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
Refresh public FunASR entrypoint links (#3361)
zhifu gaoe8bdb884dcfc
diff --git a/model_zoo/modelscope_models.md b/model_zoo/modelscope_models.mdindex 7a06c2999..cb2e354f3 100644--- a/model_zoo/modelscope_models.md+++ b/model_zoo/modelscope_models.md@@ -17,7 +17,7 @@ Here we provided several pretrained models on different datasets. The details of| Model Name | Language | Training Data | Vocab Size | Parameter | Offline/Online | Notes ||:--------------------------------------------------------------------------------------------------------------------------------------------------:|:--------:|:--------------------------------:|:----------:|:---------:|:--------------:|:--------------------------------------------------------------------------------------------------------------------------------|| [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Duration of input wav <= 20s |-| [Paraformer-large-long](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Which would deal with arbitrary length input wav |+| [Paraformer-large-long](https://www.modelscope.cn/models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Which would deal with arbitrary length input wav || [Paraformer-large-en-long](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) | EN | Alibaba Speech Data (50000hours) | 10020 | 220M | Offline | Which would deal with arbitrary length input wav || [Paraformer-large-Spk](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Supporting speaker diarizatioin for ASR results based on paraformer-large-long || [Paraformer-large-contextual](https://www.modelscope.cn/models/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Which supports the hotword customization based on the incentive enhancement, and improves the recall and precision of hotwords. |diff --git a/model_zoo/modelscope_models_zh.md b/model_zoo/modelscope_models_zh.mdindex 14d49be8e..9dccebb44 100644--- a/model_zoo/modelscope_models_zh.md+++ b/model_zoo/modelscope_models_zh.md@@ -17,7 +17,7 @@| 模型名字 | 语言 | 训练数据 | 词典大小 | 参数量 | 非实时/实时 | 备注 ||:--------------------------------------------------------------------------------------------------------------------------------------------------:|:--------:|:---------------------:|:-----------------:|:----:|:-------:|:---------------------------|| [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | 中文和英文 | 阿里巴巴语音数据(60000小时) | 8404 | 220M | 非实时 | 输入wav文件持续时间不超过20秒 |-| [Paraformer-large长音频版本](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | 中文和英文 | 阿里巴巴语音数据(60000小时) | 8404 | 220M | 非实时 | 能够处理任意长度的输入wav文件 |+| [Paraformer-large长音频版本](https://www.modelscope.cn/models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | 中文和英文 | 阿里巴巴语音数据(60000小时) | 8404 | 220M | 非实时 | 能够处理任意长度的输入wav文件 || [Paraformer-large-en长音频版本](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) | 英文 | 阿里巴巴语音数据(50000小时) | 10020 | 220M | 非实时 | 能够处理任意长度的输入wav文件 || [Paraformer-large-Spk](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) | 中文和英文 | 阿里巴巴语音数据(60000小时) | 8404 | 220M | 非实时 | 在长音频功能的基础上添加说话人识别功能 || [Paraformer-large热词](https://www.modelscope.cn/models/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/summary) | 中文和英文 | 阿里巴巴语音数据(60000小时) | 8404 | 220M | 非实时 | 基于激励增强的热词定制支持,可以提高热词的召回率和准确率,输入wav文件持续时间不超过20秒 |diff --git a/model_zoo/readme.md b/model_zoo/readme.mdindex 8feab2cf0..724eb29b3 100644--- a/model_zoo/readme.md+++ b/model_zoo/readme.md@@ -22,7 +22,7 @@ FunASR has open-sourced a large number of pre-trained models on industrial data.| Model Name | Task Details | Training Data | Parameters ||:------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------:|:--------------------------------:|:----------:|-| paraformer-zh <br> ([⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) [🤗]() ) | speech recognition, with timestamps, non-streaming | 60000 hours, Mandarin | 220M |+| paraformer-zh <br> ([⭐](https://www.modelscope.cn/models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) [🤗]() ) | speech recognition, with timestamps, non-streaming | 60000 hours, Mandarin | 220M || paraformer-zh-spk <br> ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) [🤗]() ) | speech