Update model card evaluation formatting

README.md

@@ -25,7 +25,7 @@ pipeline_tag: audio-text-to-text
   <a href="https://arxiv.org/abs/2601.01554"><img src="https://img.shields.io/badge/arXiv-2601.01554-b31b1b?logo=arxiv"></a>
 </div>
 
-MOSS-Transcribe-Diarize is an end-to-end audio understanding model for long-form multi-speaker transcription, diarization, timestamps, and acoustic event awareness.
+MOSS-Transcribe-Diarize 0.9B is an end-to-end audio understanding model for long-form multi-speaker transcription, diarization, timestamps, and acoustic event awareness.
 
 Given an audio or video file, the model generates a compact speaker-aware transcript in one pass, including timestamps and anonymous speaker labels such as `[S01]`, `[S02]`, and beyond.
 
@@ -51,23 +51,20 @@ Given an audio or video file, the model generates a compact speaker-aware transc
 
 ## Introduction
 
-MOSS-Transcribe-Diarize turns real-world long-form audio into structured, speaker-aware transcripts in one pass. Instead of stitching together separate ASR and diarization systems, it jointly performs speech transcription and speaker diarization, producing time-aligned text with consistent speaker labels.
+MOSS-Transcribe-Diarize 0.9B turns real-world long-form audio into structured, speaker-aware transcripts in one pass. Instead of stitching together separate ASR and diarization systems, it jointly performs speech transcription and speaker diarization, producing time-aligned text with consistent speaker labels.
 
 The model is built for meetings, calls, podcasts, interviews, lectures, videos, and other long or messy multi-speaker recordings. It can also emit acoustic event annotations, giving downstream systems a richer view of what happened, who spoke, and when.
 
 Core capabilities:
 
-* **Long-form ASR**: Transcribes long audio and video recordings into text.
-* **Speaker-aware transcription**: Adds anonymous speaker labels to each speech segment.
-* **Speaker diarization**: Produces "who spoke when" output without a separate diarization pipeline.
-* **Timestamp prediction**: Generates segment-level start and end timestamps.
-* **Audio and video input**: Supports common audio files and video containers through the source package utilities.
-* **Promptable generation**: Supports custom transcription instructions and hotwords.
+* **Long-form transcription**: Converts long audio or video recordings into timestamped text.
+* **Speaker-aware diarization**: Assigns anonymous speaker labels such as `[S01]` and `[S02]` without a separate diarization pipeline.
+* **Promptable generation**: Supports custom transcription instructions, hotwords, and acoustic event annotations.
 
 ## Model Architecture
 
 <p align="center">
-  <img src="Model_Architecture.png" alt="MOSS-Transcribe-Diarize model architecture" width="900">
+  <img src="Model_Architecture.png" alt="MOSS-Transcribe-Diarize 0.9B model architecture" width="900">
 </p>
 
 | Component | Specification |
@@ -136,7 +133,7 @@ We evaluate MOSS-Transcribe-Diarize using three objective metrics: Character Err
       <td>22.75</td><td>27.43</td><td>4.68</td>
       <td>26.75</td><td>32.84</td><td>6.09</td>
       <td>-</td><td>-</td><td>-</td>
-      <td>8.62</td><td>14.73</td><td>6.11</td>
+      <td>8.62</td><td>14.73</td><td><u>6.11</u></td>
     </tr>
     <tr>
       <td style="white-space: nowrap;">VIBEVOICE ASR</td>
@@ -146,17 +143,17 @@ We evaluate MOSS-Transcribe-Diarize using three objective metrics: Character Err
       <td>14.59</td><td>42.54</td><td>27.94</td>
     </tr>
     <tr>
-      <td style="white-space: nowrap;"><b>MOSS Transcribe Diarize</b></td>
-      <td>14.84</td><td>15.83</td><td>0.99</td>
-      <td>24.86</td><td>22.17</td><td>-2.69</td>
-      <td>5.97</td><td>7.37</td><td><b>1.40</b></td>
-      <td>6.36</td><td>12.76</td><td>6.40</td>
+      <td style="white-space: nowrap;"><b>MOSS Transcribe Diarize 0.9B</b></td>
+      <td><u>14.84</u></td><td><u>15.83</u></td><td><u>0.99</u></td>
+      <td><u>24.86</u></td><td><u>22.17</u></td><td><u>-2.69</u></td>
+      <td><u>5.97</u></td><td><u>7.37</u></td><td><b>1.40</b></td>
+      <td><u>6.36</u></td><td><u>12.76</u></td><td>6.40</td>
     </tr>
     <tr>
       <td style="white-space: nowrap;"><b>MOSS Transcribe Diarize Pro</b></td>
       <td><b>13.78</b></td><td><b>14.02</b></td><td><b>0.24</b></td>
       <td><b>18.22</b></td><td><b>13.94</b></td><td><b>-4.27</b></td>
-      <td><b>4.46</b></td><td><b>6.97</b></td><td>2.51</td>
+      <td><b>4.46</b></td><td><b>6.97</b></td><td><u>2.51</u></td>
       <td><b>5.86</b></td><td><b>11.78</b></td><td><b>5.92</b></td>
     </tr>
   </tbody>
@@ -254,7 +251,7 @@ More prompt recipes are available in the GitHub repository: <https://github.com/
 
 ### Serve with vLLM and SGLang
 
-MOSS-Transcribe-Diarize supports vLLM serving through the OpenAI-compatible transcription API:
+MOSS-Transcribe-Diarize 0.9B supports vLLM serving through the OpenAI-compatible transcription API:
 
 ```bash
 pip install vllm
@@ -338,11 +335,11 @@ In this format:
 
 ## License
 
-MOSS-Transcribe-Diarize is licensed under the Apache License 2.0.
+MOSS-Transcribe-Diarize 0.9B is licensed under the Apache License 2.0.
 
 ## Citation
 
-If you use MOSS-Transcribe-Diarize, please cite the technical report:
+If you use MOSS-Transcribe-Diarize 0.9B, please cite the technical report:
 
 ```bibtex
 @misc{moss_transcribe_diarize_2026,