From a49f2c6411637d696e787605ec611f05667e8935 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期四, 28 九月 2023 15:52:14 +0800
Subject: [PATCH] Merge branch 'main' of https://github.com/alibaba-damo-academy/FunASR into main

---
 funasr/runtime/onnxruntime/include/offline-stream.h                                                               |    4 
 funasr/runtime/python/websocket/funasr_wss_client.py                                                              |   11 +
 egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/finetune.py       |    2 
 funasr/runtime/onnxruntime/src/funasrruntime.cpp                                                                  |   13 +
 funasr/runtime/python/websocket/funasr_client_api.py                                                              |    5 
 funasr/runtime/onnxruntime/include/model.h                                                                        |    2 
 egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo.py           |    2 
 funasr/runtime/readme_cn.md                                                                                       |   12 
 funasr/models/decoder/sanm_decoder.py                                                                             |   89 +++++++-
 funasr/runtime/docs/SDK_advanced_guide_online_zh.md                                                               |    7 
 egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/infer.py          |    2 
 egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo_online_v2.py |   44 ++++
 funasr/runtime/onnxruntime/include/tpass-stream.h                                                                 |    4 
 funasr/modules/attention.py                                                                                       |   67 ++++++
 docs/m2met2/Dataset.md                                                                                            |    4 
 funasr/runtime/docs/SDK_tutorial_zh.md                                                                            |   10 
 funasr/runtime/onnxruntime/include/funasrruntime.h                                                                |    3 
 funasr/runtime/onnxruntime/src/precomp.h                                                                          |    4 
 docs/images/wechat.png                                                                                            |    0 
 funasr/datasets/large_datasets/datapipes/batch.py                                                                 |    2 
 funasr/datasets/large_datasets/datapipes/filter.py                                                                |    4 
 funasr/datasets/large_datasets/datapipes/map.py                                                                   |    2 
 fun_text_processing/inverse_text_normalization/en/taggers/money.py                                                |    2 
 docs/m2met2/index.rst                                                                                             |    1 
 funasr/models/encoder/sanm_encoder.py                                                                             |   72 ++++--
 funasr/runtime/onnxruntime/src/offline-stream.cpp                                                                 |    3 
 funasr/runtime/docs/SDK_advanced_guide_offline.md                                                                 |    4 
 funasr/runtime/docs/SDK_advanced_guide_offline_zh.md                                                              |   20 +
 README_zh.md                                                                                                      |    3 
 funasr/runtime/readme.md                                                                                          |   12 
 README.md                                                                                                         |    2 
 funasr/runtime/docs/SDK_advanced_guide_online.md                                                                  |    4 
 funasr/runtime/python/websocket/funasr_wss_server.py                                                              |    8 
 funasr/runtime/onnxruntime/src/tpass-stream.cpp                                                                   |    5 
 funasr/runtime/ios/paraformer_online/paraformer_online.xcodeproj/project.pbxproj                                  |   16 +
 funasr/runtime/onnxruntime/src/paraformer.cpp                                                                     |    2 
 egs_modelscope/asr/TEMPLATE/README.md                                                                             |   11 
 egs_modelscope/asr/TEMPLATE/README_zh.md                                                                          |   11 
 funasr/runtime/docs/SDK_tutorial_online_zh.md                                                                     |   19 +
 egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo_online.py    |    2 
 funasr/bin/asr_inference_launch.py                                                                                |   68 +++++-
 41 files changed, 432 insertions(+), 126 deletions(-)

diff --git a/README.md b/README.md
index 49c5e47..53961f0 100644
--- a/README.md
+++ b/README.md
@@ -60,7 +60,7 @@
 
 |DingTalk group |                     WeChat group                      |
 |:---:|:-----------------------------------------------------:|
-|<div align="left"><img src="docs/images/dingding.jpg" width="250"/> | <img src="docs/images/wechat.png" width="232"/></div> |
+|<div align="left"><img src="docs/images/dingding.jpg" width="250"/> | <img src="docs/images/wechat.png" width="215"/></div> |
 
 ## Contributors
 
diff --git a/README_zh.md b/README_zh.md
index f14a9eb..24b9aa1 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -55,9 +55,10 @@
 ## 鑱旂郴鎴戜滑
 
 濡傛灉鎮ㄥ湪浣跨敤涓亣鍒伴棶棰橈紝鍙互鐩存帴鍦╣ithub椤甸潰鎻怚ssues銆傛杩庤闊冲叴瓒ｇ埍濂借�呮壂鎻忎互涓嬬殑閽夐拤缇ゆ垨鑰呭井淇＄兢浜岀淮鐮佸姞鍏ョぞ鍖虹兢锛岃繘琛屼氦娴佸拰璁ㄨ銆�
+
 |                                  閽夐拤缇�                                  |                          寰俊                           |
 |:---------------------------------------------------------------------:|:-----------------------------------------------------:|
-| <div align="left"><img src="docs/images/dingding.jpg" width="250"/>   | <img src="docs/images/wechat.png" width="232"/></div> |
+| <div align="left"><img src="docs/images/dingding.jpg" width="250"/>   | <img src="docs/images/wechat.png" width="215"/></div> |
 
 ## 绀惧尯璐＄尞鑰�
 
diff --git a/docs/images/wechat.png b/docs/images/wechat.png
index 810cb32..9acf5b9 100644
--- a/docs/images/wechat.png
+++ b/docs/images/wechat.png
Binary files differ
diff --git a/docs/m2met2/Dataset.md b/docs/m2met2/Dataset.md
index a897d67..74548fd 100644
--- a/docs/m2met2/Dataset.md
+++ b/docs/m2met2/Dataset.md
@@ -21,4 +21,6 @@
 The three dataset for training mentioned above can be downloaded at [OpenSLR](https://openslr.org/resources.php). The participants can download via the following links. Particularly, in the baseline we provide convenient data preparation scripts for AliMeeting corpus.
 - [AliMeeting](https://openslr.org/119/)
 - [AISHELL-4](https://openslr.org/111/)
-- [CN-Celeb](https://openslr.org/82/)
\ No newline at end of file
+- [CN-Celeb](https://openslr.org/82/)
+
+Now, the new test set is available [here](https://speech-lab-share-data.oss-cn-shanghai.aliyuncs.com/AliMeeting/openlr/Test_2023_Ali.tar.gz)
diff --git a/docs/m2met2/index.rst b/docs/m2met2/index.rst
index 101b7d5..6567dee 100644
--- a/docs/m2met2/index.rst
+++ b/docs/m2met2/index.rst
@@ -9,6 +9,7 @@
 To advance the current state-of-the-art in multi-talker automatic speech recognition, the M2MeT2.0 challenge proposes a speaker-attributed ASR task, comprising two sub-tracks: fixed and open training conditions.
 To facilitate reproducible research, we provide a comprehensive overview of the dataset, challenge rules, evaluation metrics, and baseline systems. 
 