recognition with speaker diarization, with timestamps, non-streaming | 60000 hours, Mandarin | 220M || <nobr>paraformer-zh-online <br> ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [🤗]() )</nobr> | speech recognition, streaming | 60000 hours, Mandarin | 220M || paraformer-en <br> ( [⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) [🤗]() ) | speech recognition, with timestamps, non-streaming | 50000 hours, English | 220M |diff --git a/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-en.sh b/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-en.shindex 1d570aa2d..793096445 100644--- a/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-en.sh+++ b/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-en.sh@@ -27,7 +27,7 @@ SUDO_CMD="sudo"DEFAULT_DOCKER_OFFLINE_CPU_EN_LISTS_OSS="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/docker_lists/docker_offline_cpu_en_lists"-DEFAULT_DOCKER_OFFLINE_CPU_EN_LISTS_GIT="https://raw.githubusercontent.com/alibaba-damo-academy/FunASR/main/runtime/docs/docker_offline_cpu_en_lists"+DEFAULT_DOCKER_OFFLINE_CPU_EN_LISTS_GIT="https://raw.githubusercontent.com/modelscope/FunASR/main/runtime/docs/docker_offline_cpu_en_lists"DEFAULT_DOCKER_IMAGE_LISTS=$DEFAULT_DOCKER_OFFLINE_CPU_EN_LISTS_OSSDEFAULT_FUNASR_DOCKER_URL="registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr"DEFAULT_FUNASR_RUNTIME_RESOURCES="funasr-runtime-resources"diff --git a/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh b/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.shindex 4a70f7ab4..218be1a93 100644--- a/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh+++ b/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh@@ -27,7 +27,7 @@ SUDO_CMD="sudo"DEFAULT_DOCKER_OFFLINE_CPU_ZH_LISTS_OSS="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/docker_lists/docker_offline_cpu_zh_lists"-DEFAULT_DOCKER_OFFLINE_CPU_ZH_LISTS_GIT="https://raw.githubusercontent.com/alibaba-damo-academy/FunASR/main/runtime/docs/docker_offline_cpu_zh_lists"+DEFAULT_DOCKER_OFFLINE_CPU_ZH_LISTS_GIT="https://raw.githubusercontent.com/modelscope/FunASR/main/runtime/docs/docker_offline_cpu_zh_lists"DEFAULT_DOCKER_IMAGE_LISTS=$DEFAULT_DOCKER_OFFLINE_CPU_ZH_LISTS_OSSDEFAULT_FUNASR_DOCKER_URL="registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr"DEFAULT_FUNASR_RUNTIME_RESOURCES="funasr-runtime-resources"diff --git a/runtime/deploy_tools/funasr-runtime-deploy-online-cpu-zh.sh b/runtime/deploy_tools/funasr-runtime-deploy-online-cpu-zh.shindex 270191aea..86934309e 100644--- a/runtime/deploy_tools/funasr-runtime-deploy-online-cpu-zh.sh+++ b/runtime/deploy_tools/funasr-runtime-deploy-online-cpu-zh.sh@@ -27,7 +27,7 @@ SUDO_CMD="sudo"DEFAULT_DOCKER_ONLINE_CPU_ZH_LISTS_OSS="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/docker_lists/docker_online_cpu_zh_lists"-DEFAULT_DOCKER_ONLINE_CPU_ZH_LISTS_GIT="https://raw.githubusercontent.com/alibaba-damo-academy/FunASR/main/runtime/docs/docker_online_cpu_zh_lists"+DEFAULT_DOCKER_ONLINE_CPU_ZH_LISTS_GIT="https://raw.githubusercontent.com/modelscope/FunASR/main/runtime/docs/docker_online_cpu_zh_lists"DEFAULT_DOCKER_IMAGE_LISTS=$DEFAULT_DOCKER_ONLINE_CPU_ZH_LISTS_OSSDEFAULT_FUNASR_DOCKER_URL="registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr"DEFAULT_FUNASR_RUNTIME_RESOURCES="funasr-runtime-resources"diff --git a/runtime/docs/SDK_tutorial.md b/runtime/docs/SDK_tutorial.mdindex 4421d8214..0261fdb4d 100644--- a/runtime/docs/SDK_tutorial.md+++ b/runtime/docs/SDK_tutorial.md@@ -27,7 +27,7 @@ Cloud service providers offer a 3-month free trial for new users. Application tuDownload the deployment tool `funasr-runtime-deploy-offline-cpu-zh.sh````shell-curl -O https://raw.githubusercontent.com/alibaba-damo-academy/FunASR/main/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh;+curl -O https://raw.githubusercontent.com/modelscope/FunASR/main/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh;# If there is a network problem, users in mainland China can use the following command:# curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/funasr-runtime-deploy-offline-cpu-zh.sh;```diff --git a/runtime/docs/SDK_tutorial_en.md b/runtime/docs/SDK_tutorial_en.mdindex 