Feature Day-2 ONNX repos (bass/other/vocals + bag)

README.md

@@ -30,8 +30,12 @@ browser.
 | [htdemucs-ft-drums-pytorch](https://huggingface.co/StemSplitio/htdemucs-ft-drums-pytorch) | Model | ✅ live | Drums specialist sub-model. ~160 MB, ~2.6× faster than the full bag, identical drum SDR. For drum extraction, beat transcription, sample-pack creation. |
 | [htdemucs-ft-bass-pytorch](https://huggingface.co/StemSplitio/htdemucs-ft-bass-pytorch) | Model | ✅ live | Bass specialist sub-model. Same speed/quality story as drums. For bassline transcription and mix rebalancing. |
 | [htdemucs-ft-other-pytorch](https://huggingface.co/StemSplitio/htdemucs-ft-other-pytorch) | Model | ✅ live | "Other" / instrumental specialist. Pair with the vocals model for karaoke, sample-flipping, music-bed extraction. |
-| [htdemucs-ft-drums-onnx](https://huggingface.co/StemSplitio/htdemucs-ft-drums-onnx) | Model | ✅ live | **First working ONNX export of HT-Demucs on the Hub.** Runs in `onnxruntime` CPU/CoreML/CUDA/DirectML with no PyTorch required. 1.31× faster than PyTorch CPU. For iOS/Android/web deployment. |
-| Remaining stem ONNX exports + INT8 quant | Models | 🚧 in progress | bass/other/vocals ONNX + mobile-quantized variants — Day 2-3 of the ONNX project. |
+| [htdemucs-ft-onnx](https://huggingface.co/StemSplitio/htdemucs-ft-onnx) | Model | ✅ live | **First complete ONNX export of HT-Demucs FT on the Hub.** All 4 specialists + numpy bag aggregator in one repo. Runs in `onnxruntime` CPU/CoreML/CUDA/DirectML, no PyTorch required. |
+| [htdemucs-ft-drums-onnx](https://huggingface.co/StemSplitio/htdemucs-ft-drums-onnx) | Model | ✅ live | Drums specialist ONNX. ~75% smaller / 4× faster than the full bag if you only need drums. |
+| [htdemucs-ft-bass-onnx](https://huggingface.co/StemSplitio/htdemucs-ft-bass-onnx) | Model | ✅ live | Bass specialist ONNX. For bassline transcription, mix rebalancing. |
+| [htdemucs-ft-other-onnx](https://huggingface.co/StemSplitio/htdemucs-ft-other-onnx) | Model | ✅ live | Other/instrumental specialist ONNX. Pair with vocals ONNX for karaoke. |
+| [htdemucs-ft-vocals-onnx](https://huggingface.co/StemSplitio/htdemucs-ft-vocals-onnx) | Model | ✅ live | **#1 open-source vocal SDR** (9.19 dB) as ONNX. The defensible centerpiece for iOS/Android vocal-removal apps. |
+| CoreML EP profiling + INT8 quantization | Models | 🚧 in progress | Mobile-quantized variants and CoreML benchmarks — Day 3 of the ONNX project. |
 | Demo Space | Space | 🚧 in progress | Upload a track, pick a model, compare separations in your browser. |
 | Live leaderboard Space | Space | 📋 planned | Community-submittable, continuously evaluated leaderboard for stem separation. |