Rename release to VOICE

README.md

@@ -5,13 +5,13 @@ tags:
 - spatial-transcriptomics
 - image-to-expression
 ---
-# VOICE-25M
+# Histology-Based Reconstruction of Single-Cell Transcriptomics through multimodal foundation models
 
 Predict spatial single-cell gene expression from H&E images using an image encoder, a spatial decoder, and a reference bank of cells with measured expression.
 
 ## Resources
 
-- **Code:** [GitHub](https://github.com/zchxhcz1/VOICE-25M)
+- **Code:** [GitHub](https://github.com/zchxhcz1/VOICE)
 - **Paper:** [arXiv:2608.08366](https://arxiv.org/abs/2608.08366)
 
 ## Installation
@@ -19,8 +19,8 @@ Predict spatial single-cell gene expression from H&E images using an image encod
 Use Python 3.10 or later and install a PyTorch build suitable for your hardware.
 
 ```bash
-git clone https://github.com/zchxhcz1/VOICE-25M.git
-cd VOICE-25M
+git clone https://github.com/zchxhcz1/VOICE.git
+cd VOICE
 pip install -r requirements.txt
 ```
 
@@ -37,13 +37,13 @@ hf auth login
 python - <<'PYTHON'
 from huggingface_hub import snapshot_download, hf_hub_download
 
-model_dir = "models/voice25m"
-snapshot_download("zchx/VOICE-25M", local_dir=model_dir)
+model_dir = "models/voice"
+snapshot_download("zchx/VOICE", local_dir=model_dir)
 hf_hub_download("MahmoodLab/UNI2-h", "pytorch_model.bin", local_dir=f"{model_dir}/uni2h")
 PYTHON
 ```
 
-See [model files](https://github.com/zchxhcz1/VOICE-25M/blob/main/weights/README.md) for the directory structure.
+See [model files](https://github.com/zchxhcz1/VOICE/blob/main/weights/README.md) for the directory structure.
 
 ## Prediction
 
@@ -52,7 +52,7 @@ Choose your own model, image and output locations in the commands below. Run pre
 ```bash
 python predict/predict.py \
   --image /path/to/slide.svs \
-  --release models/voice25m \
+  --release models/voice \
   --out results/prediction.h5ad
 ```
 
@@ -64,7 +64,7 @@ If the image does not contain physical resolution metadata, supply its actual mi
 
 ```bash
 python predict/predict.py --image /path/to/image.png --mpp 0.25 \
-  --release models/voice25m --out results/prediction.h5ad
+  --release models/voice --out results/prediction.h5ad
 ```
 
 `0.25` is an example. Use the resolution of your image. Prediction requires no measured expression or precomputed image features for the target slide.
@@ -103,6 +103,6 @@ The combined score is `beta * A + (1 - beta) * R`. Genes without reference cover
 
 ## Training
 
-[Training instructions](https://github.com/zchxhcz1/VOICE-25M/blob/main/docs/training.md) cover RNA embedding preparation, image–RNA alignment, expression training, reference-bank construction, and fitting fusion weights. Training requires paired H&E images and measured spatial expression.
+[Training instructions](https://github.com/zchxhcz1/VOICE/blob/main/docs/training.md) cover RNA embedding preparation, image–RNA alignment, expression training, reference-bank construction, and fitting fusion weights. Training requires paired H&E images and measured spatial expression.
 
-[Input formats](https://github.com/zchxhcz1/VOICE-25M/blob/main/docs/formats.md) describe image geometry, prepared-slide files, reference-bank inputs, and output coordinates.
+[Input formats](https://github.com/zchxhcz1/VOICE/blob/main/docs/formats.md) describe image geometry, prepared-slide files, reference-bank inputs, and output coordinates.