Refine MOSS-Audio backbone enhancement bullets

README.md

@@ -16,7 +16,6 @@ tags:
 - music-captioning
 - chord-recognition
 ---
-
 # MOSS-Music
 
 <p align="center">
@@ -35,6 +34,10 @@ tags:
 
 </div>
 
+<p align="center">
+  <a href="./README.md">English</a> | <a href="./README_zh.md">简体中文</a>
+</p>
+
 **MOSS-Music** is an open-source **music understanding model** from
 [MOSI.AI](https://mosi.cn/#hero), the [OpenMOSS team](https://www.open-moss.com/),
 and [Shanghai Innovation Institute](https://www.sii.edu.cn/). Built on the same
@@ -50,7 +53,8 @@ analysis.
 
 ## News
 
-* 2026.04.20: 🎉🎉🎉 We have released [MOSS-Music](https://huggingface.co/collections/OpenMOSS-Team/moss-music). 
+* 2026.04.27: 🎉🎉🎉 We have released [MOSS-Music](https://huggingface.co/OpenMOSS-Team/MOSS-Music-8B-Instruct).
+* 2026.04.27: 🎉🎉🎉 We have released [MOSS-Music-Data-Pipeline](https://github.com/wx9songs/MOSS-Music-Data-Pipeline) for large-scale music data annotation and processing.
 
 ## Contents
 
@@ -133,15 +137,16 @@ text generation framework, naturally supporting timestamped lyrics ASR,
 beat / downbeat localisation, section boundary detection, and long-song
 retrospective QA.
 
-On top of the MOSS-Audio backbone, MOSS-Music is:
+Building on the MOSS-Audio backbone, MOSS-Music is further enhanced through:
 
-- **continually pre-trained** on a large, diverse music corpus produced by
-  the standalone data pipeline repository
-  [`MOSS-Music-Data-Pipeline`](https://github.com/OpenMOSS/MOSS-Music-Data-Pipeline),
+- **continual pre-training** on a large, diverse music corpus produced by
+  the data annotation and processing pipeline
+  [`MOSS-Music-Data-Pipeline`](https://github.com/wx9songs/MOSS-Music-Data-Pipeline),
   with an emphasis on singing, lyrics, and full-song coverage;
-- **SFT-ed** on music-centric instruction data covering captioning, lyrics
-  ASR, chord / key / structural analysis, and long-form musical QA;
-- further **reasoning-tuned** for the *Thinking* variant.
+- **supervised fine-tuning (SFT)** on music-centric instruction data covering
+  captioning, lyrics ASR, chord / key / structural analysis, and long-form
+  musical QA;
+- additional **reasoning tuning** for the *Thinking* variant.
 
 ## Released Models
 
@@ -156,8 +161,8 @@ On top of the MOSS-Audio backbone, MOSS-Music is:
 
 The training data used by MOSS-Music is produced by an end-to-end pipeline
 that goes from raw audio to chat-formatted training samples. That pipeline is
-maintained in the standalone repository
-[`MOSS-Music-Data-Pipeline`](https://github.com/OpenMOSS/MOSS-Music-Data-Pipeline),
+available at
+[`MOSS-Music-Data-Pipeline`](https://github.com/wx9songs/MOSS-Music-Data-Pipeline),
 which hosts duration detection, MIR feature extraction, song-structure
 segmentation, lyrics ASR, metadata cleanup, and ALM-driven caption / query
 generation with models such as Qwen3-Omni, MusicFlamingo, and other
@@ -405,7 +410,7 @@ If you use the default `torch==2.9.1+cu128` runtime, installing
 - **MOSI.AI**: [https://mosi.cn](https://mosi.cn)
 - **OpenMOSS**: [https://www.open-moss.com](https://www.open-moss.com)
 - **MOSS-Audio (backbone)**: [https://github.com/OpenMOSS/MOSS-Audio](https://github.com/OpenMOSS/MOSS-Audio)
-- **MOSS-Music Data Pipeline**: [https://github.com/OpenMOSS/MOSS-Music-Data-Pipeline](https://github.com/OpenMOSS/MOSS-Music-Data-Pipeline)
+- **MOSS-Music Data Pipeline**: [https://github.com/wx9songs/MOSS-Music-Data-Pipeline](https://github.com/wx9songs/MOSS-Music-Data-Pipeline)
 
 ## LICENSE