Update README.md

README.md

@@ -16,7 +16,7 @@ pipeline_tag: text-to-speech
 # GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS
 
 <div align="center">
-<img src=https://raw.githubusercontent.com/zai-org/GLM-V/refs/heads/main/assets/images/logo.svg  width="50%"/>
+<img src=https://raw.githubusercontent.com/zai-org/GLM-TTS/refs/heads/main/assets/images/logo.svg  width="50%"/>
 </div>
 
 <p align="center">
@@ -50,7 +50,7 @@ GLM-TTS follows a two-stage design:
 2.  **Stage 2 (Flow Matching):** A Flow model converts token sequences into high-quality mel-spectrograms, which are then turned into waveforms by a vocoder.
 
 <div align="center">
-  <img src="https://raw.githubusercontent.com/zai-org/GLM-V/refs/heads/main/assets/images/architecture.png" width="60%" alt="GLM-TTS Architecture">
+  <img src="https://raw.githubusercontent.com/zai-org/GLM-TTS/refs/heads/main/assets/images/architecture.png" width="60%" alt="GLM-TTS Architecture">
 </div>
 
 ### Reinforcement Learning Alignment