From 567bf98954820394559db6679f210f4f4081b385 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 31 十月 2024 16:22:18 +0800
Subject: [PATCH] fix(model): 调整Codec子模型中的上采样逻辑并修正准确率计算偏移问题

---
 docs/tutorial/Tables_zh.md |   61 +++++++++++++++++++++++++-----
 1 files changed, 50 insertions(+), 11 deletions(-)

diff --git a/docs/tutorial/Tables_zh.md b/docs/tutorial/Tables_zh.md
index 9f616cf..576b408 100644
--- a/docs/tutorial/Tables_zh.md
+++ b/docs/tutorial/Tables_zh.md
@@ -1,6 +1,6 @@
 # FunASR-1.x.x聽娉ㄥ唽妯″瀷鏁欑▼
 
-1.0鐗堟湰鐨勮璁″垵琛锋槸銆�**璁╂ā鍨嬮泦鎴愭洿绠�鍗�**銆戯紝鏍稿績feature涓烘敞鍐岃〃涓嶢utoModel锛�
+funasr-1.x.x聽鐗堟湰鐨勮璁″垵琛锋槸銆�**璁╂ā鍨嬮泦鎴愭洿绠�鍗�**銆戯紝鏍稿績feature涓烘敞鍐岃〃涓嶢utoModel锛�
 
 *   娉ㄥ唽琛ㄧ殑寮曞叆锛屼娇寰楀紑鍙戜腑鍙互鐢ㄦ惌绉湪鐨勬柟寮忔帴鍏ユā鍨嬶紝鍏煎澶氱task锛�
     
@@ -10,8 +10,6 @@
     
 *   缁熶竴瀛︽湳涓庡伐涓氭ā鍨嬫帹鐞嗚缁冭剼鏈紱
     
-
-![image](https://alidocs.oss-cn-zhangjiakou.aliyuncs.com/a/6Ea1DxkZVte8y0g2/150e0eafd1c34f2dbb9360ccb5db4dc40521.png)
 
 # 蹇�熶笂鎵�
 
@@ -119,11 +117,15 @@
 
 # 娉ㄥ唽琛ㄨ瑙�
 
+浠enseVoiceSmall妯″瀷涓轰緥锛岃瑙e浣曟敞鍐屾柊妯″瀷锛屾ā鍨嬮摼鎺ワ細
+
+**modelscope锛�**[https://www.modelscope.cn/models/iic/SenseVoiceSmall/files](https://www.modelscope.cn/models/iic/SenseVoiceSmall/files)
+
+**huggingface锛�**[https://huggingface.co/FunAudioLLM/SenseVoiceSmall](https://huggingface.co/FunAudioLLM/SenseVoiceSmall)
+
 ## 妯″瀷璧勬簮鐩綍
 
 ![image.png](https://alidocs.oss-cn-zhangjiakou.aliyuncs.com/res/8oLl9y628rBNlapY/img/cab7f215-787f-4407-885a-14dc89ae9e02.png)
-
-**妯″瀷閾炬帴涓猴細**[https://www.modelscope.cn/models/iic/SenseVoiceSmall/files](https://www.modelscope.cn/models/iic/SenseVoiceSmall/files)
 
 **閰嶇疆鏂囦欢**锛歝onfig.yaml
 
@@ -213,7 +215,7 @@
 
 **妯″瀷鍙傛暟**锛歮odel.pt
 
-**璺緞瑙f瀽**锛歝onfiguration.json
+**璺緞瑙f瀽**锛歝onfiguration.json锛堥潪蹇呴渶锛�
 
 ```json
 {
@@ -232,9 +234,21 @@
 }
 ```
 
-鍐呭鍙互澶嶇敤锛岀洿鎺ユ嫹璐濆嵆鍙紝闇�瑕佹敞鎰忓瓧娈� `file_path_metas` 鎵�鏈夊唴瀹逛細鑷姩鎷兼帴妯″瀷璧勬簮璺緞锛屽苟涓斾細瑕嗙洊 `config.yaml` 涓浉鍚屽瓧娈电殑璺緞銆�
+configuration.json鐨勪綔鐢ㄦ槸缁檉ile\_path\_metas涓殑item鎷兼帴涓婃ā鍨嬫牴鐩綍锛屼互渚夸簬璺緞鑳藉琚纭殑瑙f瀽锛屼互涓婁负渚嬶紝鍋囪妯″瀷鏍圭洰褰曚负锛�/home/zhifu.gzf/init\_model/SenseVoiceSmall锛岀洰褰曚腑config.yaml涓殑鐩稿叧璺緞琚浛鎹㈡垚浜嗘纭殑璺緞锛堝拷鐣ユ棤鍏抽厤缃級锛�
+
+```yaml
+init_param: /home/zhifu.gzf/init_model/SenseVoiceSmall/model.pt
+
+tokenizer_conf:
+  bpemodel: /home/zhifu.gzf/init_model/SenseVoiceSmall/chn_jpn_yue_eng_ko_spectok.bpe.model
+
+frontend_conf:
+    cmvn_file: /home/zhifu.gzf/init_model/SenseVoiceSmall/am.mvn
+```
 
