Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
docs: add Qwen3-ASR to README and examples
游雁12e7e93ab504
diff --git a/README.md b/README.mdindex 91dc7eb1c..490ada144 100644--- a/README.md+++ b/README.md@@ -42,6 +42,7 @@- 2024/09/25:keyword spotting models are new supported. Supports fine-tuning and inference for four models: [fsmn_kws](https://modelscope.cn/models/iic/speech_sanm_kws_phone-xiaoyun-commands-online), [fsmn_kws_mt](https://modelscope.cn/models/iic/speech_sanm_kws_phone-xiaoyun-commands-online), [sanm_kws](https://modelscope.cn/models/iic/speech_sanm_kws_phone-xiaoyun-commands-offline), [sanm_kws_streaming](https://modelscope.cn/models/iic/speech_sanm_kws_phone-xiaoyun-commands-online).- 2024/07/04:[SenseVoice](https://github.com/FunAudioLLM/SenseVoice) is a speech foundation model with multiple speech understanding capabilities, including ASR, LID, SER, and AED.+- 2026/05/20: Added Qwen3-ASR (0.6B/1.7B) multi-language speech recognition models, supporting 52 languages with auto language detection. [usage](examples/industrial_data_pretraining/qwen3_asr).<details><summary>Full Changelog</summary>- 2024/07/01: Offline File Transcription Service GPU 1.1 released, optimize BladeDISC model compatibility issues; ref to ([docs](runtime/readme.md))@@ -125,6 +126,8 @@ FunASR has open-sourced a large number of pre-trained models on industrial data.| Whisper-large-v3-turbo <br> ([⭐](https://www.modelscope.cn/models/iic/Whisper-large-v3-turbo/summary) [🍀](https://github.com/openai/whisper) ) | speech recognition, with timestamps, non-streaming | multilingual | 809 M || Qwen-Audio <br> ([⭐](examples/industrial_data_pretraining/qwen_audio/demo.py) [🤗](https://huggingface.co/Qwen/Qwen-Audio) ) | audio-text multimodal models (pretraining) | multilingual | 8B || Qwen-Audio-Chat <br> ([⭐](examples/industrial_data_pretraining/qwen_audio/demo_chat.py) [🤗](https://huggingface.co/Qwen/Qwen-Audio-Chat) ) | audio-text multimodal models (chat) | multilingual | 8B |+| Qwen3-ASR-1.7B <br> ([⭐](examples/industrial_data_pretraining/qwen3_asr/demo.py) [🤗](https://huggingface.co/Qwen/Qwen3-ASR-1.7B) [🤖](https://modelscope.cn/models/Qwen/Qwen3-ASR-1.7B) ) | speech recognition, 52 languages, auto language detection | multilingual | 1.7B |+| Qwen3-ASR-0.6B <br> ([⭐](examples/industrial_data_pretraining/qwen3_asr/demo.py) [🤗](https://huggingface.co/Qwen/Qwen3-ASR-0.6B) [🤖](https://modelscope.cn/models/Qwen/Qwen3-ASR-0.6B) ) | speech recognition, 52 languages, auto language detection | multilingual | 0.6B || emotion2vec+large <br> ([⭐](https://modelscope.cn/models/iic/emotion2vec_plus_large/summary) [🤗](https://huggingface.co/emotion2vec/emotion2vec_plus_large) ) | speech emotion recongintion | 40000 hours | 300M |[//]: #diff --git a/README_zh.md b/README_zh.mdindex 162f9b5c1..22d937238 100644--- a/README_zh.md+++ b/README_zh.md@@ -42,6 +42,7 @@ FunASR 希望在语音识别的学术研究和工业应用之间架起一座桥- 2024/09/25:新增语音唤醒模型,支持[fsmn_kws](https://modelscope.cn/models/iic/speech_sanm_kws_phone-xiaoyun-commands-online), [fsmn_kws_mt](https://modelscope.cn/models/iic/speech_sanm_kws_phone-xiaoyun-commands-online), [sanm_kws](https://modelscope.cn/models/iic/speech_sanm_kws_phone-xiaoyun-commands-offline), [sanm_kws_streaming](https://modelscope.cn/models/iic/speech_sanm_kws_phone-xiaoyun-commands-online) 4 个模型的微调和推理。- 2024/07/04:[SenseVoice](https://github.com/FunAudioLLM/SenseVoice) 是一个基础语音理解模型,具备多种语音理解能力,涵盖了自动语音识别(ASR)、语言识别(LID)、情感识别(SER)以及音频事件检测(AED)。