09dcf4642..d4d6264aa 100644--- a/runtime/docs/SDK_tutorial_en.md+++ b/runtime/docs/SDK_tutorial_en.md@@ -27,7 +27,7 @@ Cloud service providers offer a 3-month free trial for new users. Application tuDownload the deployment tool `funasr-runtime-deploy-offline-cpu-en.sh````shell-curl -O https://raw.githubusercontent.com/alibaba-damo-academy/FunASR/main/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-en.sh;+curl -O https://raw.githubusercontent.com/modelscope/FunASR/main/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-en.sh;# If there is a network problem, users in mainland China can use the following command:# curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/funasr-runtime-deploy-offline-cpu-en.sh;```diff --git a/runtime/docs/SDK_tutorial_en_zh.md b/runtime/docs/SDK_tutorial_en_zh.mdindex 196a09442..20941b8a3 100644--- a/runtime/docs/SDK_tutorial_en_zh.md+++ b/runtime/docs/SDK_tutorial_en_zh.md@@ -28,7 +28,7 @@ FunASR提供可便捷本地或者云端服务器部署的离线文件转写服下载部署工具`funasr-runtime-deploy-offline-cpu-en.sh````shell-curl -O https://raw.githubusercontent.com/alibaba-damo-academy/FunASR/main/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-en.sh;+curl -O https://raw.githubusercontent.com/modelscope/FunASR/main/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-en.sh;# 如遇到网络问题,中国大陆用户,可以使用下面的命令:# curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/funasr-runtime-deploy-offline-cpu-en.sh;```diff --git a/runtime/docs/SDK_tutorial_online.md b/runtime/docs/SDK_tutorial_online.mdindex c8e78be67..e8794b6ce 100644--- a/runtime/docs/SDK_tutorial_online.md+++ b/runtime/docs/SDK_tutorial_online.md@@ -24,7 +24,7 @@ Cloud service providers offer a 3-month free trial for new users. Application tuDownload the deployment tool `funasr-runtime-deploy-online-cpu-zh.sh````shell-curl -O https://raw.githubusercontent.com/alibaba-damo-academy/FunASR/main/runtime/deploy_tools/funasr-runtime-deploy-online-cpu-zh.sh;+curl -O https://raw.githubusercontent.com/modelscope/FunASR/main/runtime/deploy_tools/funasr-runtime-deploy-online-cpu-zh.sh;# If there is a network problem, users in mainland China can use the following command:# curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/funasr-runtime-deploy-online-cpu-zh.sh;```diff --git a/runtime/docs/SDK_tutorial_online_zh.md b/runtime/docs/SDK_tutorial_online_zh.mdindex cdff0fc0c..6a14e2ff0 100644--- a/runtime/docs/SDK_tutorial_online_zh.md+++ b/runtime/docs/SDK_tutorial_online_zh.md@@ -25,7 +25,7 @@ FunASR集成了达摩院语音实验室在Modelscope社区开源的语音端点下载部署工具`funasr-runtime-deploy-online-cpu-zh.sh````shell-curl -O https://raw.githubusercontent.com/alibaba-damo-academy/FunASR/main/runtime/deploy_tools/funasr-runtime-deploy-online-cpu-zh.sh;+curl -O https://raw.githubusercontent.com/modelscope/FunASR/main/runtime/deploy_tools/funasr-runtime-deploy-online-cpu-zh.sh;# 如遇到网络问题,中国大陆用户,可以使用下面的命令:# curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/funasr-runtime-deploy-online-cpu-zh.sh;```diff --git a/runtime/docs/SDK_tutorial_zh.md b/runtime/docs/SDK_tutorial_zh.mdindex 597529a56..2d75ee437 100644--- a/runtime/docs/SDK_tutorial_zh.md+++ b/runtime/docs/SDK_tutorial_zh.md@@ -28,7 +28,7 @@ FunASR提供可便捷本地或者云端服务器部署的离线文件转写服下载部署工具`funasr-runtime-deploy-offline-cpu-zh.sh````shell-curl -O https://raw.githubusercontent.com/alibaba-damo-academy/FunASR/main/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh;+curl -O https://raw.githubusercontent.com/modelscope/FunASR/main/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh;# 如遇到网络问题,中国大陆用户,可以使用下面的命令:# curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/funasr-runtime-deploy-offline-cpu-zh.sh;```diff --git a/runtime/python/http/server.py b/runtime/python/http/server.pyindex 8ddcee2e8..4f9782135 100644--- a/runtime/python/http/server.py+++ b/runtime/python/http/server.py@@ -23,21 +23,21 @@ parser.add_argument("--asr_model",type=str,default="paraformer-zh",- help="asr model from https://github.com/alibaba-damo-academy/FunASR?tab=readme-ov-file#model-zoo",+ help="asr model from https://github.com/modelscope/FunASR?tab=readme-ov-file#model-zoo",)parser.add_argument("--asr_model_revision", type=str, default="v2.0.4", help="")parser.add_argument("--vad_model",type=str,default="fsmn-vad",- help="vad