+Now the new test set contains about 10 hours audio is available. You can download from `here <https://speech-lab-share-data.oss-cn-shanghai.aliyuncs.com/AliMeeting/openlr/Test_2023_Ali.tar.gz>`_
 
 .. toctree::
    :maxdepth: 1
diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md
index a8cb486..4cf6a7e 100644
--- a/egs_modelscope/asr/TEMPLATE/README.md
+++ b/egs_modelscope/asr/TEMPLATE/README.md
@@ -27,15 +27,18 @@
 inference_pipeline = pipeline(
     task=Tasks.auto_speech_recognition,
     model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
-    model_revision='v1.0.6',
+    model_revision='v1.0.7',
     update_model=False,
     mode='paraformer_streaming'
     )
 import soundfile
 speech, sample_rate = soundfile.read("example/asr_example.wav")
 
-chunk_size = [5, 10, 5] #[5, 10, 5] 600ms, [8, 8, 4] 480ms
-param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size}
+chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
+encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
+decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
+param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size,
+              "encoder_chunk_look_back": encoder_chunk_look_back, "decoder_chunk_look_back": decoder_chunk_look_back}
 chunk_stride = chunk_size[1] * 960 # 600ms銆�480ms
 # first chunk, 600ms
 speech_chunk = speech[0:chunk_stride]
@@ -55,7 +58,7 @@
 inference_pipeline = pipeline(
     task=Tasks.auto_speech_recognition,
     model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
-    model_revision='v1.0.6',
+    model_revision='v1.0.7',
     update_model=False,
     mode="paraformer_fake_streaming"
 )
diff --git a/egs_modelscope/asr/TEMPLATE/README_zh.md b/egs_modelscope/asr/TEMPLATE/README_zh.md
index 81e0271..6db310e 100644
--- a/egs_modelscope/asr/TEMPLATE/README_zh.md
+++ b/egs_modelscope/asr/TEMPLATE/README_zh.md
@@ -27,15 +27,18 @@
 inference_pipeline = pipeline(
     task=Tasks.auto_speech_recognition,
     model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
-    model_revision='v1.0.6',
+    model_revision='v1.0.7',
     update_model=False,
     mode='paraformer_streaming'
     )
 import soundfile
 speech, sample_rate = soundfile.read("example/asr_example.wav")
 
-chunk_size = [5, 10, 5] #[5, 10, 5] 600ms, [8, 8, 4] 480ms
-param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size}
+chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
+encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
+decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
+param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size,
+              "encoder_chunk_look_back": encoder_chunk_look_back, "decoder_chunk_look_back": decoder_chunk_look_back}
 chunk_stride = chunk_size[1] * 960 # 600ms銆�480ms
 # first chunk, 600ms
 speech_chunk = speech[0:chunk_stride]
@@ -55,7 +58,7 @@
 inference_pipeline = pipeline(
     task=Tasks.auto_speech_recognition,
     model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
-    model_revision='v1.0.6',
+    model_revision='v1.0.7',
     update_model=False,
     mode="paraformer_fake_streaming"
 )
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo.py
index bef3849..a3d5222 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo.py
@@ -4,7 +4,7 @@
 inference_pipeline = pipeline(
     task=Tasks.auto_speech_recognition,
     model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
-    model_revision='v1.0.6',
+    model_revision='v1.0.7',
     update_model=False,
     mode="paraformer_fake_streaming"
 )
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo_online.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo_online.py
index c1f4afe..d9b5b2d 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo_online.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo_online.py
@@ -14,7 +14,7 @@
 inference_pipeline = pipeline(
     task=Tasks.auto_speech_recognition,
     model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
-    model_revision='v1.0.6',
+    model_revision='v1.0.7',
     update_model=False,
     mode="paraformer_streaming"
 )
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo_online_v2.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo_online_v2.py
new file mode 100644
index 0000000..1f2500d
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo_online_v2.py
@@ -0,0 +1,44 @@
+import os
+import logging
+import torch
+import soundfile
+
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+from modelscope.utils.logger import get_logger
+
+logger = get_logger(log_level=logging.CRITICAL)
+logger.setLevel(logging.CRITICAL)
+
+os.environ["MODELSCOPE_CACHE"] = "./"
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
+    model_revision='v1.0.7',
+    update_model=False,
+    mode="paraformer_streaming"
+)
+
+model_dir = os.path.join(os.environ["MODELSCOPE_CACHE"], "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online")
+speech, sample_rate = soundfile.read(os.path.join(model_dir, "example/asr_example.wav"))
+speech_length = speech.shape[0]
+
+sample_offset = 0
+chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
+encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
+decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
+stride_size =  chunk_size[1] * 960
+param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size, 
+              "encoder_chunk_look_back": encoder_chunk_look_back, "decoder_chunk_look_back": decoder_chunk_look_back}
+final_result = ""
+
+for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)):
+    if sample_offset + stride_size >= speech_length - 1:
+        stride_size = speech_length - sample_offset
+        param_dict["is_final"] = True
+    rec_result = inference_pipeline(audio_in=speech[sample_offset: sample_offset + stride_size],
+                                    param_dict=param_dict)
+    if len(rec_result) != 0:
+        final_result += rec_result['text']
+        print(rec_result)
+print(final_result)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/finetune.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/finetune.py
index 30034aa..fa046d8 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/finetune.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/finetune.py
@@ -14,7 +14,7 @@
     ds_dict = MsDataset.load(params.data_path)
     kwargs = dict(
         model=params.model,
-        model_revision='v1.0.6',
+        model_revision='v1.0.7',
         update_model=False,
         data_dir=ds_dict,
         dataset_type=params.dataset_type,
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/infer.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/infer.py
index 241ebef..0537dda 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/infer.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/infer.py
@@ -11,7 +11,7 @@
         model=args.model,
         output_dir=args.output_dir,
         batch_size=args.batch_size,
-        model_revision='v1.0.6',
+        model_revision='v1.0.7',
         update_model=False,
         mode="paraformer_fake_streaming",
         param_dict={"decoding_model": args.decoding_mode, "hotword": args.hotword_txt}
diff --git a/fun_text_processing/inverse_text_normalization/en/taggers/money.py b/fun_text_processing/inverse_text_normalization/en/taggers/money.py
index 7fdfb96..df6812d 100644
--- a/fun_text_processing/inverse_text_normalization/en/taggers/money.py
+++ b/fun_text_processing/inverse_text_normalization/en/taggers/money.py
@@ -53,7 +53,7 @@
             + pynini.union(
                 pynutil.add_weight(((DAMO_SIGMA - "one") @ cardinal_graph), -0.7) @ add_leading_zero_to_double_digit
                 + delete_space
-                + pynutil.delete("cents"),
+                + (pynutil.delete("cents") | pynutil.delete("cent")),
                 pynini.cross("one", "01") + delete_space + pynutil.delete("cent"),
             )
             + pynutil.insert("\"")
diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index ad657eb..50b9886 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -842,37 +842,72 @@
             data = yaml.load(f, Loader=yaml.Loader)
         return data
 
