From b9bcf1f093c3053fdc4e2cf4a1d38e27bbf429fb Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 19 十月 2023 14:03:48 +0800
Subject: [PATCH] docs

---
 egs_modelscope/asr/TEMPLATE/README.md |   44 ++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 44 insertions(+), 0 deletions(-)

diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md
index e44a09d..10ddc1e 100644
--- a/egs_modelscope/asr/TEMPLATE/README.md
+++ b/egs_modelscope/asr/TEMPLATE/README.md
@@ -21,6 +21,28 @@
 rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
 print(rec_result)
 ```
+#### [Paraformer-long Model](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model='damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
+    vad_model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',
+    #punc_model='damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch',
+    punc_model='damo/punc_ct-transformer_cn-en-common-vocab471067-large',
+)
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav', 
+                                batch_size_token=5000, batch_size_token_threshold_s=40, max_single_segment_time=6000)
+print(rec_result)
+```
+Where, 
+- `batch_size_token` refs to dynamic batch_size and the total tokens of batch is `batch_size_token`, 1 token = 60 ms. 
+- `batch_size_token_threshold_s`: The batch_size is set to 1, when the audio duration exceeds the threshold value of `batch_size_token_threshold_s`, specified in `s`.
+- `max_single_segment_time`: The maximum length for audio segmentation in VAD, specified in `ms`.
+
 #### [Paraformer-online Model](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary)
 ##### Streaming Decoding
 ```python
@@ -99,6 +121,28 @@
 ```
 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