From a05e753d11d9c36983ec4e58c421dbcf86d1dcd4 Mon Sep 17 00:00:00 2001
From: Xian Shi <40013335+R1ckShi@users.noreply.github.com>
Date: 星期二, 17 十月 2023 16:47:27 +0800
Subject: [PATCH] Merge branch 'main' into dev_onnx

---
 egs_modelscope/asr/TEMPLATE/README.md |   39 +++++++++++++++++++++++++++++++++++++++
 1 files changed, 39 insertions(+), 0 deletions(-)

diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md
index bd0e6a9..ac73950 100644
--- a/egs_modelscope/asr/TEMPLATE/README.md
+++ b/egs_modelscope/asr/TEMPLATE/README.md
@@ -68,6 +68,23 @@
 ```
 Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/241)
 
+#### [Paraformer-contextual Model](https://www.modelscope.cn/models/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/summary)
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+param_dict = dict()
+# param_dict['hotword'] = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/hotword.txt"
+param_dict['hotword']="閭撻儊鏉� 鐜嬮鏄� 鐜嬫檾鍚�"
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404",
+    param_dict=param_dict)
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_hotword.wav')
+print(rec_result)
+```
+
 #### [UniASR Model](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
 There are three decoding mode for UniASR model(`fast`銆乣normal`銆乣offline`), for more model details, please refer to [docs](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
 ```python
@@ -82,6 +99,28 @@
 ```
 The decoding mode of `fast` and `normal` is fake streaming, which could be used for evaluating of recognition accuracy.
 Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/151)
+
+#### [Paraformer-Spk](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary)
+This model allows user to get recognition results which contain speaker info of each sentence. Refer to [CAM++](https://modelscope.cn/models/damo/speech_campplus_speaker-diarization_common/summary) for detailed information about speaker diarization model.
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+if __name__ == '__main__':
+    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_speaker_demo.wav'
+    output_dir = "./results"
+    inference_pipeline = pipeline(
+        task=Tasks.auto_speech_recognition,
+        model='damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn',
+        model_revision='v0.0.2',
+        vad_model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',
+        punc_model='damo/punc_ct-transformer_cn-en-common-vocab471067-large',
+        output_dir=output_dir,
+    )
+    rec_result = inference_pipeline(audio_in=audio_in, batch_size_token=5000, batch_size_token_threshold_s=40, max_single_segment_time=6000)
+    print(rec_result)
+```
+
 #### [RNN-T-online model]()
 Undo
 

--
Gitblit v1.9.1