+- 2026/05/20: 新增 Qwen3-ASR(0.6B/1.7B)多语言语音识别模型,支持52种语言自动语言检测。[使用示例](examples/industrial_data_pretraining/qwen3_asr)。<details><summary>展开日志</summary>- 2024/07/01:中文离线文件转写服务 GPU 版本 1.1 发布,优化 bladedisc 模型兼容性问题;详细信息参阅([部署文档](runtime/readme_cn.md))@@ -125,6 +126,8 @@ FunASR 开源了大量在工业数据上预训练模型,您可以在[模型许| Whisper-large-v3-turbo <br> ([⭐](https://www.modelscope.cn/models/iic/Whisper-large-v3-turbo/summary) [🍀](https://github.com/openai/whisper) ) | 语音识别,带时间戳输出,非实时 | 多语言 | 809 M || Qwen-Audio <br> ([⭐](examples/industrial_data_pretraining/qwen_audio/demo.py) [🤗](https://huggingface.co/Qwen/Qwen-Audio) ) | 音频文本多模态大模型(预训练) | 多语言 | 8B || Qwen-Audio-Chat <br> ([⭐](examples/industrial_data_pretraining/qwen_audio/demo_chat.py) [🤗](https://huggingface.co/Qwen/Qwen-Audio-Chat) ) | 音频文本多模态大模型(chat 版本) | 多语言 | 8B |+| Qwen3-ASR-1.7B <br> ([⭐](examples/industrial_data_pretraining/qwen3_asr/demo.py) [🤗](https://huggingface.co/Qwen/Qwen3-ASR-1.7B) [🤖](https://modelscope.cn/models/Qwen/Qwen3-ASR-1.7B) ) | 语音识别,支持52种语言,自动语言检测 | 多语言 | 1.7B |+| Qwen3-ASR-0.6B <br> ([⭐](examples/industrial_data_pretraining/qwen3_asr/demo.py) [🤗](https://huggingface.co/Qwen/Qwen3-ASR-0.6B) [🤖](https://modelscope.cn/models/Qwen/Qwen3-ASR-0.6B) ) | 语音识别,支持52种语言,自动语言检测 | 多语言 | 0.6B || emotion2vec+large <br> ([⭐](https://modelscope.cn/models/iic/emotion2vec_plus_large/summary) [🤗](https://huggingface.co/emotion2vec/emotion2vec_plus_large) ) | 情感识别模型 | 40000 小时,4 种情感类别 | 300M |<a name="快速开始"></a>diff --git a/examples/industrial_data_pretraining/qwen3_asr/demo.py b/examples/industrial_data_pretraining/qwen3_asr/demo.pynew file mode 100644index 000000000..277508d97--- /dev/null+++ b/examples/industrial_data_pretraining/qwen3_asr/demo.py@@ -0,0 +1,37 @@+#!/usr/bin/env python3+# -*- encoding: utf-8 -*-+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.+# MIT License (https://opensource.org/licenses/MIT)++# To install requirements: pip install qwen-asr++from funasr import AutoModel++# Initialize Qwen3-ASR model+# hub: "ms" for ModelScope (default), "hf" for HuggingFace+model = AutoModel(+ model="Qwen/Qwen3-ASR-1.7B",+ hub="hf",+ device="cuda:0",+ dtype="bf16",+)++# Chinese speech recognition+res = model.generate(+ input="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav",+ language="Chinese",+)+print("Chinese:", res[0]["text"])++# English speech recognition+res = model.generate(+ input="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav",+ language="English",+)+print("English:", res[0]["text"])++# Auto language detection (supports 52 languages)+res = model.generate(+ input="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav",+)+print("Auto:", res[0]["text"], "| Language:", res[0].get("language", ""))diff --git a/examples/industrial_data_pretraining/qwen3_asr/demo_ms.py b/examples/industrial_data_pretraining/qwen3_asr/demo_ms.pynew file mode 100644index 000000000..b56741b0d--- /dev/null+++ b/examples/industrial_data_pretraining/qwen3_asr/demo_ms.py@@ -0,0 +1,22 @@+#!/usr/bin/env python3+# -*- encoding: utf-8 -*-+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.+# MIT License (https://opensource.org/licenses/MIT)++# To install requirements: pip install qwen-asr++from funasr import AutoModel++# Download from ModelScope (recommended for Chinese users)+model = AutoModel(+ model="Qwen/Qwen3-ASR-1.7B",+ hub="ms",+ device="cuda:0",+ dtype="bf16",+)++res = model.generate(+ input="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav",+ language="Chinese",+)+print(res[0]["text"])