-    def _prepare_cache(cache: dict = {}, chunk_size=[5, 10, 5], batch_size=1):
+    def _prepare_cache(cache: dict = {}, chunk_size=[5, 10, 5], encoder_chunk_look_back=0,
+                       decoder_chunk_look_back=0, batch_size=1):
         if len(cache) > 0:
             return cache
         config = _read_yaml(asr_train_config)
         enc_output_size = config["encoder_conf"]["output_size"]
         feats_dims = config["frontend_conf"]["n_mels"] * config["frontend_conf"]["lfr_m"]
         cache_en = {"start_idx": 0, "cif_hidden": torch.zeros((batch_size, 1, enc_output_size)),
-                    "cif_alphas": torch.zeros((batch_size, 1)), "chunk_size": chunk_size, "last_chunk": False,
+                    "cif_alphas": torch.zeros((batch_size, 1)), "chunk_size": chunk_size,
+                    "encoder_chunk_look_back": encoder_chunk_look_back, "last_chunk": False, "opt": None,
                     "feats": torch.zeros((batch_size, chunk_size[0] + chunk_size[2], feats_dims)), "tail_chunk": False}
         cache["encoder"] = cache_en
 
-        cache_de = {"decode_fsmn": None}
+        cache_de = {"decode_fsmn": None, "decoder_chunk_look_back": decoder_chunk_look_back, "opt": None, "chunk_size": chunk_size}
         cache["decoder"] = cache_de
 
         return cache
 
-    def _cache_reset(cache: dict = {}, chunk_size=[5, 10, 5], batch_size=1):
+    def _cache_reset(cache: dict = {}, chunk_size=[5, 10, 5], encoder_chunk_look_back=0,
+                     decoder_chunk_look_back=0, batch_size=1):
         if len(cache) > 0:
             config = _read_yaml(asr_train_config)
             enc_output_size = config["encoder_conf"]["output_size"]
             feats_dims = config["frontend_conf"]["n_mels"] * config["frontend_conf"]["lfr_m"]
             cache_en = {"start_idx": 0, "cif_hidden": torch.zeros((batch_size, 1, enc_output_size)),
-                        "cif_alphas": torch.zeros((batch_size, 1)), "chunk_size": chunk_size, "last_chunk": False,
-                        "feats": torch.zeros((batch_size, chunk_size[0] + chunk_size[2], feats_dims)),
-                        "tail_chunk": False}
+                        "cif_alphas": torch.zeros((batch_size, 1)), "chunk_size": chunk_size,
+                        "encoder_chunk_look_back": encoder_chunk_look_back, "last_chunk": False, "opt": None,
+                        "feats": torch.zeros((batch_size, chunk_size[0] + chunk_size[2], feats_dims)), "tail_chunk": False}
             cache["encoder"] = cache_en
 
-            cache_de = {"decode_fsmn": None}
+            cache_de = {"decode_fsmn": None, "decoder_chunk_look_back": decoder_chunk_look_back, "opt": None, "chunk_size": chunk_size}
             cache["decoder"] = cache_de
 
         return cache
+
+    #def _prepare_cache(cache: dict = {}, chunk_size=[5, 10, 5], batch_size=1):
+    #    if len(cache) > 0:
+    #        return cache
+    #    config = _read_yaml(asr_train_config)
+    #    enc_output_size = config["encoder_conf"]["output_size"]
+    #    feats_dims = config["frontend_conf"]["n_mels"] * config["frontend_conf"]["lfr_m"]
+    #    cache_en = {"start_idx": 0, "cif_hidden": torch.zeros((batch_size, 1, enc_output_size)),
+    #                "cif_alphas": torch.zeros((batch_size, 1)), "chunk_size": chunk_size, "last_chunk": False,
+    #                "feats": torch.zeros((batch_size, chunk_size[0] + chunk_size[2], feats_dims)), "tail_chunk": False}
+    #    cache["encoder"] = cache_en
+
+    #    cache_de = {"decode_fsmn": None}
+    #    cache["decoder"] = cache_de
+
+    #    return cache
+
+    #def _cache_reset(cache: dict = {}, chunk_size=[5, 10, 5], batch_size=1):
+    #    if len(cache) > 0:
+    #        config = _read_yaml(asr_train_config)
+    #        enc_output_size = config["encoder_conf"]["output_size"]
+    #        feats_dims = config["frontend_conf"]["n_mels"] * config["frontend_conf"]["lfr_m"]
+    #        cache_en = {"start_idx": 0, "cif_hidden": torch.zeros((batch_size, 1, enc_output_size)),
+    #                    "cif_alphas": torch.zeros((batch_size, 1)), "chunk_size": chunk_size, "last_chunk": False,
+    #                    "feats": torch.zeros((batch_size, chunk_size[0] + chunk_size[2], feats_dims)),
+    #                    "tail_chunk": False}
+    #        cache["encoder"] = cache_en
+
+    #        cache_de = {"decode_fsmn": None}
+    #        cache["decoder"] = cache_de
+
+    #    return cache
 
