Update README.md

README.md

@@ -8,16 +8,13 @@ pipeline_tag: text-to-audio
 
 **Foley-Omni: A Unified Multimodal Generation Model from Task-Level Audio Synthesis to Complete Video Soundtrack Generation**
 
-[GitHub Code](CODE_REPO_LINK) | [arXiv](ARXIV_LINK) | [Demo](DEMO_LINK)
+[GitHub Code](https://github.com/NJU-Speech/Foley-Omni) | [arXiv](https://arxiv.org/abs/2606.03672) | [Demo](https://ty0402.github.io/Foley-omni-Web/)
 
 ## Overview
 
 This repository packages the public inference checkpoint set for **Foley-Omni**.
 The release focuses on **Video-to-Soundtrack (V2ST)** generation, where the model jointly generates synchronized **speech**, **sound effects**, and **music** from a video and optional text prompt.
 
-The main model checkpoint in this release is an inference-only export from:
-
-- `ckpts/v3_fintune_final/checkpoints/model-epoch-000010.pth`
 
 ## Repository Contents
 
@@ -68,28 +65,3 @@ This repository redistributes a small subset of files from the following upstrea
 - **MMAudio**: audio VAE, vocoder, and Synchformer files
 
 Please refer to the original upstream repositories for their licenses, usage terms, and project details.
-
-## Quick Start
-
-Use the code repository for inference scripts, configs, examples, and feature extraction tools:
-
-- `inference_v2st.py`
-- `inference_v2st.yaml`
-- `examples/video_text_example.json`
-- `data_process/convert_memmap_to_npy.py`
-
-Download the packaged checkpoints with:
-
-```bash
-hf download CocoBro/Foley-Omni \
-  ckpts/Foley-Omni/v2st.pth \
-  ckpts/Wan2.2-TI2V-5B/models_t5_umt5-xxl-enc-bf16.pth \
-  ckpts/Wan2.2-TI2V-5B/google/umt5-xxl/special_tokens_map.json \
-  ckpts/Wan2.2-TI2V-5B/google/umt5-xxl/spiece.model \
-  ckpts/Wan2.2-TI2V-5B/google/umt5-xxl/tokenizer.json \
-  ckpts/Wan2.2-TI2V-5B/google/umt5-xxl/tokenizer_config.json \
-  ckpts/mmaudio/ext_weights/v1-16.pth \
-  ckpts/mmaudio/ext_weights/best_netG.pt \
-  ckpts/mmaudio/ext_weights/synchformer_state_dict.pth \
-  --local-dir .
-```