model from https://github.com/alibaba-damo-academy/FunASR?tab=readme-ov-file#model-zoo",+ help="vad model from https://github.com/modelscope/FunASR?tab=readme-ov-file#model-zoo",)parser.add_argument("--vad_model_revision", type=str, default="v2.0.4", help="")parser.add_argument("--punc_model",type=str,default="ct-punc-c",- help="model from https://github.com/alibaba-damo-academy/FunASR?tab=readme-ov-file#model-zoo",+ help="model from https://github.com/modelscope/FunASR?tab=readme-ov-file#model-zoo",)parser.add_argument("--punc_model_revision", type=str, default="v2.0.4", help="")parser.add_argument("--ngpu", type=int, default=1, help="0 for cpu, 1 for gpu")diff --git a/runtime/python/libtorch/setup.py b/runtime/python/libtorch/setup.pyindex 2e6179bb5..b7cca4c91 100644--- a/runtime/python/libtorch/setup.py+++ b/runtime/python/libtorch/setup.py@@ -17,7 +17,7 @@ setuptools.setup(name="funasr_torch",version="0.1.3",platforms="Any",- url="https://github.com/alibaba-damo-academy/FunASR.git",+ url="https://github.com/modelscope/FunASR.git",author="Speech Lab of DAMO Academy, Alibaba Group",author_email="[email protected]",description="FunASR: A Fundamental End-to-End Speech Recognition Toolkit",diff --git a/runtime/python/onnxruntime/setup.py b/runtime/python/onnxruntime/setup.pyindex 564cbc17a..652371465 100644--- a/runtime/python/onnxruntime/setup.py+++ b/runtime/python/onnxruntime/setup.py@@ -19,7 +19,7 @@ setuptools.setup(name=MODULE_NAME,version=VERSION_NUM,platforms="Any",- url="https://github.com/alibaba-damo-academy/FunASR.git",+ url="https://github.com/modelscope/FunASR.git",author="Speech Lab of DAMO Academy, Alibaba Group",author_email="[email protected]",description="FunASR: A Fundamental End-to-End Speech Recognition Toolkit",diff --git a/tests/test_docs_funasr_install_commands.py b/tests/test_docs_funasr_install_commands.pyindex 0f39239ae..8ee7c33bb 100644--- a/tests/test_docs_funasr_install_commands.py+++ b/tests/test_docs_funasr_install_commands.py@@ -40,6 +40,24 @@ PUBLIC_DOCS_SHOULD_USE_CURRENT_HOSTS = ["runtime/html5/readme_zh.md",]+PUBLIC_ENTRYPOINTS_SHOULD_USE_CURRENT_REPO_URLS = [+ "model_zoo/modelscope_models.md",+ "model_zoo/modelscope_models_zh.md",+ "model_zoo/readme.md",+ "runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-en.sh",+ "runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh",+ "runtime/deploy_tools/funasr-runtime-deploy-online-cpu-zh.sh",+ "runtime/docs/SDK_tutorial.md",+ "runtime/docs/SDK_tutorial_en.md",+ "runtime/docs/SDK_tutorial_en_zh.md",+ "runtime/docs/SDK_tutorial_online.md",+ "runtime/docs/SDK_tutorial_online_zh.md",+ "runtime/docs/SDK_tutorial_zh.md",+ "runtime/python/http/server.py",+ "runtime/python/libtorch/setup.py",+ "runtime/python/onnxruntime/setup.py",+]+def test_current_funasr_install_commands_are_quoted():for relpath in DOCS_WITH_CURRENT_FUNASR_INSTALL:@@ -62,6 +80,18 @@ def test_public_docs_use_current_repository_and_docs_hosts():assert "alibaba-damo-academy.github.io/FunASR" not in text+def test_public_entrypoints_use_current_repository_urls():+ forbidden = [+ "github.com/alibaba-damo-academy/FunASR",+ "raw.githubusercontent.com/alibaba-damo-academy/FunASR",+ ]++ for relpath in PUBLIC_ENTRYPOINTS_SHOULD_USE_CURRENT_REPO_URLS:+ text = (ROOT / relpath).read_text()+ for marker in forbidden:+ assert marker not in text++def test_public_docs_do_not_advertise_stale_release_or_star_copy():checked_docs = ["docs/repository_roles.md",@@ -116,6 +146,29 @@ def test_readme_model_tables_use_current_modelscope_entries():assert marker not in text+def test_model_zoo_tables_use_current_paraformer_modelscope_entry():+ docs = [+ (ROOT / "model_zoo/modelscope_models.md").read_text(),+ (ROOT / "model_zoo/modelscope_models_zh.md").read_text(),+ (ROOT / "model_zoo/readme.md").read_text(),+ ]++ current = (+ "models/iic/"+ "speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch"+ "/summary"+ )+ stale = (+ "models/damo/"+ "speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch"+ "/summary"+ )++ for text in docs:+ assert current in text+ assert stale not in text++def test_readme_model_tables_surface_public_gguf_entries():readmes = [(ROOT / "README.md").read_text(),