     def _forward(
             data_path_and_name_and_type,
@@ -901,24 +936,34 @@
         is_final = False
         cache = {}
         chunk_size = [5, 10, 5]
+        encoder_chunk_look_back = 0
+        decoder_chunk_look_back = 0
         if param_dict is not None and "cache" in param_dict:
             cache = param_dict["cache"]
         if param_dict is not None and "is_final" in param_dict:
             is_final = param_dict["is_final"]
         if param_dict is not None and "chunk_size" in param_dict:
             chunk_size = param_dict["chunk_size"]
+        if param_dict is not None and "encoder_chunk_look_back" in param_dict:
+            encoder_chunk_look_back = param_dict["encoder_chunk_look_back"]
+            if encoder_chunk_look_back > 0:
+                chunk_size[0] = 0
+        if param_dict is not None and "decoder_chunk_look_back" in param_dict:
+            decoder_chunk_look_back = param_dict["decoder_chunk_look_back"]
 
         # 7 .Start for-loop
         # FIXME(kamo): The output format should be discussed about
         raw_inputs = torch.unsqueeze(raw_inputs, axis=0)
         asr_result_list = []
-        cache = _prepare_cache(cache, chunk_size=chunk_size, batch_size=1)
+        cache = _prepare_cache(cache, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, 
+                               decoder_chunk_look_back=decoder_chunk_look_back, batch_size=1)
         item = {}
         if data_path_and_name_and_type is not None and data_path_and_name_and_type[2] == "sound":
             sample_offset = 0
             speech_length = raw_inputs.shape[1]
             stride_size = chunk_size[1] * 960
-            cache = _prepare_cache(cache, chunk_size=chunk_size, batch_size=1)
+            cache = _prepare_cache(cache, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, 
+                                   decoder_chunk_look_back=decoder_chunk_look_back, batch_size=1)
             final_result = ""
             for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)):
                 if sample_offset + stride_size >= speech_length - 1:
@@ -939,7 +984,8 @@
 
         asr_result_list.append(item)
         if is_final:
-            cache = _cache_reset(cache, chunk_size=chunk_size, batch_size=1)
+            cache = _cache_reset(cache, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, 
+                                 decoder_chunk_look_back=decoder_chunk_look_back, batch_size=1)
         return asr_result_list
 
     return _forward
diff --git a/funasr/datasets/large_datasets/datapipes/batch.py b/funasr/datasets/large_datasets/datapipes/batch.py
index 8ec43e9..35e5dba 100644
--- a/funasr/datasets/large_datasets/datapipes/batch.py
+++ b/funasr/datasets/large_datasets/datapipes/batch.py
@@ -39,7 +39,7 @@
         self.batch_mode = batch_mode
 
     def set_epoch(self, epoch):
-        self.epoch = epoch
+        self.datapipe.set_epoch(epoch)
 
     def __iter__(self):
         buffer = []
diff --git a/funasr/datasets/large_datasets/datapipes/filter.py b/funasr/datasets/large_datasets/datapipes/filter.py
index e79934d..6fe7153 100644
--- a/funasr/datasets/large_datasets/datapipes/filter.py
+++ b/funasr/datasets/large_datasets/datapipes/filter.py
@@ -13,7 +13,7 @@
         self.fn = fn
 
     def set_epoch(self, epoch):
-        self.epoch = epoch
+        self.datapipe.set_epoch(epoch)
 
     def __iter__(self):
         assert callable(self.fn)
@@ -21,4 +21,4 @@
             if self.fn(data):
                 yield data
             else:
-                continue
\ No newline at end of file
+                continue
diff --git a/funasr/datasets/large_datasets/datapipes/map.py b/funasr/datasets/large_datasets/datapipes/map.py
index 6e0168d..dfcd6a0 100644
--- a/funasr/datasets/large_datasets/datapipes/map.py
+++ b/funasr/datasets/large_datasets/datapipes/map.py
@@ -14,7 +14,7 @@
         self.fn = fn
 
     def set_epoch(self, epoch):
-        self.epoch = epoch
+        self.datapipe.set_epoch(epoch)
 
     def __iter__(self):
         assert callable(self.fn)
diff --git a/funasr/models/decoder/sanm_decoder.py b/funasr/models/decoder/sanm_decoder.py
index c12e098..ff35e46 100644
--- a/funasr/models/decoder/sanm_decoder.py
+++ b/funasr/models/decoder/sanm_decoder.py
@@ -105,7 +105,7 @@
 
         return x, tgt_mask, memory, memory_mask, cache
 
-    def forward_chunk(self, tgt, tgt_mask, memory, memory_mask=None, cache=None):
+    def forward_one_step(self, tgt, tgt_mask, memory, memory_mask=None, cache=None):
         """Compute decoded features.
 
