Fix MLT model card quickstarts and benchmark scope

Point all quickstarts at the MLT checkpoint, use deterministic decoding, select the Hugging Face hub explicitly, and clarify that the existing benchmark tables are family-level rather than MLT-specific.

README.md

@@ -57,11 +57,11 @@ This model is part of the **FunASR** ecosystem — one industrial-grade open-sou
 </div>
 
 
-# Fun-ASR
+# Fun-ASR-MLT-Nano-2512
 
 「[简体中文](README_zh.md)」|「English」
 
-Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab. It is trained on tens of millions of hours of real speech data, possessing powerful contextual understanding capabilities and industry adaptability. It supports low-latency real-time transcription and covers 31 languages. It excels in vertical domains such as education and finance, accurately recognizing professional terminology and industry expressions, effectively addressing challenges like "hallucination" generation and language confusion, achieving "clear hearing, understanding meaning, and accurate writing."
+Fun-ASR-MLT-Nano-2512 is the 800M-parameter multilingual checkpoint in the Fun-ASR family. It is trained on hundreds of thousands of hours of multilingual speech and supports 31 languages, with emphasis on East and Southeast Asian languages. For the Chinese, English, and Japanese checkpoint trained on tens of millions of hours, use [Fun-ASR-Nano-2512](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512).
 
 <div align="center">
 <img src="images/funasr-v2.png">
@@ -77,10 +77,7 @@ Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.
 
 </h4>
 
-Model Repository: [modelscope](https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-Nano-2512), [huggingface](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512)
-
-Online Experience:
-[ModelScope Community Space](https://modelscope.cn/studios/FunAudioLLM/Fun-ASR-Nano), [huggingface space](https://huggingface.co/spaces/FunAudioLLM/Fun-ASR-Nano)
+Model Repository: [modelscope](https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-MLT-Nano-2512), [huggingface](https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512)
 
 </div>
 
@@ -93,19 +90,17 @@ Online Experience:
 
 # What's New 🔥
 
-- 2025/12: [Fun-ASR-Nano-2512](https://modelscope.cn/models/FunAudioLLM/Fun-ASR-Nano-2512) is an end-to-end speech recognition large model trained on tens of millions of hours real speech data. It supports low-latency real-time transcription and covers 31 languages.
+- 2025/12: [Fun-ASR-MLT-Nano-2512](https://modelscope.cn/models/FunAudioLLM/Fun-ASR-MLT-Nano-2512) is the multilingual 800M checkpoint, trained on hundreds of thousands of hours of speech and covering 31 languages.
 - 2024/7: [FunASR](https://github.com/modelscope/FunASR) is a fundamental speech recognition toolkit that offers a variety of features, including speech recognition (ASR), Voice Activity Detection (VAD), Punctuation Restoration, Language Models, Speaker Verification, Speaker Diarization and multi-talker ASR.
 
 # Core Features 🎯
 
-**Fun-ASR** focuses on high-precision speech recognition, multi-language support, and industry customization capabilities
+**This repository hosts the MLT checkpoint.** Its supported-language scope differs from the standard Fun-ASR-Nano checkpoint.
 
-- **Far-field High-noise Recognition:** Deeply optimized for far-distance sound pickup and high-noise scenarios (such as conference rooms, in-vehicle environments, industrial sites, etc.), improving recognition accuracy to **93%**.
-- **Chinese Dialects and Regional Accents:**
-  - Supports **7 major dialects**: Wu, Cantonese, Min, Hakka, Gan, Xiang, Jin
-  - Covers **26 regional accents**: including Henan, Shaanxi, Hubei, Sichuan, Chongqing, Yunnan, Guizhou, Guangdong, Guangxi and more than 20 other regions
-- **Multi-language Free Speech:** Supports recognition of **31 languages**, with focused optimization on East and Southeast Asian languages, supporting free language switching and mixed recognition.
-- **Music Background Lyric Recognition:** Enhanced speech recognition performance under music background interference, supporting accurate recognition of lyric content in songs.
+- **31 languages:** Covers the languages listed in the model table above, with focused optimization on East and Southeast Asian languages.
+- **Compact multilingual model:** Uses approximately 800M parameters.
+- **Language control:** Accepts the language names shown in the inference example and supports multilingual recognition.
+- **Context controls:** The FunASR inference API exposes hotwords and inverse text normalization (ITN).
 
 # Environment Setup 🐍
 
@@ -134,9 +129,10 @@ from funasr import AutoModel
 
 
 def main():
-    model_dir = "FunAudioLLM/Fun-ASR-Nano-2512"
+    model_dir = "FunAudioLLM/Fun-ASR-MLT-Nano-2512"
     model = AutoModel(
         model=model_dir,
+        hub="hf",
         trust_remote_code=True,
         remote_code="./model.py",
         device="cuda:0",
@@ -148,26 +144,33 @@ def main():
         cache={},
         batch_size=1,
         hotwords=["开放时间"],
-        # 中文、英文、日文 for Fun-ASR-Nano-2512
         # 中文、英文、粤语、日文、韩文、越南语、印尼语、泰语、马来语、菲律宾语、阿拉伯语、
         # 印地语、保加利亚语、克罗地亚语、捷克语、��麦语、荷兰语、爱沙尼亚语、芬兰语、希腊语、
         # 匈牙利语、爱尔兰语、拉脱维亚语、立陶宛语、马耳他语、波兰语、葡萄牙语、罗马尼亚语、
         # 斯洛伐克语、斯洛文尼亚语、瑞典语 for Fun-ASR-MLT-Nano-2512
         language="中文",
         itn=True, # or False
+        llm_kwargs={"do_sample": False},
     )
     text = res[0]["text"]
     print(text)
 
