From e30a17cf4e715b3d139fa1e0ba01cda1bcf0f884 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期三, 10 一月 2024 11:23:41 +0800
Subject: [PATCH] update funasr-onnx

---
 README_zh.md |   64 +++++++++++++++++++++-----------
 1 files changed, 42 insertions(+), 22 deletions(-)

diff --git a/README_zh.md b/README_zh.md
index e4b3658..274e14b 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -81,39 +81,59 @@
 
 ### 闈炲疄鏃惰闊宠瘑鍒�
 ```python
-from funasr import infer
+from funasr import AutoModel
 
-p = infer(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc", model_hub="ms")
+model = AutoModel(model="paraformer-zh")
+# for the long duration wav, you could add vad model
+# model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad")
 
-res = p("asr_example_zh.wav", batch_size_token=5000)
+res = model(input="asr_example_zh.wav", batch_size=64)
 print(res)
 ```
 娉細`model_hub`锛氳〃绀烘ā鍨嬩粨搴擄紝`ms`涓洪�夋嫨modelscope涓嬭浇锛宍hf`涓洪�夋嫨huggingface涓嬭浇銆�
 
-### 瀹炴椂璇煶璇嗗埆
-```python
-from funasr import infer
+[//]: # (### 瀹炴椂璇煶璇嗗埆)
 
-p = infer(model="paraformer-zh-streaming", model_hub="ms")
+[//]: # (```python)
 
-chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
-param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size, "encoder_chunk_look_back": 4, "decoder_chunk_look_back": 1}
+[//]: # (from funasr import infer)
 
-import torchaudio
-speech = torchaudio.load("asr_example_zh.wav")[0][0]
-speech_length = speech.shape[0]
+[//]: # ()
+[//]: # (p = infer&#40;model="paraformer-zh-streaming", model_hub="ms"&#41;)
 
-stride_size = chunk_size[1] * 960
-sample_offset = 0
-for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)):
-    param_dict["is_final"] = True if sample_offset + stride_size >= speech_length - 1 else False
-    input = speech[sample_offset: sample_offset + stride_size]
-    rec_result = p(input=input, param_dict=param_dict)
-    print(rec_result)
-```
-娉細`chunk_size`涓烘祦寮忓欢鏃堕厤缃紝`[0,10,5]`琛ㄧず涓婂睆瀹炴椂鍑哄瓧绮掑害涓篳10*60=600ms`锛屾湭鏉ヤ俊鎭负`5*60=300ms`銆傛瘡娆℃帹鐞嗚緭鍏ヤ负`600ms`锛堥噰鏍风偣鏁颁负`16000*0.6=960`锛夛紝杈撳嚭涓哄搴旀枃瀛楋紝鏈�鍚庝竴涓闊崇墖娈佃緭鍏ラ渶瑕佽缃甡is_final=True`鏉ュ己鍒惰緭鍑烘渶鍚庝竴涓瓧銆�
+[//]: # ()
+[//]: # (chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms)
 
-鏇村璇︾粏鐢ㄦ硶锛圼鏂颁汉鏂囨。](https://alibaba-damo-academy.github.io/FunASR/en/funasr/quick_start_zh.html)锛�
+[//]: # (param_dict = {"cache": dict&#40;&#41;, "is_final": False, "chunk_size": chunk_size, "encoder_chunk_look_back": 4, "decoder_chunk_look_back": 1})
+
+[//]: # ()
+[//]: # (import torchaudio)
+
+[//]: # (speech = torchaudio.load&#40;"asr_example_zh.wav"&#41;[0][0])
+
+[//]: # (speech_length = speech.shape[0])
+
+[//]: # ()
+[//]: # (stride_size = chunk_size[1] * 960)
+
+[//]: # (sample_offset = 0)
+
+[//]: # (for sample_offset in range&#40;0, speech_length, min&#40;stride_size, speech_length - sample_offset&#41;&#41;:)
+
+[//]: # (    param_dict["is_final"] = True if sample_offset + stride_size >= speech_length - 1 else False)
+
+[//]: # (    input = speech[sample_offset: sample_offset + stride_size])
+
+[//]: # (    rec_result = p&#40;input=input, param_dict=param_dict&#41;)
+
+[//]: # (    print&#40;rec_result&#41;)
+
+[//]: # (```)
+
+[//]: # (娉細`chunk_size`涓烘祦寮忓欢鏃堕厤缃紝`[0,10,5]`琛ㄧず涓婂睆瀹炴椂鍑哄瓧绮掑害涓篳10*60=600ms`锛屾湭鏉ヤ俊鎭负`5*60=300ms`銆傛瘡娆℃帹鐞嗚緭鍏ヤ负`600ms`锛堥噰鏍风偣鏁颁负`16000*0.6=960`锛夛紝杈撳嚭涓哄搴旀枃瀛楋紝鏈�鍚庝竴涓闊崇墖娈佃緭鍏ラ渶瑕佽缃甡is_final=True`鏉ュ己鍒惰緭鍑烘渶鍚庝竴涓瓧銆�)
+
+[//]: # ()
+[//]: # (鏇村璇︾粏鐢ㄦ硶锛圼鏂颁汉鏂囨。]&#40;https://alibaba-damo-academy.github.io/FunASR/en/funasr/quick_start_zh.html&#41;锛�)
 
 
 <a name="鏈嶅姟閮ㄧ讲"></a>

--
Gitblit v1.9.1