         Args:
@@ -147,6 +147,47 @@
 
 
         return x, tgt_mask, memory, memory_mask, cache
+
+    def forward_chunk(self, tgt, memory, fsmn_cache=None, opt_cache=None, chunk_size=None, look_back=0):
+        """Compute decoded features.
+
+        Args:
+            tgt (torch.Tensor): Input tensor (#batch, maxlen_out, size).
+            tgt_mask (torch.Tensor): Mask for input tensor (#batch, maxlen_out).
+            memory (torch.Tensor): Encoded memory, float32 (#batch, maxlen_in, size).
+            memory_mask (torch.Tensor): Encoded memory mask (#batch, maxlen_in).
+            cache (List[torch.Tensor]): List of cached tensors.
+                Each tensor shape should be (#batch, maxlen_out - 1, size).
+
+        Returns:
+            torch.Tensor: Output tensor(#batch, maxlen_out, size).
+            torch.Tensor: Mask for output tensor (#batch, maxlen_out).
+            torch.Tensor: Encoded memory (#batch, maxlen_in, size).
+            torch.Tensor: Encoded memory mask (#batch, maxlen_in).
+
+        """
+        residual = tgt
+        if self.normalize_before:
+            tgt = self.norm1(tgt)
+        tgt = self.feed_forward(tgt)
+
+        x = tgt
+        if self.self_attn:
+            if self.normalize_before:
+                tgt = self.norm2(tgt)
+            x, fsmn_cache = self.self_attn(tgt, None, fsmn_cache)
+            x = residual + self.dropout(x)
+
+        if self.src_attn is not None:
+            residual = x
+            if self.normalize_before:
+                x = self.norm3(x)
+
+            x, opt_cache = self.src_attn.forward_chunk(x, memory, opt_cache, chunk_size, look_back)
+            x = residual + x
+
+        return x, memory, fsmn_cache, opt_cache
+
 
 class FsmnDecoderSCAMAOpt(BaseTransformerDecoder):
     """
@@ -397,7 +438,7 @@
         for i in range(self.att_layer_num):
             decoder = self.decoders[i]
             c = cache[i]
-            x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_chunk(
+            x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_one_step(
                 x, tgt_mask, memory, memory_mask, cache=c
             )
             new_cache.append(c_ret)
@@ -407,13 +448,13 @@
                 j = i + self.att_layer_num
                 decoder = self.decoders2[i]
                 c = cache[j]
-                x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_chunk(
+                x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_one_step(
                     x, tgt_mask, memory, memory_mask, cache=c
                 )
                 new_cache.append(c_ret)
 
         for decoder in self.decoders3:
-            x, tgt_mask, memory, memory_mask, _ = decoder.forward_chunk(
+            x, tgt_mask, memory, memory_mask, _ = decoder.forward_one_step(
                 x, tgt_mask, memory, None, cache=None
             )
 
@@ -837,6 +878,7 @@
         lora_rank: int = 8,
         lora_alpha: int = 16,
         lora_dropout: float = 0.1,
+        chunk_multiply_factor: tuple = (1,),
         tf2torch_tensor_name_prefix_torch: str = "decoder",
         tf2torch_tensor_name_prefix_tf: str = "seq2seq/decoder",
     ):
@@ -929,6 +971,7 @@
         )
         self.tf2torch_tensor_name_prefix_torch = tf2torch_tensor_name_prefix_torch
         self.tf2torch_tensor_name_prefix_tf = tf2torch_tensor_name_prefix_tf
+        self.chunk_multiply_factor = chunk_multiply_factor
 
     def forward(
         self,
@@ -1020,35 +1063,43 @@
             cache_layer_num = len(self.decoders)
             if self.decoders2 is not None:
                 cache_layer_num += len(self.decoders2)
-            new_cache = [None] * cache_layer_num
+            fsmn_cache = [None] * cache_layer_num
         else:
-            new_cache = cache["decode_fsmn"]
+            fsmn_cache = cache["decode_fsmn"]
+
+        if cache["opt"] is None:
+            cache_layer_num = len(self.decoders)
+            opt_cache = [None] * cache_layer_num
+        else:
+            opt_cache = cache["opt"]
+
         for i in range(self.att_layer_num):
             decoder = self.decoders[i]
-            x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_chunk(
-                x, None, memory, None, cache=new_cache[i]
+            x, memory, fsmn_cache[i], opt_cache[i] = decoder.forward_chunk(
+                x, memory, fsmn_cache=fsmn_cache[i], opt_cache=opt_cache[i],
+                chunk_size=cache["chunk_size"], look_back=cache["decoder_chunk_look_back"]
             )
-            new_cache[i] = c_ret
 
         if self.num_blocks - self.att_layer_num > 1:
             for i in range(self.num_blocks - self.att_layer_num):
                 j = i + self.att_layer_num
                 decoder = self.decoders2[i]
-                x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_chunk(
-                    x, None, memory, None, cache=new_cache[j]
+                x, memory, fsmn_cache[j], _  = decoder.forward_chunk(
+                    x, memory, fsmn_cache=fsmn_cache[j]
                 )
-                new_cache[j] = c_ret
 
         for decoder in self.decoders3:
-
-            x, tgt_mask, memory, memory_mask, _ = decoder.forward_chunk(
-                x, None, memory, None, cache=None
+            x, memory, _, _ = decoder.forward_chunk(
+                x, memory
             )
         if self.normalize_before:
             x = self.after_norm(x)
         if self.output_layer is not None:
             x = self.output_layer(x)
-        cache["decode_fsmn"] = new_cache
+
+        cache["decode_fsmn"] = fsmn_cache
+        if cache["decoder_chunk_look_back"] > 0 or cache["decoder_chunk_look_back"] == -1:
+            cache["opt"] = opt_cache
         return x
 
     def forward_one_step(
@@ -1082,7 +1133,7 @@
         for i in range(self.att_layer_num):
             decoder = self.decoders[i]
             c = cache[i]
-            x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_chunk(
+            x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_one_step(
                 x, tgt_mask, memory, None, cache=c
             )
             new_cache.append(c_ret)
@@ -1092,14 +1143,14 @@
                 j = i + self.att_layer_num
                 decoder = self.decoders2[i]
                 c = cache[j]
-                x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_chunk(
+                x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_one_step(
                     x, tgt_mask, memory, None, cache=c
                 )
                 new_cache.append(c_ret)
 
         for decoder in self.decoders3:
 