     model = AutoModel(
         model=model_dir,
+        hub="hf",
         trust_remote_code=True,
         vad_model="fsmn-vad",
         vad_kwargs={"max_single_segment_time": 30000},
         remote_code="./model.py",
         device="cuda:0",
     )
-    res = model.generate(input=[wav_path], cache={}, batch_size=1)
+    res = model.generate(
+        input=[wav_path],
+        cache={},
+        batch_size=1,
+        language="中文",
+        llm_kwargs={"do_sample": False},
+    )
     text = res[0]["text"]
     print(text)
 
@@ -183,11 +186,16 @@ from model import FunASRNano
 
 
 def main():
-    model_dir = "FunAudioLLM/Fun-ASR-Nano-2512"
-    m, kwargs = FunASRNano.from_pretrained(model=model_dir, device="cuda:0")
+    model_dir = "FunAudioLLM/Fun-ASR-MLT-Nano-2512"
+    m, kwargs = FunASRNano.from_pretrained(
+        model=model_dir,
+        hub="hf",
+        device="cuda:0",
+    )
     m.eval()
 
     wav_path = f"{kwargs['model_path']}/example/zh.mp3"
+    kwargs["llm_kwargs"] = {"do_sample": False}
     res = m.inference(data_in=[wav_path], **kwargs)
     text = res[0][0]["text"]
     print(text)
@@ -208,7 +216,9 @@ if __name__ == "__main__":
 
 # Performance 📝
 
-We evaluated Fun-ASR against other state-of-the-art models on open-source benchmarks, Chinese dialect datasets, and industry-specific test sets. The results demonstrate that Fun-ASR achieves superior performance across various scenarios.
+> **Benchmark scope:** The tables below are Fun-ASR family results reproduced from the project report. They do not contain a column identified as `Fun-ASR-MLT-Nano-2512`, so they must not be interpreted as checkpoint-specific results for this MLT model. MLT per-language results will be added when a reproducible evaluation is published.
+
+The family-level comparison covers open-source benchmarks, Chinese dialect datasets, and industry-specific test sets.
 
 ### 1. Open-Source Dataset Performance (WER %)
 

README_zh.md

@@ -1,8 +1,8 @@
-# Fun-ASR
+# Fun-ASR-MLT-Nano-2512
 
 「简体中文」|「[English](README.md)」
 
-Fun-ASR 是通义实验室推出的端到端语音识别大模型，是基于数千万小时真实语音数据训练而成，具备强大的上下文理解能力与行业适应性，支持低延迟实时听写，并且覆盖 31 个语种。在教育、金融等垂直领域表现出色，能准确识别专业术语与行业表达，有效应对"幻觉"生成和语种混淆等挑战，实现"听得清、懂其意、写得准"。
+Fun-ASR-MLT-Nano-2512 是 Fun-ASR 系列中约 8 亿参数的多语言模型，基于数十万小时多语言语音训练，支持 31 种语言，并重点优化东亚与东南亚语种。基于数千万小时数据训练、面向中文、英文和日文的版本请使用 [Fun-ASR-Nano-2512](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512)。
 
 <div align="center">
 <img src="images/funasr-v2.png">
@@ -18,10 +18,7 @@ Fun-ASR 是通义实验室推出的端到端语音识别大模型，是基于数
 
 </h4>
 
-模型仓库：[modelscope](https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-Nano-2512)，[huggingface](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512)
-
-在线体验：
-[魔搭社区创空间](https://modelscope.cn/studios/FunAudioLLM/Fun-ASR-Nano)，[huggingface space](https://huggingface.co/spaces/FunAudioLLM/Fun-ASR-Nano)
+模型仓库：[modelscope](https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-MLT-Nano-2512)，[huggingface](https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512)
 
 </div>
 
@@ -34,19 +31,17 @@ Fun-ASR 是通义实验室推出的端到端语音识别大模型，是基于数
 
 # 最新动态 🔥
 
-- 2025/12: [Fun-ASR-Nano-2512](https://modelscope.cn/models/FunAudioLLM/Fun-ASR-Nano-2512) 是一款基于数千万小时真实语音数据训练的端到端语音识别大模型。它支持低延迟实时转写，并涵盖 31 种语言识别功能。
+- 2025/12: [Fun-ASR-MLT-Nano-2512](https://modelscope.cn/models/FunAudioLLM/Fun-ASR-MLT-Nano-2512) 是约 8 亿参数的多语言模型，基于数十万小时语音训练，覆盖 31 种语言。
 - 2024/7: [FunASR](https://github.com/modelscope/FunASR) 是一款功能全面的语音识别基础工具包，集成了多项核心功能，包括自动语音识别（ASR）、语音活动检测（VAD）、标点恢复、语言模型、说话人验证、说话人日志记录以及多说话人语音识别。
 
