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 entrypoint links
zhifu gao874330a1f788
diff --git a/benchmarks/benchmark_pipeline_cer.md b/benchmarks/benchmark_pipeline_cer.mdindex 98aa6d726..d874963cd 100644--- a/benchmarks/benchmark_pipeline_cer.md+++ b/benchmarks/benchmark_pipeline_cer.md@@ -56,7 +56,7 @@ bash infer.sh<tr align="center"><td style="border: 1px solid"></td><td style="border: 1px solid"></td>- <td style="border: 1px solid">dev</td>+ <td style="border: 1px solid">dev</td><td style="border: 1px solid">test</td><td style="border: 1px solid">dev_ios</td><td style="border: 1px solid">test_ios</td>@@ -67,7 +67,7 @@ bash infer.sh<td style="border: 1px solid">test_net</td></tr><tr align="center">- <td style="border: 1px solid"> <a href="https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary">Paraformer-large</a> </td>+ <td style="border: 1px solid"> <a href="https://www.modelscope.cn/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary">Paraformer-large</a> </td><td style="border: 1px solid">Offline</td><td style="border: 1px solid">1.76</td><td style="border: 1px solid">1.94</td>@@ -80,8 +80,8 @@ bash infer.sh<td style="border: 1px solid">6.66</td></tr><tr align="center">- <td style="border: 1px solid"> <a href="https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary">Paraformer-large-long</a> </td>- <td style="border: 1px solid">Offline</td>+ <td style="border: 1px solid"> <a href="https://www.modelscope.cn/models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary">Paraformer-large-long</a> </td>+ <td style="border: 1px solid">Offline</td><td style="border: 1px solid">1.80</td><td style="border: 1px solid">2.10</td><td style="border: 1px solid">2.78</td>@@ -106,7 +106,7 @@ bash infer.sh<td style="border: 1px solid">6.72</td></tr><tr align="center">- <td style="border: 1px solid"> <a href="https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary">Paraformer-large-online</a> </td>+ <td style="border: 1px solid"> <a href="https://www.modelscope.cn/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary">Paraformer-large-online</a> </td><td style="border: 1px solid">Online</td><td style="border: 1px solid">2.37</td><td style="border: 1px solid">3.34</td>@@ -119,7 +119,7 @@ bash infer.sh<td style="border: 1px solid">7.78</td></tr><tr align="center">- <td style="border: 1px solid"> <a href="https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary">Paraformer</a> </td>+ <td style="border: 1px solid"> <a href="https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary">Paraformer</a> </td><td style="border: 1px solid">Offline</td><td style="border: 1px solid">3.24</td><td style="border: 1px solid">3.69</td>@@ -132,7 +132,7 @@ bash infer.sh<td style="border: 1px solid">9.19</td></tr><tr align="center">- <td style="border: 1px solid"> <a href="https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-online/summary">UniASR</a> </td>+ <td style="border: 1px solid"> <a href="https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-online/summary">UniASR</a> </td><td style="border: 1px solid">Online</td><td style="border: 1px solid">3.34</td><td style="border: 1px solid">3.99</td>@@ -145,8 +145,8 @@ bash infer.sh<td style="border: 1px solid">9.70</td></tr><tr align="center">- <td style="border: 1px solid"> <a href="https://modelscope.cn/models/damo/speech_UniASR-large_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline/summary">UniASR-large</a> </td>- <td style="border: 1px solid">Offline</td>+ <td style="border: 1px solid"> <a href="https://modelscope.cn/models/damo/speech_UniASR-large_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline/summary">UniASR-large</a> </td>+ <td style="border: 1px solid">Offline</td><td style="border: 1px solid">2.93</td><td style="border: 1px solid">3.48</td><td style="border: 1px solid">3.95</td>@@ -184,7 +184,7 @@ bash infer.sh<td style="border: 1px solid">-</td></tr><tr align="center">- <td style="border: 1px solid"> <a href="https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/summary">Paraformer-aishell2</a> </td>+ <td style="border: 1px solid"> <a href="https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/summary">Paraformer-aishell2</a> </td><td style="border: 1px solid">Offline</td><td style="border: 1px solid">-</td><td style="border: 1px solid">-</td>@@ -197,7 +197,7 @@ bash infer.sh<td style="border: 1px solid">-</td></tr><tr align="center">- <td style="border: 1px solid"> <a href="https://www.modelscope.cn/models/damo/speech_paraformerbert_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/summary">ParaformerBert-aishell2</a> </td>+ <td style="border: 1px solid"> <a href="https://www.modelscope.cn/models/damo/speech_paraformerbert_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/summary">ParaformerBert-aishell2</a> </td><td