Add `library_name` to metadata

This PR enhances the model card by adding `library_name: transformers` to the metadata.

This tag is justified by the `config.json` file, which specifies `"architectures": ["LlamaForCausalLM"]` and `"model_type": "llama"`. Llama-based models are typically integrated and used with the Hugging Face `transformers` library, enabling a predefined code snippet for users on the Hub.

No sample usage code snippet has been added as the provided GitHub README does not contain a suitable Python example for programmatic inference via a library.

README.md

@@ -2,6 +2,8 @@
 language:
 - zh
 - en
+license: mit
+pipeline_tag: text-to-speech
 tags:
 - llm
 - tts
@@ -9,8 +11,7 @@ tags:
 - voice-cloning
 - reinforcement-learning
 - flow-matching
-license: mit
-pipeline_tag: text-to-speech
+library_name: transformers
 ---
 
 # GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS
@@ -35,12 +36,12 @@ By introducing a **Multi-Reward Reinforcement Learning** framework, GLM-TTS sign
 
 ### Key Features
 
-* **Zero-shot Voice Cloning:** Clone any speaker's voice with just 3-10 seconds of prompt audio.
-* **RL-enhanced Emotion Control:** Utilizes a multi-reward reinforcement learning framework (GRPO) to optimize prosody and emotion.
-* **High-quality Synthesis:** Generates speech comparable to commercial systems with reduced Character Error Rate (CER).
-* **Phoneme-level Control:** Supports "Hybrid Phoneme + Text" input for precise pronunciation control (e.g., polyphones).
-* **Streaming Inference:** Supports real-time audio generation suitable for interactive applications.
-* **Bilingual Support:** Optimized for Chinese and English mixed text.
+*   **Zero-shot Voice Cloning:** Clone any speaker's voice with just 3-10 seconds of prompt audio.
+*   **RL-enhanced Emotion Control:** Utilizes a multi-reward reinforcement learning framework (GRPO) to optimize prosody and emotion.
+*   **High-quality Synthesis:** Generates speech comparable to commercial systems with reduced Character Error Rate (CER).
+*   **Phoneme-level Control:** Supports "Hybrid Phoneme + Text" input for precise pronunciation control (e.g., polyphones).
+*   **Streaming Inference:** Supports real-time audio generation suitable for interactive applications.
+*   **Bilingual Support:** Optimized for Chinese and English mixed text.
 
 ## System Architecture
 
@@ -73,7 +74,7 @@ Evaluated on `seed-tts-eval`. **GLM-TTS_RL** achieves the lowest Character Error
 ### Installation
 
 ```bash
-git clone [https://github.com/zai-org/GLM-TTS.git](https://github.com/zai-org/GLM-TTS.git)
+git clone https://github.com/zai-org/GLM-TTS.git
 cd GLM-TTS
 pip install -r requirements.txt
 ```
@@ -115,4 +116,4 @@ If you find GLM-TTS useful for your research, please cite our technical report:
       primaryClass={cs.SD},
       url={https://arxiv.org/abs/2512.14291}, 
 }
-}
+```