From 595b2dc13858dbd19ecfeecf212e71de857ebc68 Mon Sep 17 00:00:00 2001
From: pengzhendong <275331498@qq.com>
Date: Thu, 8 Jan 2026 19:33:32 +0800
Subject: [PATCH] add thrid party url

---
 README.md        | 4 ++++
 README_zh.md     | 4 ++++
 requirements.txt | 2 +-
 3 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index addb347..4ed2730 100644
--- a/README.md
+++ b/README.md
@@ -193,6 +193,10 @@ We evaluated Fun-ASR against other state-of-the-art models on open-source benchm
 <img src="images/compare_en.png" width="800" />
 </div>
 
+## Remarkable Third-Party Work
+
+- vLLM (GPU) Deployment Best Practices: An accelerated implementation of Fun-ASR using vLLM. [Repository](https://github.com/yuekaizhang/Fun-ASR-vllm/README.md)
+
 ## Citations
 
 ```bibtex
diff --git a/README_zh.md b/README_zh.md
index 25fb544..a83ff49 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -193,6 +193,10 @@ if __name__ == "__main__":
 <img src="images/compare_zh.png" width="800" />
 </div>
 
+## 优秀三方工作
+
+- vLLM (GPU) 最佳部署时间: 使用 vLLM 实现对 Fun-ASR 的加速. [Repository](https://github.com/yuekaizhang/Fun-ASR-vllm/README.md)
+
 ## Citations
 
 ```bibtex
diff --git a/requirements.txt b/requirements.txt
index e9a0d2f..d8a6816 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,7 +1,7 @@
 torch
 torchaudio
 transformers
-git+https://github.com/modelscope/FunASR
+funasr>=1.3.0
 zhconv
 whisper_normalizer
 pyopenjtalk-plus