 # 核心特性 🎯
 
-**Fun-ASR** 专注于高精度语音识别、多语言支持和行业定制化能力
+**本仓库提供 MLT 多语言模型。** 它与标准版 Fun-ASR-Nano 的支持范围不同。
 
-- **远场高噪声识别：** 针对远距离拾音及高噪声场景（如会议室、车载环境、工业现场等）进行深度优化，识别准确率提升至 **93%**。
-- **中文方言与地方口音：**
-  - 支持 **7 大方言**：吴语、粤语、闽语、客家话、赣语、湘语、晋语
-  - 覆盖 **26 个地区口音**：包括河南、陕西、湖北、四川、重庆、云南、贵州、广东、广西等 20 多个地区
-- **多语言自由说：** 支持 **31 种语言**识别，重点优化东亚与东南亚语种，支持语种自由切换和混合识别。
-- **音乐背景歌词识别：** 强化在音乐背景干扰下的语音识别性能，支持对歌曲中歌词内容的精准识别。
+- **31 种语言：** 覆盖上方模型表列出的语言，并重点优化东亚与东南亚语种。
+- **紧凑多语言模型：** 参数量约 8 亿。
+- **语种控制：** 接受推理示例中列出的语种名称，并支持多语言识别。
+- **上下文控制：** FunASR 推理接口支持热词和逆文本标准化（ITN）。
 
 # 环境安装 🐍
 
@@ -75,9 +70,10 @@ from funasr import AutoModel
 
 
 def main():
-    model_dir = "FunAudioLLM/Fun-ASR-Nano-2512"
+    model_dir = "FunAudioLLM/Fun-ASR-MLT-Nano-2512"
     model = AutoModel(
         model=model_dir,
+        hub="hf",
         trust_remote_code=True,
         remote_code="./model.py",
         device="cuda:0",
@@ -89,26 +85,33 @@ def main():
         cache={},
         batch_size=1,
         hotwords=["开放时间"],
-        # 中文、英文、日文 for Fun-ASR-Nano-2512
         # 中文、英文、粤语、日文、韩文、越南语、印尼语、泰语、马来语、菲律宾语、阿拉伯语、
         # 印地语、保加利亚语、克罗地亚语、捷克语、丹麦语、荷兰语、爱沙尼亚语、芬兰语、希腊语、
         # 匈牙利语、爱尔兰语、拉脱维亚语、立陶宛语、马耳他语、波兰语、葡萄牙语、罗马尼亚语、
         # 斯洛伐克语、斯洛文尼亚语、瑞典语 for Fun-ASR-MLT-Nano-2512
         language="中文",
         itn=True, # or False
+        llm_kwargs={"do_sample": False},
     )
     text = res[0]["text"]
     print(text)
 
     model = AutoModel(
         model=model_dir,
+        hub="hf",
         trust_remote_code=True,
         vad_model="fsmn-vad",
         vad_kwargs={"max_single_segment_time": 30000},
         remote_code="./model.py",
         device="cuda:0",
     )
-    res = model.generate(input=[wav_path], cache={}, batch_size=1)
+    res = model.generate(
+        input=[wav_path],
+        cache={},
+        batch_size=1,
+        language="中文",
+        llm_kwargs={"do_sample": False},
+    )
     text = res[0]["text"]
     print(text)
 
@@ -124,11 +127,16 @@ from model import FunASRNano
 
 
 def main():
-    model_dir = "FunAudioLLM/Fun-ASR-Nano-2512"
-    m, kwargs = FunASRNano.from_pretrained(model=model_dir, device="cuda:0")
+    model_dir = "FunAudioLLM/Fun-ASR-MLT-Nano-2512"
+    m, kwargs = FunASRNano.from_pretrained(
+        model=model_dir,
+        hub="hf",
+        device="cuda:0",
+    )
     m.eval()
 
     wav_path = f"{kwargs['model_path']}/example/zh.mp3"
+    kwargs["llm_kwargs"] = {"do_sample": False}
     res = m.inference(data_in=[wav_path], **kwargs)
     text = res[0][0]["text"]
     print(text)
@@ -149,7 +157,9 @@ if __name__ == "__main__":
 
 # 性能评测 📝
 
-我们在开源基准数据集、中文方言测试集和工业测试集上，比较了 Fun-ASR 与其他模型的多语言语音识别性能。Fun-ASR 模型均具有明显的效果优势。
+> **评测范围说明：** 下表复用了项目报告中的 Fun-ASR 系列结果，其中没有名为 `Fun-ASR-MLT-Nano-2512` 的独立列，因此不能视为本 MLT checkpoint 的专属评测结果。待发布可复现的 MLT 分语言评测后再补充对应数据。
+
+以下系列级对比覆盖开源基准、中文方言数据集和工业测试集。
 
 ### 1. 开源数据集性能 (WER %)