From 8c7b7e5feb68fda1fc4ddd627bad0f915358149e Mon Sep 17 00:00:00 2001
From: Zhanzhao (Deo) Liang <liangzhanzhao1985@gmail.com>
Date: 星期三, 25 十二月 2024 16:40:29 +0800
Subject: [PATCH] fix export_meta import of sense voice (#2334)

---
 docs/tutorial/Tables.md |   70 ++++++++++++++++++-----------------
 1 files changed, 36 insertions(+), 34 deletions(-)

diff --git a/docs/tutorial/Tables.md b/docs/tutorial/Tables.md
index 3dfaa73..831a3ac 100644
--- a/docs/tutorial/Tables.md
+++ b/docs/tutorial/Tables.md
@@ -1,15 +1,17 @@
-# FunASR-1.x.x聽Registration聽Tutorial
+# FunASR-1.x.x聽Registration聽 New Model Tutorial
+
+([绠�浣撲腑鏂嘳(./Tables_zh.md)|English)
 
 The聽original聽intention聽of聽the聽funasr-1.x.x聽version聽is聽to聽make聽model聽integration聽easier.聽The聽core聽feature聽is聽the聽registry聽and聽AutoModel:
 
 *   The聽introduction聽of聽the聽registry聽enables聽the聽development聽of聽building聽blocks聽to聽access聽the聽model,聽compatible聽with聽a聽variety聽of聽tasks;
-    
+
 *   The聽newly聽designed聽AutoModel聽interface聽unifies聽modelscope,聽huggingface,聽and聽funasr聽inference聽and聽training聽interfaces,聽and聽supports聽free聽download聽of聽repositories;
-    
+
 *   Support聽model聽export,聽demo-level聽service聽deployment,聽and聽industrial-level聽multi-concurrent聽service聽deployment;
-    
+
 *   Unify聽academic聽and聽industrial聽model聽inference聽training聽scripts;
-    
+
 
 # Quick聽to聽get聽started
 
@@ -49,19 +51,19 @@
 ```
 
 *   `model`(str):聽[Model聽Warehouse](https://github.com/alibaba-damo-academy/FunASR/tree/main/model_zoo)The聽model聽name聽in,聽or聽the聽model聽path聽in聽the聽local聽disk
-    
+
 *   `device`(str):聽`cuda:0`(Default聽gpu0),聽using聽GPU聽for聽inference,聽specified.聽If`cpu`Then聽the聽CPU聽is聽used聽for聽inference
-    
+
 *   `ncpu`(int):聽`4`(Default),聽set聽the聽number聽of聽threads聽used聽for聽CPU聽internal聽operation聽parallelism
-    
+
 *   `output_dir`(str):聽`None`(Default)聽If聽set,聽the聽output聽path聽of聽the聽output聽result
-    
+
 *   `batch_size`(int):聽`1`(Default),聽batch聽processing聽during聽decoding,聽number聽of聽samples
-    
+
 *   `hub`(str)锛歚ms`(Default)聽to聽download聽the聽model聽from聽modelscope.聽If`hf`To聽download聽the聽model聽from聽huggingface.
-    
+
 *   `**kwargs`(dict):聽All聽in`config.yaml`Parameters,聽which聽can聽be聽specified聽directly聽here,聽for聽example,聽the聽maximum聽cut聽length聽in聽the聽vad聽model.`max_single_segment_time=6000`(Milliseconds).
-    
+
 
 #### AutoModel聽reasoning
 
@@ -70,13 +72,13 @@
 ```
 
