From 1e5395b0f31d6f38b17e6cebe7110db63fc8bdd1 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 19 十月 2023 14:00:54 +0800
Subject: [PATCH] docs

---
 egs_modelscope/asr/TEMPLATE/README.md    |   22 ++++++++++++++++++++++
 egs_modelscope/asr/TEMPLATE/README_zh.md |   22 ++++++++++++++++++++++
 2 files changed, 44 insertions(+), 0 deletions(-)

diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md
index ac73950..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
diff --git a/egs_modelscope/asr/TEMPLATE/README_zh.md b/egs_modelscope/asr/TEMPLATE/README_zh.md
index 47656b3..591ac17 100644
--- a/egs_modelscope/asr/TEMPLATE/README_zh.md
+++ b/egs_modelscope/asr/TEMPLATE/README_zh.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` 琛ㄧず閲囩敤鍔ㄦ�乥atch锛宐atch涓�籺oken鏁颁负 `batch_size_token`锛�1 token = 60 ms. 
+- `batch_size_token_threshold_s`: 琛ㄧず闊抽鏃堕暱瓒呰繃 `batch_size_token_threshold_s`闃堝�兼槸锛宐atch鏁拌缃负1, 鍗曚綅涓簊.
+- `max_single_segment_time`: 琛ㄧずVAD鏈�澶у垏鍓查煶棰戞椂闀�, 鍗曚綅鏄痬s.
+
 #### [Paraformer-瀹炴椂妯″瀷](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary)
 ##### 瀹炴椂鎺ㄧ悊
 ```python

--
Gitblit v1.9.1