Improve model card for ReVerT (Think, Verbalize, then Speak) (#1)

- Improve model card for ReVerT (Think, Verbalize, then Speak) (86aba8ddaacd2b47e8424098328196d19afd50c1)


Co-authored-by: Niels Rogge <[email protected]>

README.md

@@ -1,199 +1,135 @@
 ---
 library_name: transformers
 tags: []
+pipeline_tag: text-generation
+license: other
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
+# Model Card for ReVerT (Think, Verbalize, then Speak)
 
+This model implements the **ReVerT** verbalizer, a core component of the **Think-Verbalize-Speak (TVS)** framework, introduced in the paper [Think, Verbalize, then Speak: Bridging Complex Thoughts and Comprehensible Speech](https://huggingface.co/papers/2509.16028).
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+Spoken dialogue systems increasingly employ large language models (LLMs) to leverage their advanced reasoning capabilities. However, direct application of LLMs in spoken communication often yields suboptimal results due to mismatches between optimal textual and verbal delivery. While existing approaches adapt LLMs to produce speech-friendly outputs, their impact on reasoning performance remains underexplored.
 
-### Model Sources [optional]
+The **Think-Verbalize-Speak** framework decouples reasoning from spoken delivery to preserve the full reasoning capacity of LLMs. Central to this method is **verbalizing**, an intermediate step that translates complex thoughts into natural, speech-ready text. This model, **ReVerT**, is a latency-efficient verbalizer based on incremental and asynchronous summarization. Experiments across multiple benchmarks show that this method enhances speech naturalness and conciseness with minimal impact on reasoning.
 
-<!-- Provide the basic links for the model. -->
+-   **Developed by:** Sang Hoon Woo, Sehun Lee, Kang-wook Kim, Gunhee Kim
+-   **Model type:** Qwen2ForCausalLM fine-tuned as a verbalizer for text generation.
+-   **Language(s) (NLP):** English
+-   **License:** No explicit license found in the provided sources, please refer to the original project for license information.
+-   **Finetuned from model:** Qwen/Qwen2.5-3B-Instruct
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+### Model Sources
 
-## Uses
+-   **Repository:** https://github.com/yhytoto12/TVS-ReVerT
+-   **Paper:** https://huggingface.co/papers/2509.16028
+-   **Project Page:** https://yhytoto12.github.io/TVS-ReVerT
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+## 💥 News
 
-### Direct Use
+-   `2025.09.22` 🚀 We released our paper on [arXiv](https://arxiv.org/abs/2509.16028).
+-   `2025.09.19` 🔥 We released the training code, datasets, models, and interactive demo.
+-   `2025.08.21` 🎉 Our paper got accepted to **EMNLP 2025**!
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+## 👀 Introduction
 
-[More Information Needed]
+<p align="center">
+    <img src="https://github.com/yhytoto12/TVS-ReVerT/raw/main/assets/tvs-framework.png" width="100%"> <br>
+</p>
 
-### Downstream Use [optional]
+## Uses
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+### Direct Use
 
-[More Information Needed]
+This model is intended to be used as a "verbalizer" within a spoken dialogue system. Its primary purpose is to convert complex, often structured, "thoughts" generated by a Large Language Model into natural, concise, and speech-ready text that can then be fed into a Text-to-Speech (TTS) system. This ensures that the full reasoning capacity of the LLM is preserved while optimizing the output for verbal delivery.
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+This model is not designed for direct end-to-end reasoning or speech synthesis. It specifically focuses on the text-to-text verbalization step. It should not be used as a standalone reasoning engine, nor should its outputs be directly consumed by users without further processing (e.g., TTS).
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
+-   The model's performance and potential biases are influenced by the underlying base LLM (Qwen2.5) and the characteristics of the training datasets (GSM8k, 2WikiMultihopQA).
+-   While designed for naturalness and conciseness, the quality of verbalization might vary depending on the complexity and domain of the input "thoughts."
+-   The model's effectiveness is contingent on its integration into a larger Think-Verbalize-Speak framework, including a robust "Think" model and a speech synthesizer.
 