-            x, tgt_mask, memory, memory_mask, _ = decoder.forward_chunk(
+            x, tgt_mask, memory, memory_mask, _ = decoder.forward_one_step(
                 x, tgt_mask, memory, None, cache=None
             )
 
diff --git a/funasr/models/encoder/sanm_encoder.py b/funasr/models/encoder/sanm_encoder.py
index 9e27d4a..c15343e 100644
--- a/funasr/models/encoder/sanm_encoder.py
+++ b/funasr/models/encoder/sanm_encoder.py
@@ -114,8 +114,44 @@
         if not self.normalize_before:
             x = self.norm2(x)
 
-
         return x, mask, cache, mask_shfit_chunk, mask_att_chunk_encoder
+
+    def forward_chunk(self, x, cache=None, chunk_size=None, look_back=0):
+        """Compute encoded features.
+
+        Args:
+            x_input (torch.Tensor): Input tensor (#batch, time, size).
+            mask (torch.Tensor): Mask tensor for the input (#batch, time).
+            cache (torch.Tensor): Cache tensor of the input (#batch, time - 1, size).
+
+        Returns:
+            torch.Tensor: Output tensor (#batch, time, size).
+            torch.Tensor: Mask tensor (#batch, time).
+
+        """
+
+        residual = x
+        if self.normalize_before:
+            x = self.norm1(x)
+
+        if self.in_size == self.size:
+            attn, cache = self.self_attn.forward_chunk(x, cache, chunk_size, look_back)
+            x = residual + attn
+        else:
+            x, cache = self.self_attn.forward_chunk(x, cache, chunk_size, look_back)
+
+        if not self.normalize_before:
+            x = self.norm1(x)
+
+        residual = x
+        if self.normalize_before:
+            x = self.norm2(x)
+        x = residual + self.feed_forward(x)
+        if not self.normalize_before:
+            x = self.norm2(x)
+
+        return x, cache
+
 
 class SANMEncoder(AbsEncoder):
     """
@@ -841,7 +877,6 @@
                       xs_pad: torch.Tensor,
                       ilens: torch.Tensor,
                       cache: dict = None,
-                      ctc: CTC = None,
                       ):
         xs_pad *= self.output_size() ** 0.5
         if self.embed is None:
@@ -852,34 +887,25 @@
             xs_pad = to_device(cache["feats"], device=xs_pad.device)
         else:
             xs_pad = self._add_overlap_chunk(xs_pad, cache)
-        encoder_outs = self.encoders0(xs_pad, None, None, None, None)
-        xs_pad, masks = encoder_outs[0], encoder_outs[1]
-        intermediate_outs = []
-        if len(self.interctc_layer_idx) == 0:
-            encoder_outs = self.encoders(xs_pad, None, None, None, None)
-            xs_pad, masks = encoder_outs[0], encoder_outs[1]
+        if cache["opt"] is None:
+            cache_layer_num = len(self.encoders0) + len(self.encoders)
+            new_cache = [None] * cache_layer_num
         else:
-            for layer_idx, encoder_layer in enumerate(self.encoders):
-                encoder_outs = encoder_layer(xs_pad, None, None, None, None)
-                xs_pad, masks = encoder_outs[0], encoder_outs[1]
-                if layer_idx + 1 in self.interctc_layer_idx:
-                    encoder_out = xs_pad
+            new_cache = cache["opt"]
 
-                    # intermediate outputs are also normalized
-                    if self.normalize_before:
-                        encoder_out = self.after_norm(encoder_out)
+        for layer_idx, encoder_layer in enumerate(self.encoders0):
+            encoder_outs = encoder_layer.forward_chunk(xs_pad, new_cache[layer_idx], cache["chunk_size"], cache["encoder_chunk_look_back"])
+            xs_pad, new_cache[0] = encoder_outs[0], encoder_outs[1]
 
-                    intermediate_outs.append((layer_idx + 1, encoder_out))
-
-                    if self.interctc_use_conditioning:
-                        ctc_out = ctc.softmax(encoder_out)
-                        xs_pad = xs_pad + self.conditioning_layer(ctc_out)
+        for layer_idx, encoder_layer in enumerate(self.encoders):
+            encoder_outs = encoder_layer.forward_chunk(xs_pad, new_cache[layer_idx+len(self.encoders0)], cache["chunk_size"], cache["encoder_chunk_look_back"])
+            xs_pad, new_cache[layer_idx+len(self.encoders0)] = encoder_outs[0], encoder_outs[1]
 
         if self.normalize_before:
             xs_pad = self.after_norm(xs_pad)
+        if cache["encoder_chunk_look_back"] > 0 or cache["encoder_chunk_look_back"] == -1:
+            cache["opt"] = new_cache
 
-        if len(intermediate_outs) > 0:
-            return (xs_pad, intermediate_outs), None, None
         return xs_pad, ilens, None
 
     def gen_tf2torch_map_dict(self):
diff --git a/funasr/modules/attention.py b/funasr/modules/attention.py
index ab59493..b007d58 100644
--- a/funasr/modules/attention.py
+++ b/funasr/modules/attention.py
@@ -456,6 +456,44 @@
         att_outs = self.forward_attention(v_h, scores, mask, mask_att_chunk_encoder)
         return att_outs + fsmn_memory
 
