From 1af063cd523f4eab15c35911573aaf5051db4a46 Mon Sep 17 00:00:00 2001
From: speech_asr <wangjiaming.wjm@alibaba-inc.com>
Date: 星期二, 14 二月 2023 16:14:00 +0800
Subject: [PATCH] update docs

---
 docs_cn/build_task.md |  105 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 103 insertions(+), 2 deletions(-)

diff --git a/docs_cn/build_task.md b/docs_cn/build_task.md
index a999c86..7507a17 100644
--- a/docs_cn/build_task.md
+++ b/docs_cn/build_task.md
@@ -1,4 +1,105 @@
 # 鎼缓鑷畾涔変换鍔�
-FunASR绫讳技ESPNet锛屼互`Task`涓洪�氱敤鎺ュ彛锛屼粠鑰屽疄鐜版ā鍨嬬殑璁粌鍜屾帹鐞嗐�備笅闈㈡垜浠皢浠araformer妯″瀷涓轰緥锛屼粙缁嶅浣曞畾涔変竴涓柊鐨刞Task`銆�
+FunASR绫讳技ESPNet锛屼互`Task`涓洪�氱敤鎺ュ彛锛屼粠鑰屽疄鐜版ā鍨嬬殑璁粌鍜屾帹鐞嗐�傛瘡涓�涓猔Task`鏄竴涓被锛屽叾闇�瑕佺户鎵縛AbsTask`锛屽叾瀵瑰簲鐨勫叿浣撲唬鐮佽`funasr/tasks/abs_task.py`銆備笅闈㈢粰鍑哄叾鍖呭惈鐨勪富瑕佸嚱鏁板強鍔熻兘浠嬬粛锛�
+```python
+class AbsTask(ABC):
+    @classmethod
+    def add_task_arguments(cls, parser: argparse.ArgumentParser):
+        pass
+    
+    @classmethod
+    def build_preprocess_fn(cls, args, train):
+        (...)
+    
+    @classmethod
+    def build_collate_fn(cls, args: argparse.Namespace):
+        (...)
 