 ### Recommendations
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+Users should be aware of these limitations and consider the potential for biases inherited from the training data and base models. Thorough evaluation in target deployment scenarios is recommended, especially for sensitive applications.
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
-
-[More Information Needed]
+You can try the interactive demo for the Think-Verbalize-Speak framework, which utilizes this ReVerT verbalizer. The setup instructions from the GitHub repository are provided below.
 
-## Training Details
+First, set up the environment:
+```bash
+git clone https://github.com/yhytoto12/TVS-ReVerT.git
+cd TVS-ReVerT
+conda create -n tvs python=3.10
+conda activate tvs
+pip install -r requirements.txt
 
-### Training Data
+# Use flash attention for faster training and inference (optional)
+pip install -U flash-attn --no-build-isolation
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+# For deepspeed training (optional)
+pip install deepspeed
+```
 
-[More Information Needed]
+Then, run the interactive demo using one of the following commands:
 
-### Training Procedure
+*   **Using OpenAI models as the Think model:**
+    ```bash
+    python demo.py --think_model <openai_model_name> --verbalize_model yhytoto12/revert-Qwen2.5-3B --use_openai_think
+    ```
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+*   **Using local models as the Think model (with vLLM backend):**
+    First, start the vLLM backend in one terminal:
+    ```bash
+    python -m vllm.entrypoints.transformers --model Qwen/Qwen2.5-7B-Instruct --host 0.0.0.0 --port 8000
+    ```
+    Then, run the demo in a separate terminal:
+    ```bash
+    python demo.py --think_model Qwen/Qwen2.5-7B-Instruct --verbalize_model yhytoto12/revert-Qwen2.5-3B --vllm_url http://localhost:8000/v1
+    ```
 
-#### Preprocessing [optional]
+## Training Details
 
-[More Information Needed]
+### Training Data
 
+The ReVerT verbalizer models were trained using specialized datasets containing thought-verbalization pairs. These datasets are available on Hugging Face:
 
-#### Training Hyperparameters
+-   [🤗 **GSM8k**](https://huggingface.co/datasets/yhytoto12/tvs-gsm8k)
+-   [🤗 **2WikiMultihopQA**](https://huggingface.co/datasets/yhytoto12/tvs-2wikimultihopqa)
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+### Training Procedure
 
-#### Speeds, Sizes, Times [optional]
+Training scripts for the various models discussed in the paper, including the ReVerT verbalizer, are provided in the [GitHub repository](https://github.com/yhytoto12/TVS-ReVerT) under the `scripts/` directory. The default base model for training is `Qwen/Qwen2.5-3B-Instruct`, which can be modified within the training scripts.
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+Example script for training the TVS(ReVerT) Model:
+```bash
+bash scripts/train_tvs_revert.sh -g <num_gpus>
+```
 
-[More Information Needed]
+#### Training Hyperparameters
+Specific training hyperparameters would be found within the `scripts/train_tvs_revert.sh` script and associated configuration files in the GitHub repository.
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
+The paper details experiments across multiple benchmarks showing that the Think-Verbalize-Speak method, including ReVerT, enhances speech naturalness and conciseness with minimal impact on reasoning performance. Refer to the [paper](https://huggingface.co/papers/2509.16028) for comprehensive evaluation protocols and results.
 
-## Model Card Contact
+## Citation
 
-[More Information Needed]
+If you find our project useful for your research and applications, please kindly cite using this BibTeX:
+```bibtex
+@inproceedings{tvs2025@woolee,
+  title={Think, Verbalize, then Speak: Bridging Complex Thoughts and Comprehensible Speech},
+  author={Sang Hoon Woo, Sehun Lee, Kang-wook Kim, Gunhee Kim},
+  booktitle={Proceedings of the EMNLP 2025},
+  year={2025}
+}
+```