 *   *   wav聽file聽path,聽for聽example:聽asr\_example.wav
-        
+
     *   pcm聽file聽path,聽for聽example:聽asr\_example.pcm,聽you聽need聽to聽specify聽the聽audio聽sampling聽rate聽fs聽(default聽is聽16000)
-        
+
     *   Audio聽byte聽stream,聽for聽example:聽microphone聽byte聽data
-        
+
     *   wav.scp,kaldi-style聽wav聽list聽(`wav_id聽\t聽wav_path`),聽for聽example:
-        
+
 
 ```plaintext
 Asr_example1./audios/asr_example1.wav
@@ -87,13 +89,13 @@
 In聽this聽input
 
 *   Audio聽sampling聽points,聽for聽example:`audio,聽rate聽=聽soundfile.read("asr_example_zh.wav")`Is聽numpy.ndarray.聽batch聽input聽is聽supported.聽The聽type聽is聽list:`[audio_sample1,聽audio_sample2,聽...,聽audio_sampleN]`
-    
+
 *   fbank聽input,聽support聽group聽batch.聽shape聽is聽\[batch,聽frames,聽dim\],聽type聽is聽torch.Tensor,聽for聽example
-    
+
 *   `output_dir`:聽None聽(default),聽if聽set,聽the聽output聽path聽of聽the聽output聽result
-    
+
 *   `**kwargs`(dict):聽Model-related聽inference聽parameters,聽e.g,`beam_size=10`,`decoding_ctc_weight=0.1`.
-    
+
 
 Detailed聽documentation聽link:[https://github.com/modelscope/FunASR/blob/main/examples/README\_zh.md](https://github.com/modelscope/FunASR/blob/main/examples/README_zh.md)
 
@@ -126,7 +128,7 @@
     pos_enc_class: SinusoidalPositionEncoder
     normalize_before: true
     kernel_size: 11
-    sanm_shfit: 0
+    sanm_shift: 0
     selfattention_layer_type: sanm
 
 
@@ -206,23 +208,23 @@
   "model": {"type" : "funasr"},
   "pipeline": {"type":"funasr-pipeline"},
   "model_name_in_hub": {
-    "ms":"", 
+    "ms":"",
     "hf":""},
   "file_path_metas": {
-    "init_param":"model.Pt"
-"Config": "config.yaml"
-Languagename_conf: {"bpemodel": "chn_jpn_yue_eng_spectok.bpe.Model"},
-"Frontend_conf":{"cmvn_file": "am.mvn"}}
+    "init_param":"model.pt",
+    "config":"config.yaml",
+    "tokenizer_conf": {"bpemodel": "chn_jpn_yue_eng_ko_spectok.bpe.model"},
+    "frontend_conf":{"cmvn_file": "am.mvn"}}
 }
 ```
 
 The聽function聽of聽configuration.json聽is聽to聽add聽the聽model聽root聽directory聽to聽the聽item聽in聽file\_path\_metas,聽so聽that聽the聽path聽can聽be聽correctly聽parsed.聽For聽example,聽assume聽that聽the聽model聽root聽directory聽is:/home/zhifu.gzf/init\_model/SenseVoiceSmall,The聽relevant聽path聽in聽config.yaml聽in聽the聽directory聽is聽replaced聽with聽the聽correct聽path聽(ignoring聽irrelevant聽configuration):
 
 ```yaml
-Init_param: /home/zhifu.gz F/init_model/sensevoicemail Mall/model.pt
+init_param: /home/zhifu.gz F/init_model/sensevoicemail Mall/model.pt
 
-Tokenizer_conf:
-Bmodeler: /home/Zhifu.gzf/init_model/SenseVoiceSmall/chn_jpn_yue_eng_ko_spectok.bpe.model
+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
@@ -272,7 +274,7 @@
   def forward(
       self,
       **kwargs,
-  ):  
+  ):
 
   def inference(
       self,
@@ -318,9 +320,9 @@
 ## Principles聽of聽Registration
 
 *   Model:聽models聽are聽independent聽of聽each聽other.聽Each聽Model聽needs聽to聽create聽a聽new聽Model聽directory聽under聽funasr/models/.聽Do聽not聽use聽class聽inheritance聽method!!!聽Do聽not聽import聽from聽other聽model聽directories,聽and聽put聽everything聽you聽need聽into聽your聽own聽model聽directory!!!聽Do聽not聽modify聽the聽existing聽model聽code!!!
-    
+
 *   dataset,frontend,tokenizer,聽if聽you聽can聽reuse聽the聽existing聽one,聽reuse聽it聽directly,聽if聽you聽cannot聽reuse聽it,聽please聽register聽a聽new聽one,聽modify聽it聽again,聽and聽do聽not聽modify聽the聽original聽one!!!
-    
+
 
 # Independent聽warehouse
 
@@ -335,7 +337,7 @@
 model = AutoModel (
 model="iic/SenseVoiceSmall ",
 trust_remote_code=True
-remote_code = "./model.py", 
+remote_code = "./model.py",
 )
 ```
 
@@ -358,4 +360,4 @@
 print(text)
 ```
 
-Trim聽reference:[https://github.com/FunAudioLLM/SenseVoice/blob/main/finetune.sh](https://github.com/FunAudioLLM/SenseVoice/blob/main/finetune.sh)
\ No newline at end of file
+Trim聽reference:[https://github.com/FunAudioLLM/SenseVoice/blob/main/finetune.sh](https://github.com/FunAudioLLM/SenseVoice/blob/main/finetune.sh)

--
Gitblit v1.9.1