style="border: 1px solid">Offline</td><td style="border: 1px solid">-</td><td style="border: 1px solid">-</td>@@ -213,4 +213,3 @@ bash infer.sh### English Dataset-diff --git a/runtime/docs/benchmark_libtorch.md b/runtime/docs/benchmark_libtorch.mdindex 274710dbf..e7e97171e 100644--- a/runtime/docs/benchmark_libtorch.md+++ b/runtime/docs/benchmark_libtorch.md@@ -35,7 +35,7 @@ nohup bash test_cer.sh &> log.txt &```-## [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)+## [Paraformer-large](https://www.modelscope.cn/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)### Intel(R) Xeon(R) Platinum 8269CY CPU @ 2.50GHz 16core-32processor with avx512_vnnidiff --git a/runtime/docs/benchmark_onnx.md b/runtime/docs/benchmark_onnx.mdindex 6f77b4b46..38fa5156d 100644--- a/runtime/docs/benchmark_onnx.md+++ b/runtime/docs/benchmark_onnx.md@@ -35,9 +35,9 @@ set the model, data path and output_dirnohup bash test_cer.sh &> log.txt &```-## [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)+## [Paraformer-large](https://www.modelscope.cn/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)-Number of Parameter: 220M+Number of Parameter: 220MStorage size: 880MB@@ -95,7 +95,7 @@ CER after int8-quant: 1.95%## [Paraformer](https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary)-Number of Parameter: 68M+Number of Parameter: 68MStorage size: 275MBdiff --git a/runtime/docs/benchmark_onnx_cpp.md b/runtime/docs/benchmark_onnx_cpp.mdindex 3ecf632cb..7667970d8 100644--- a/runtime/docs/benchmark_onnx_cpp.md+++ b/runtime/docs/benchmark_onnx_cpp.md@@ -43,7 +43,7 @@ cmake -DCMAKE_BUILD_TYPE=release .. -DONNXRUNTIME_DIR=/path/to/onnxruntime-linumake```-## [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)+## [Paraformer-large](https://www.modelscope.cn/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)```shell./funasr-onnx-offline-rtf \--model-dir ./damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch \@@ -51,10 +51,10 @@ make--wav-path ./aishell1_test.scp \--thread-num 32-Node: '--quantize false' means fp32, otherwise it will be int8+Node: '--quantize false' means fp32, otherwise it will be int8```-Number of Parameter: 220M+Number of Parameter: 220MStorage size: 880MB@@ -100,7 +100,7 @@ CER after int8-quant: 1.95%| 96 (onnx fp32) | 115s | 0.003183 | 314 || 96 (onnx int8) | 80s | 0.002222 | 450 |-## [FSMN-VAD](https://www.modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx/summary) + [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) + [CT-Transformer](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx/summary)+## [FSMN-VAD](https://www.modelscope.cn/models/iic/speech_fsmn_vad_zh-cn-16k-common-onnx/summary) + [Paraformer-large](https://www.modelscope.cn/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) + [CT-Transformer](https://www.modelscope.cn/models/iic/punc_ct-transformer_zh-cn-common-vocab272727-onnx/summary)```shell./funasr-onnx-offline-rtf \@@ -111,7 +111,7 @@ CER after int8-quant: 1.95%--wav-path ./aishell1_test.scp \--thread-num 32-Node: '--quantize false' means fp32, otherwise it will be int8+Node: '--quantize false' means fp32, otherwise it will be int8```### Intel(R) Xeon(R) Platinum 8369B CPU @ 2.90GHz 16core-32processor with avx512_vnni@@ -152,7 +152,7 @@ Node: '--quantize false' means fp32, otherwise it will be int8-## [FSMN-VAD](https://www.modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx/summary) + [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) +[Ngram](https://www.modelscope.cn/models/damo/speech_ngram_lm_zh-cn-ai-wesp-fst/summary) + [CT-Transformer](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx/summary)+## [FSMN-VAD](https://www.modelscope.cn/models/iic/speech_fsmn_vad_zh-cn-16k-common-onnx/summary) + [Paraformer-large](https://www.modelscope.cn/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) +[Ngram](https://www.modelscope.cn/models/damo/speech_ngram_lm_zh-cn-ai-wesp-fst/summary) + [CT-Transformer](https://www.modelscope.cn/models/iic/punc_ct-transformer_zh-cn-common-vocab272727-onnx/summary)```shell./funasr-onnx-offline-rtf \@@ -164,7 +164,7 @@ Node: '--quantize false' means fp32, otherwise it will be int8--wav-path ./aishell1_test.scp \--thread-num 32-Node: '--quantize false' means fp32, otherwise it will be int8+Node: '--quantize false' means fp32, otherwise it will be int8```### Intel(R) Xeon(R) Platinum 8369B CPU @ 2.90GHz 16core-32processor with avx512_vnni@@ -197,7 +197,7 @@ Node: '--quantize false' means fp32, otherwise it will be int8--wav-path ./aishell1_test.scp \--thread-num 32-Node: '--quantize false' means fp32, otherwise it will be int8+Node: '--quantize false' means fp32, otherwise it will be