+    def forward_chunk(self, x, cache=None, chunk_size=None, look_back=0):
+        """Compute scaled dot product attention.
+
+        Args:
+            query (torch.Tensor): Query tensor (#batch, time1, size).
+            key (torch.Tensor): Key tensor (#batch, time2, size).
+            value (torch.Tensor): Value tensor (#batch, time2, size).
+            mask (torch.Tensor): Mask tensor (#batch, 1, time2) or
+                (#batch, time1, time2).
+
+        Returns:
+            torch.Tensor: Output tensor (#batch, time1, d_model).
+
+        """
+        q_h, k_h, v_h, v = self.forward_qkv(x)
+        if chunk_size is not None and look_back > 0 or look_back == -1:
+            if cache is not None:
+                k_h_stride = k_h[:, :, :-(chunk_size[2]), :]
+                v_h_stride = v_h[:, :, :-(chunk_size[2]), :]
+                k_h = torch.cat((cache["k"], k_h), dim=2)
+                v_h = torch.cat((cache["v"], v_h), dim=2)
+
+                cache["k"] = torch.cat((cache["k"], k_h_stride), dim=2)
+                cache["v"] = torch.cat((cache["v"], v_h_stride), dim=2)
+                if look_back != -1:
+                    cache["k"] = cache["k"][:, :, -(look_back * chunk_size[1]):, :]
+                    cache["v"] = cache["v"][:, :, -(look_back * chunk_size[1]):, :]
+            else:
+                cache_tmp = {"k": k_h[:, :, :-(chunk_size[2]), :],
+                             "v": v_h[:, :, :-(chunk_size[2]), :]}
+                cache = cache_tmp
+        fsmn_memory = self.forward_fsmn(v, None)
+        q_h = q_h * self.d_k ** (-0.5)
+        scores = torch.matmul(q_h, k_h.transpose(-2, -1))
+        att_outs = self.forward_attention(v_h, scores, None)
+        return att_outs + fsmn_memory, cache
+
+
 class MultiHeadedAttentionSANMwithMask(MultiHeadedAttentionSANM):
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
@@ -667,6 +705,35 @@
         scores = torch.matmul(q_h, k_h.transpose(-2, -1))
         return self.forward_attention(v_h, scores, memory_mask)
 
+    def forward_chunk(self, x, memory, cache=None, chunk_size=None, look_back=0):
+        """Compute scaled dot product attention.
+
+        Args:
+            query (torch.Tensor): Query tensor (#batch, time1, size).
+            key (torch.Tensor): Key tensor (#batch, time2, size).
+            value (torch.Tensor): Value tensor (#batch, time2, size).
+            mask (torch.Tensor): Mask tensor (#batch, 1, time2) or
+                (#batch, time1, time2).
+
+        Returns:
+            torch.Tensor: Output tensor (#batch, time1, d_model).
+
+        """
+        q_h, k_h, v_h = self.forward_qkv(x, memory)
+        if chunk_size is not None and look_back > 0:
+            if cache is not None:
+                k_h = torch.cat((cache["k"], k_h), dim=2)
+                v_h = torch.cat((cache["v"], v_h), dim=2)
+                cache["k"] = k_h[:, :, -(look_back * chunk_size[1]):, :]
+                cache["v"] = v_h[:, :, -(look_back * chunk_size[1]):, :]
+            else:
+                cache_tmp = {"k": k_h[:, :, -(look_back * chunk_size[1]):, :],
+                             "v": v_h[:, :, -(look_back * chunk_size[1]):, :]}
+                cache = cache_tmp
+        q_h = q_h * self.d_k ** (-0.5)
+        scores = torch.matmul(q_h, k_h.transpose(-2, -1))
+        return self.forward_attention(v_h, scores, None), cache
+
 
 class MultiHeadSelfAttention(nn.Module):
     """Multi-Head Attention layer.
diff --git a/funasr/runtime/docs/SDK_advanced_guide_offline.md b/funasr/runtime/docs/SDK_advanced_guide_offline.md
index c839e77..63276eb 100644
--- a/funasr/runtime/docs/SDK_advanced_guide_offline.md
+++ b/funasr/runtime/docs/SDK_advanced_guide_offline.md
@@ -36,9 +36,9 @@
 Use the following command to pull and launch the Docker image for the FunASR runtime-SDK:
 
 ```shell
-sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.2.1
+sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.2.2
 
-sudo docker run -p 10095:10095 -it --privileged=true -v /root:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.2.1
+sudo docker run -p 10095:10095 -it --privileged=true -v /root:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.2.2
 ```
 
 Introduction to command parameters: 
diff --git a/funasr/runtime/docs/SDK_advanced_guide_offline_zh.md b/funasr/runtime/docs/SDK_advanced_guide_offline_zh.md
index 282ec4c..09f4cdc 100644
--- a/funasr/runtime/docs/SDK_advanced_guide_offline_zh.md
+++ b/funasr/runtime/docs/SDK_advanced_guide_offline_zh.md
@@ -22,9 +22,12 @@
 閫氳繃涓嬭堪鍛戒护鎷夊彇骞跺惎鍔‵unASR runtime-SDK鐨刣ocker闀滃儚锛�
 
 ```shell
-sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.2.1
+sudo docker pull \
+  registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.2.2
 mkdir -p ./funasr-runtime-resources/models
-sudo docker run -p 10095:10095 -it --privileged=true -v ./funasr-runtime-resources/models:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.2.1
+sudo docker run -p 10095:10095 -it --privileged=true \
+  -v ./funasr-runtime-resources/models:/workspace/models \
+  registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.2.2
 ```
 濡傛灉鎮ㄦ病鏈夊畨瑁卍ocker锛屽彲鍙傝�僛Docker瀹夎](#Docker瀹夎)
 
@@ -100,18 +103,20 @@
 鑻ユ兂鐩存帴杩愯client杩涜娴嬭瘯锛屽彲鍙傝�冨涓嬬畝鏄撹鏄庯紝浠ython鐗堟湰涓轰緥锛�
 
 ```shell
-python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --output_dir "./results"
+python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline \
+        --audio_in "../audio/asr_example.wav" --output_dir "./results"
 ```
 
