxpopuli) |
 | Whisper | 49.19 | 38.67 | 28.61 | 42.75 | 38.82 | [openai/whisper-base](https://huggingface.co/openai/whisper-base) |
+| Audio-JEPA | 29.64 | 44.27 | 25.61 | 31.18 | 33.17 | [Audio-JEPA-base](https://huggingface.co/ltuncay/Audio-JEPA-base) |
 | BEST-RQ (Conformer) | 40.43 | 35.58 | 30.81 | 37.43 | 35.60 | Separate codebase |
 | BEST-RQ (ViT) | 32.87 | 41.62 | 34.50 | 34.88 | 36.33 | [BEST-RQ-ViT](https://huggingface.co/ltuncay/BEST-RQ-ViT) |
 | BEST-RQ-2 (Interspeech 2026) | 38.49 | 54.40 | 46.39 | 43.21 | 46.43 | [BEST-RQ-2](https://huggingface.co/ltuncay/BEST-RQ-2) |
@@ -43,7 +44,7 @@ split for 200,000 steps**. The pretrained baselines are shown for comparison.
 Global Mean averages all benchmark task scores. Mean of Means gives equal
 weight to the Speech, Music, and Environment category means.
 
-These are the research results reported in the [project README](https://github.com/LudovicTuncay/audio-embeddings/blob/bb88bf790b1dcf8251c6b38e7a4766534adf33d3/README.md), not a new benchmark run of the Transformers exports.
+Audio-JEPA scores were supplied by the author for [run `jp6l70l6`](https://wandb.ai/tuncay-ludovic/audio%20embeddings/runs/jp6l70l6). The remaining scores are reported in the [project README](https://github.com/LudovicTuncay/audio-embeddings/blob/bb88bf790b1dcf8251c6b38e7a4766534adf33d3/README.md). These are reported research results, not a new benchmark run of the Transformers exports.
 
 ## Model and training
 

export_manifest.json

@@ -38,7 +38,7 @@
   },
   "files": {
     "CODE_LICENSE": "8fe9e8b749cd4abedabcb3100df445db899e72192394d14cc2dbf24a40811af6",
-    "README.md": "96bc9111eda43b9ab7512624a5d0baf6f1e95949d5d4efcff0457bc916b4fc04",
+    "README.md": "e90a591ff29cacd941a00c678ecd9088796341cad39329544c64a7766ddfd67c",
     "adapters.py": "ca0f26826763c0e48b7508da732242bb83adfeb4814e389ed3fde93ad648c728",
     "config.json": "d37b85c37f17aa954f715b3b3d956c9ed18215ec6ea9565bcd4a403e9b51a134",
     "configuration_audio.py": "59f3a0b8db0df5af85e677ac33a4431595e9b2eff6d34c1e6a1778dd75a4568d",