-`Task`鏄竴涓被锛屽叾闇�瑕佺户鎵縛AbsTask`锛屽叾瀵瑰簲鐨勪唬鐮佽`funasr/tasks/abs_task.py`锛�
\ No newline at end of file
+    @classmethod
+    def build_model(cls, args):
+        (...)
+    
+    @classmethod
+    def main(cls, args):
+        (...)
+```
+- add_task_arguments锛氭坊鍔犵壒瀹歚Task`闇�瑕佺殑鍙傛暟
+- build_preprocess_fn锛氬畾涔夊浣曞鐞嗗鏍锋湰杩涜棰勫鐞�
+- build_collate_fn锛氬畾涔夊浣曞皢澶氫釜鏍锋湰缁勬垚涓�涓猔batch`
+- build_model锛氬畾涔夋ā鍨�
+- main锛氳缁冨叆鍙ｏ紝閫氳繃`Task.main()`鏉ュ惎鍔ㄨ缁�
+
+涓嬮潰鎴戜滑灏嗕互璇煶璇嗗埆浠诲姟涓轰緥锛屼粙缁嶅浣曞畾涔変竴涓柊鐨刞Task`锛屽叿浣撲唬鐮佽`funasr/tasks/asr.py`涓殑`ASRTask`銆� 瀹氫箟鏂扮殑`Task`鐨勮繃绋嬶紝鍏跺疄灏辨槸鏍规嵁浠诲姟闇�姹傦紝閲嶅畾涔変笂杩板嚱鏁扮殑杩囩▼銆�
+- add_task_arguments
+```python
+@classmethod
+def add_task_arguments(cls, parser: argparse.ArgumentParser):
+    group = parser.add_argument_group(description="Task related")
+    group.add_argument(
+        "--token_list",
+        type=str_or_none,
+        default=None,
+        help="A text mapping int-id to token",
+    )
+    (...)
+```
+瀵逛簬璇煶璇嗗埆浠诲姟锛岄渶瑕佺殑鐗瑰畾鍙傛暟鍖呮嫭`token_list`绛夈�傛牴鎹笉鍚屼换鍔＄殑鐗瑰畾闇�姹傦紝鐢ㄦ埛鍙互鍦ㄦ鍑芥暟涓畾涔夌浉搴旂殑鍙傛暟銆�
+
+- build_preprocess_fn
+```python
+@classmethod
+def build_preprocess_fn(cls, args, train):
+    if args.use_preprocessor:
+        retval = CommonPreprocessor(
+                    train=train,
+                    token_type=args.token_type,
+                    token_list=args.token_list,
+                    bpemodel=args.bpemodel,
+                    non_linguistic_symbols=args.non_linguistic_symbols,
+                    text_cleaner=args.cleaner,
+                    ...
+                )
+    else:
+        retval = None
+    return retval
+```
+璇ュ嚱鏁板畾涔変簡濡備綍瀵规牱鏈繘琛岄澶勭悊銆傚叿浣撳湴锛岃闊宠瘑鍒换鍔＄殑杈撳叆鍖呮嫭闊抽鍜屾妱鏈�傚浜庨煶棰戯紝鍦ㄦ瀹炵幇浜�(鍙��)瀵归煶棰戝姞鍣０锛屽姞娣峰搷绛夊姛鑳斤紱瀵逛簬鎶勬湰锛屽湪姝ゅ疄鐜颁簡(鍙��)鏍规嵁bpe澶勭悊鎶勬湰锛屽皢鎶勬湰鏄犲皠鎴恅tokenid`绛夊姛鑳姐�傜敤鎴峰彲浠ヨ嚜宸遍�夋嫨闇�瑕佸鏍锋湰杩涜鐨勯澶勭悊鎿嶄綔锛屽疄鐜版柟娉曞彲浠ュ弬鑰僠CommonPreprocessor`銆�
+
+- build_collate_fn
+```python
+@classmethod
+def build_collate_fn(cls, args, train):
+    return CommonCollateFn(float_pad_value=0.0, int_pad_value=-1)
+```
+璇ュ嚱鏁板畾涔変簡濡備綍灏嗗涓牱鏈粍鎴愪竴涓猔batch`銆傚浜庤闊宠瘑鍒换鍔★紝鍦ㄦ瀹炵幇鐨勬槸灏嗕笉鍚岀殑闊抽鍜屾妱鏈紝閫氳繃`padding`鐨勬柟寮忔潵寰楀埌绛夐暱鐨勬暟鎹�傚叿浣撳湴锛岃嚜姝ゆ垜浠粯璁ょ敤`0.0`鏉ヤ綔涓洪煶棰戠殑濉厖鍊硷紝鐢╜-1`浣滀负鎶勬湰鐨勯粯璁ゅ～鍏呭�笺�傜敤鎴峰彲浠ュ湪姝ゅ畾涔変笉鍚岀殑缁刞batch`鎿嶄綔锛屽疄鐜版柟娉曞彲浠ュ弬鑰僠CommonCollateFn`銆�
+
+- build_model
+```python
+@classmethod
+def build_model(cls, args, train):
+    with open(args.token_list, encoding="utf-8") as f:
+        token_list = [line.rstrip() for line in f]
+        vocab_size = len(token_list)
+        frontend = frontend_class(**args.frontend_conf)
+        specaug = specaug_class(**args.specaug_conf)
+        normalize = normalize_class(**args.normalize_conf)
+        preencoder = preencoder_class(**args.preencoder_conf)
+        encoder = encoder_class(input_size=input_size, **args.encoder_conf)
+        postencoder = postencoder_class(input_size=encoder_output_size, **args.postencoder_conf)
+        decoder = decoder_class(vocab_size=vocab_size, encoder_output_size=encoder_output_size,  **args.decoder_conf)
+        ctc = CTC(odim=vocab_size, encoder_output_size=encoder_output_size, **args.ctc_conf)
+        model = model_class(
+            vocab_size=vocab_size,
+            frontend=frontend,
+            specaug=specaug,
+            normalize=normalize,
+            preencoder=preencoder,
+            encoder=encoder,
+            postencoder=postencoder,
+            decoder=decoder,
+            ctc=ctc,
+            token_list=token_list,
+            **args.model_conf,
+        )
+    return model
+```
+璇ュ嚱鏁板畾涔変簡鍏蜂綋鐨勬ā鍨嬨�傚浜庝笉鍚岀殑璇煶璇嗗埆妯″瀷锛屽線寰�鍙互鍏辩敤鍚屼竴涓闊宠瘑鍒玚Task`锛岀劧鍚庡湪姝ゅ嚱鏁颁腑瀹氫箟鐗瑰畾鐨勬ā鍨嬨�備緥濡傦紝杩欓噷缁欏嚭鐨勬槸涓�涓爣鍑嗙殑encoder-decoder缁撴瀯鐨勮闊宠瘑鍒ā鍨嬨�傚叿浣撳湴锛屽厛瀹氫箟璇ユā鍨嬬殑鍚勪釜妯″潡锛屽寘鎷琫ncoder锛宒ecoder绛夛紝鐒跺悗鍦ㄥ皢杩欎簺妯″潡缁勫悎鍦ㄤ竴璧峰緱鍒颁竴涓畬鏁寸殑妯″瀷銆傚湪FunASR涓紝妯″瀷闇�瑕佺户鎵縛AbsESPnetModel`锛屽叾鍏蜂綋浠ｇ爜瑙乣funasr/train/abs_espnet_model.py`锛屼富瑕侀渶瑕佸疄鐜扮殑鏄痐forward`鍑芥暟銆�

--
Gitblit v1.9.1