Update README.md

README.md

@@ -77,4 +77,40 @@ Evaluated on `seed-tts-eval`. **GLM-TTS_RL** achieves the lowest Character Error
 ```bash
 git clone [https://github.com/zai-org/GLM-TTS.git](https://github.com/zai-org/GLM-TTS.git)
 cd GLM-TTS
-pip install -r requirements.txt
+pip install -r requirements.txt
+```
+
+#### Command Line Inference
+
+```bash
+python glmtts_inference.py \
+    --data=example_zh \
+    --exp_name=_test \
+    --use_cache \
+    # --phoneme # Add this flag to enable phoneme capabilities.
+```
+
+#### Using Pre-trained Script
+
+```bash
+bash glmtts_inference.sh
+```
+
+## 🙏 Acknowledgments & Citation
+
+We thank the following open-source projects for their support:
+
+- [CosyVoice](https://github.com/FunAudioLLM/CosyVoice) - Providing frontend processing framework and high-quality vocoder
+- [Llama](https://github.com/meta-llama/llama) - Providing basic language model architecture
+- [Vocos](https://github.com/charactr-platform/vocos) - Providing high-quality vocoder
+- [GRPO-Zero](https://github.com/policy-gradient/GRPO-Zero) - Reinforcement learning algorithm implementation inspiration
+
+If you use GLM-TTS in your research, please cite:
+
+```bibtex
+@misc{glmtts2025,
+  title={GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning},
+  author={CogAudio Group Members},
+  year={2025},
+  publisher={Zhipu AI Inc}
+}