int8```### Intel(R) Xeon(R) Platinum 8369B CPU @ 2.90GHz 16core-32processor with avx512_vnni@@ -218,7 +218,7 @@ Node: '--quantize false' means fp32, otherwise it will be int8| 96 (onnx int8) | 122s | 0.0033 | 294 |-## [FSMN-VAD](https://www.modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx/summary) + [Paraformer-en](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-en-16k-common-vocab10020-onnx/summary) + [CT-Transformer](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx/summary)+## [FSMN-VAD](https://www.modelscope.cn/models/iic/speech_fsmn_vad_zh-cn-16k-common-onnx/summary) + [Paraformer-en](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-en-16k-common-vocab10020-onnx/summary) + [CT-Transformer](https://www.modelscope.cn/models/iic/punc_ct-transformer_zh-cn-common-vocab272727-onnx/summary)```shell./funasr-onnx-offline-rtf \@@ -229,7 +229,7 @@ Node: '--quantize false' means fp32, otherwise it will be int8--wav-path ./librispeech_test_clean.scp \--thread-num 32-Node: '--quantize false' means fp32, otherwise it will be int8+Node: '--quantize false' means fp32, otherwise it will be int8```### Intel(R) Xeon(R) Platinum 8369B CPU @ 2.90GHz 16core-32processor with avx512_vnni@@ -247,4 +247,4 @@ Node: '--quantize false' means fp32, otherwise it will be int8| 64 (onnx fp32) | 79s | 0.0041 | 243 || 64 (onnx int8) | 44s | 0.0022 | 438 || 96 (onnx fp32) | 80s | 0.0041 | 240 |-| 96 (onnx int8) | 45s | 0.0023 | 428 |\ No newline at end of file+| 96 (onnx int8) | 45s | 0.0023 | 428 |diff --git a/tests/test_docs_funasr_install_commands.py b/tests/test_docs_funasr_install_commands.pyindex f6f10028d..dd130548d 100644--- a/tests/test_docs_funasr_install_commands.py+++ b/tests/test_docs_funasr_install_commands.py@@ -44,6 +44,9 @@ PUBLIC_ENTRYPOINTS_SHOULD_USE_CURRENT_REPO_URLS = ["model_zoo/modelscope_models.md","model_zoo/modelscope_models_zh.md","model_zoo/readme.md",+ "web-pages/src/views/home/index.vue",+ "web-pages/src/views/home/lxwjzxfw.vue",+ "web-pages/src/views/home/sstx.vue","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",@@ -229,6 +232,32 @@ def test_full_modelscope_tables_use_current_core_entries():assert marker not in text+def test_runtime_benchmark_docs_use_current_core_modelscope_entries():+ docs = [+ (ROOT / "benchmarks/benchmark_pipeline_cer.md").read_text(),+ (ROOT / "runtime/docs/benchmark_libtorch.md").read_text(),+ (ROOT / "runtime/docs/benchmark_onnx.md").read_text(),+ (ROOT / "runtime/docs/benchmark_onnx_cpp.md").read_text(),+ ]++ current_entries = [+ "models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary",+ "models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary",+ "models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary",+ "models/iic/speech_fsmn_vad_zh-cn-16k-common-onnx/summary",+ "models/iic/punc_ct-transformer_zh-cn-common-vocab272727-onnx/summary",+ ]+ stale_entries = [+ entry.replace("models/iic/", "models/damo/") for entry in current_entries+ ]++ combined = "\n".join(docs)+ for marker in current_entries:+ assert marker in combined+ for marker in stale_entries:+ assert marker not in combined++def test_model_zoo_landing_tables_link_huggingface_repos():docs = [(diff --git a/web-pages/src/views/home/index.vue b/web-pages/src/views/home/index.vueindex 0c53fb52c..9bf9a8aae 100644--- a/web-pages/src/views/home/index.vue+++ b/web-pages/src/views/home/index.vue@@ -6,7 +6,7 @@<li :ref="item.ref" v-for="(item, index) in headerList" :key="index" @click="anchorTo(item)"><p>{{item.name}}</p></li>- <li @click="toPage({link: 'https://github.com/alibaba-damo-academy/FunASR'})">+ <li @click="toPage({link: 'https://github.com/modelscope/FunASR'})">Github</li><li>diff --git a/web-pages/src/views/home/lxwjzxfw.vue b/web-pages/src/views/home/lxwjzxfw.vueindex fe1c8b4fc..39fe898af 100644--- a/web-pages/src/views/home/lxwjzxfw.vue+++ b/web-pages/src/views/home/lxwjzxfw.vue@@ -135,7 +135,7 @@ export default {{icon: require('./assets/images/lxwj-az.png'),title: '安 装',- link: 'https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/SDK_advanced_guide_offline_zh.md'+ link: 'https://github.com/modelscope/FunASR/blob/main/runtime/docs/SDK_advanced_guide_offline_zh.md'},{icon: require('./assets/images/lxwj-sy.png'),diff --git a/web-pages/src/views/home/sstx.vue b/web-pages/src/views/home/sstx.vueindex 9913da420..a4ea244f3 100644--- a/web-pages/src/views/home/sstx.vue+++ b/web-pages/src/views/home/sstx.vue@@ -153,7 +153,7 @@ export default {{icon: require('./assets/images/lxwj-az.png'),title: '安 装',- link: 'https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/SDK_advanced_guide_online_zh.md'+ link: 'https://github.com/modelscope/FunASR/blob/main/runtime/docs/SDK_advanced_guide_online_zh.md'},{icon: require('./assets/images/lxwj-sy.png'),