update model

README.md

@@ -16,16 +16,46 @@ pipeline_tag: text-generation
 
 # 🗣️ ssml-text2breaks-fr-lora
 
-This is the first-stage LoRA adapter for French SSML prosody generation, responsible for inserting symbolic pause markers (e.g., #250, #500) at linguistically appropriate positions in raw French text.
+# 🇫🇷 ssml-text2breaks-fr-lora — Symbolic Pause Prediction for French TTS
 
-This model is part of the SSML generation cascade described in the accepted paper:
+**ssml-text2breaks-fr-lora** is a LoRA adapter built on top of `Qwen/Qwen2.5-7B`, trained to predict **symbolic pause markers** (e.g., `#250`, `#500`) in raw French text. These symbolic tags indicate appropriate prosodic boundaries for speech synthesis systems.
 
-**"Improving French Synthetic Speech Quality via SSML Prosody Control"**
-Nassima Ould-Ouali, Éric Moulines – ICNLSP 2025 (Springer LNCS) [accepted].
+This model is the **first stage** in the cascaded pipeline presented in:
 
-It performs linguistically-aware break prediction, identifying phrasing and syntactic pause points, and outputs text marked with symbolic durations that can then be converted to valid SSML tags (e.g., <break time="250ms"/>) by the second-stage model.
+> **"Improving French Synthetic Speech Quality via SSML Prosody Control"**  
+> *Nassima Ould-Ouali, Éric Moulines* – ICNLSP 2025 (*Springer LNCS*, accepted)
+
+It is designed to be followed by [`ssml-break2ssml-fr-lora`](https://huggingface.co/nassimaODL/ssml-break2ssml-fr-lora), which converts symbolic markers into valid SSML tags.
+
+---
+
+## 🧩 Pipeline Overview
+
+| Stage | Model Name | Description |
+|-------|------------|-------------|
+| 1️⃣    | `ssml-text2breaks-fr-lora` | Predicts symbolic pause markers such as `#250`, `#500` |
+| 2️⃣    | `ssml-break2ssml-fr-lora` | Converts symbolic markers into `<break time="..."/>` SSML tags |
 
 ---
+
+## ✨ Example
+
+**Input:**
+
+```text
+Bonjour je m'appelle Bertrand Perier. Je suis avocat à la cour.
+
+```
+
+**Output**
+```text
+Bonjour#250 je m'appelle Bertrand Perier.#500 Je suis avocat à la cour.
+
+```
+
+
+
+
 ## Model Details
 
 - **Base Model**: Qwen/Qwen2.5-7B
@@ -33,7 +63,7 @@ It performs linguistically-aware break prediction, identifying phrasing and synt
 - **Task**: Text-to-SSML conversion with pause prediction
 - **Languages**: English, French (and others supported by base model)
 
-## Usage
+## 🚀 How to Use
 
 ```python
 import torch