 ## 娉ㄥ唽琛�
+
+![image](https://alidocs.oss-cn-zhangjiakou.aliyuncs.com/a/6Ea1DxkZVte8y0g2/c92059e82c38493988fbc8c032d3f5380521.png)
 
 ### 鏌ョ湅娉ㄥ唽琛�
 
@@ -244,7 +258,24 @@
 tables.print()
 ```
 
-鏀寔鏌ョ湅鎸囧畾绫诲瀷鐨勬敞鍐岃〃锛屼緥濡傚彧鐪嬫敞鍐岀殑`model`绫伙細`tables.print("model")`
+鏀寔鏌ョ湅鎸囧畾绫诲瀷鐨勬敞鍐岃〃锛歕`tables.print("model")\`锛岀洰鍓峟unasr宸茬粡娉ㄥ唽妯″瀷濡備笂鍥炬墍绀恒�傜洰鍓嶉鍏堝畾涔変簡濡備笅鍑犱釜鍒嗙被锛�
+
+```python
+    model_classes = {}
+    frontend_classes = {}
+    specaug_classes = {}
+    normalize_classes = {}
+    encoder_classes = {}
+    decoder_classes = {}
+    joint_network_classes = {}
+    predictor_classes = {}
+    stride_conv_classes = {}
+    tokenizer_classes = {}
+    dataloader_classes = {}
+    batch_sampler_classes = {}
+    dataset_classes = {}
+    index_ds_classes = {}
+```
 
 ### 娉ㄥ唽妯″瀷
 
@@ -274,7 +305,15 @@
 
 ```
 
-鍦ㄩ渶瑕佹敞鍐岀殑绫诲悕鍓嶅姞涓� `@tables.register("model_classes","SenseVoiceSmall")`锛屽嵆鍙畬鎴愭敞鍐岋紝绫婚渶瑕佸疄鐜版湁锛歘_init__锛宖orward锛宨nference鏂规硶銆�
+鍦ㄩ渶瑕佹敞鍐岀殑绫诲悕鍓嶅姞涓娐燖tables.register("model\_classes",聽"SenseVoiceSmall")锛屽嵆鍙畬鎴愭敞鍐岋紝绫婚渶瑕佸疄鐜版湁锛歕_\_init\_\_锛宖orward锛宨nference鏂规硶銆�
+
+register鐢ㄦ硶锛�
+
+```python
+@tables.register("娉ㄥ唽鍒嗙被", "娉ㄥ唽鍚�")
+```
+
+鍏朵腑锛�"娉ㄥ唽鍒嗙被"鍙互鏄鍏堝畾涔夊ソ鐨勫垎绫伙紙瑙佷笂闈㈠浘锛夛紝濡傛灉鏄嚜宸卞畾涔夌殑鏂板垎绫伙紝浼氳嚜鍔ㄥ皢鏂板垎绫诲啓杩涙敞鍐岃〃鍒嗙被涓紝"娉ㄥ唽鍚�"鍗冲笇鏈涙敞鍐屽悕瀛楋紝鍚庣画鍙互鐩存帴鏉ヤ娇鐢ㄣ��
 
 瀹屾暣浠g爜锛歔https://github.com/modelscope/FunASR/blob/main/funasr/models/sense\_voice/model.py#L443](https://github.com/modelscope/FunASR/blob/main/funasr/models/sense_voice/model.py#L443)
 
@@ -286,9 +325,9 @@
   ...
 ```
 
-## 娉ㄥ唽澶辫触
+### 娉ㄥ唽澶辫触
 
-濡傛灉鍑虹幇鎵句笉鍒版敞鍐屾ā鍨嬫垨鑰呮敞鍐屽嚱鏁帮紝`assert model_class is not None, f'{kwargs["model"]} is not registered'`銆傛ā鍨嬫敞鍐岀殑鍘熺悊鏄紝import 妯″瀷鏂囦欢锛屽彲浠ラ�氳繃import鏉ユ煡鐪嬪叿浣撴敞鍐屽け璐ュ師鍥狅紝渚嬪锛屼笂杩版ā鍨嬫枃浠朵负锛宖unasr/models/sense_voice/model.py锛�
+濡傛灉鍑虹幇鎵句笉鍒版敞鍐屾ā鍨嬫垨鍙戞柟娉曪紝assert聽model\_class聽is聽not聽None,聽f'{kwargs\["model"\]}聽is聽not聽registered'銆傛ā鍨嬫敞鍐岀殑鍘熺悊鏄紝import聽妯″瀷鏂囦欢锛屽彲浠ラ�氳繃import鏉ユ煡鐪嬪叿浣撴敞鍐屽け璐ュ師鍥狅紝渚嬪锛屼笂杩版ā鍨嬫枃浠朵负锛宖unasr/models/sense\_voice/model.py锛�
 
 ```python
 from funasr.models.sense_voice.model import *

--
Gitblit v1.9.1