From b66a41fb735c164e525b18a45769141413d30ffe Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 21 十二月 2023 21:28:14 +0800
Subject: [PATCH] funasr1.0
---
README_zh.md | 56 +++++++++++++++++++++++++++++++++++++-------------------
1 files changed, 37 insertions(+), 19 deletions(-)
diff --git a/README_zh.md b/README_zh.md
index 5007da1..274e14b 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -92,30 +92,48 @@
```
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(model="paraformer-zh-streaming", model_hub="ms"))
-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(), "is_final": False, "chunk_size": chunk_size, "encoder_chunk_look_back": 4, "decoder_chunk_look_back": 1})
+
+[//]: # ()
+[//]: # (import torchaudio)
+
+[//]: # (speech = torchaudio.load("asr_example_zh.wav")[0][0])
+
+[//]: # (speech_length = speech.shape[0])
+
+[//]: # ()
+[//]: # (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�)
+
+[//]: # ()
+[//]: # (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�)
<a name="鏈嶅姟閮ㄧ讲"></a>
--
Gitblit v1.9.1