 鍛戒护鍙傛暟璇存槑锛�
 ```text
---host 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛岄渶瑕佹敼涓洪儴缃叉満鍣╥p
+--host 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛�
+       闇�瑕佹敼涓洪儴缃叉満鍣╥p
 --port 10095 閮ㄧ讲绔彛鍙�
 --mode offline琛ㄧず绂荤嚎鏂囦欢杞啓
 --audio_in 闇�瑕佽繘琛岃浆鍐欑殑闊抽鏂囦欢锛屾敮鎸佹枃浠惰矾寰勶紝鏂囦欢鍒楄〃wav.scp
 --thread_num 璁剧疆骞跺彂鍙戦�佺嚎绋嬫暟锛岄粯璁や负1
 --ssl 璁剧疆鏄惁寮�鍚痵sl璇佷功鏍￠獙锛岄粯璁�1寮�鍚紝璁剧疆涓�0鍏抽棴
---hotword 濡傛灉妯″瀷涓虹儹璇嶆ā鍨嬶紝鍙互璁剧疆鐑瘝: *.txt(姣忚涓�涓儹璇�) 鎴栬�呯┖鏍煎垎闅旂殑鐑瘝瀛楃涓� (could be: 闃块噷宸村反 杈炬懇闄�)
+--hotword 濡傛灉妯″瀷涓虹儹璇嶆ā鍨嬶紝鍙互璁剧疆鐑瘝: *.txt(姣忚涓�涓儹璇�) 鎴栬�呯┖鏍煎垎闅旂殑鐑瘝瀛楃涓�(闃块噷宸村反 杈炬懇闄�)
 --use_itn 璁剧疆鏄惁浣跨敤itn锛岄粯璁�1寮�鍚紝璁剧疆涓�0鍏抽棴
 ```
 
@@ -124,10 +129,11 @@
 鍛戒护鍙傛暟璇存槑锛�
 
 ```text
---server-ip 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛岄渶瑕佹敼涓洪儴缃叉満鍣╥p
+--server-ip 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛�
+            闇�瑕佹敼涓洪儴缃叉満鍣╥p
 --port 10095 閮ㄧ讲绔彛鍙�
 --wav-path 闇�瑕佽繘琛岃浆鍐欑殑闊抽鏂囦欢锛屾敮鎸佹枃浠惰矾寰�
---hotword 濡傛灉妯″瀷涓虹儹璇嶆ā鍨嬶紝鍙互璁剧疆鐑瘝: *.txt(姣忚涓�涓儹璇�) 鎴栬�呯┖鏍煎垎闅旂殑鐑瘝瀛楃涓� (could be: 闃块噷宸村反 杈炬懇闄�)
+--hotword 濡傛灉妯″瀷涓虹儹璇嶆ā鍨嬶紝鍙互璁剧疆鐑瘝: *.txt(姣忚涓�涓儹璇�) 鎴栬�呯┖鏍煎垎闅旂殑鐑瘝瀛楃涓� (闃块噷宸村反 杈炬懇闄�)
 --use-itn 璁剧疆鏄惁浣跨敤itn锛岄粯璁�1寮�鍚紝璁剧疆涓�0鍏抽棴
 ```
 
diff --git a/funasr/runtime/docs/SDK_advanced_guide_online.md b/funasr/runtime/docs/SDK_advanced_guide_online.md
index e8a8e8c..204e544 100644
--- a/funasr/runtime/docs/SDK_advanced_guide_online.md
+++ b/funasr/runtime/docs/SDK_advanced_guide_online.md
@@ -8,9 +8,9 @@
 Use the following command to pull and start the FunASR software package docker image:
 
 ```shell
-sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.1
+sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.2
 mkdir -p ./funasr-runtime-resources/models
-sudo docker run -p 10095:10095 -it --privileged=true -v ./funasr-runtime-resources/models:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.1
+sudo docker run -p 10095:10095 -it --privileged=true -v ./funasr-runtime-resources/models:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.2
 ```
 If you do not have Docker installed, please refer to [Docker Installation](https://alibaba-damo-academy.github.io/FunASR/en/installation/docker.html)
 
diff --git a/funasr/runtime/docs/SDK_advanced_guide_online_zh.md b/funasr/runtime/docs/SDK_advanced_guide_online_zh.md
index e9089cc..52f325f 100644
--- a/funasr/runtime/docs/SDK_advanced_guide_online_zh.md
+++ b/funasr/runtime/docs/SDK_advanced_guide_online_zh.md
@@ -11,9 +11,12 @@
 閫氳繃涓嬭堪鍛戒护鎷夊彇骞跺惎鍔‵unASR杞欢鍖呯殑docker闀滃儚锛�
 
 ```shell
-sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.1
+sudo docker pull \
+  registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.2
 mkdir -p ./funasr-runtime-resources/models
-sudo docker run -p 10095:10095 -it --privileged=true -v ./funasr-runtime-resources/models:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.1
+sudo docker run -p 10095:10095 -it --privileged=true \
+  -v ./funasr-runtime-resources/models:/workspace/models \
+  registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.2
 ```
 濡傛灉鎮ㄦ病鏈夊畨瑁卍ocker锛屽彲鍙傝�僛Docker瀹夎](https://alibaba-damo-academy.github.io/FunASR/en/installation/docker_zh.html)
 
diff --git a/funasr/runtime/docs/SDK_tutorial_online_zh.md b/funasr/runtime/docs/SDK_tutorial_online_zh.md
index afcca4b..f0d447a 100644
--- a/funasr/runtime/docs/SDK_tutorial_online_zh.md
+++ b/funasr/runtime/docs/SDK_tutorial_online_zh.md
@@ -67,34 +67,39 @@
 
 鍛戒护鍙傛暟璇存槑锛�
 ```text
---host 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛岄渶瑕佹敼涓洪儴缃叉満鍣╥p
+--host 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛�
+       闇�瑕佹敼涓洪儴缃叉満鍣╥p
 --port 10095 閮ㄧ讲绔彛鍙�
---mode锛歚offline`琛ㄧず鎺ㄧ悊妯″紡涓轰竴鍙ヨ瘽璇嗗埆锛沗online`琛ㄧず鎺ㄧ悊妯″紡涓哄疄鏃惰闊宠瘑鍒紱`2pass`琛ㄧず涓哄疄鏃惰闊宠瘑鍒紝骞朵笖璇磋瘽鍙ュ熬閲囩敤绂荤嚎妯″瀷杩涜绾犻敊銆�
+--mode锛歚offline`琛ㄧず鎺ㄧ悊妯″紡涓轰竴鍙ヨ瘽璇嗗埆锛沗online`琛ㄧず鎺ㄧ悊妯″紡涓哄疄鏃惰闊宠瘑鍒紱`2pass`琛ㄧず涓哄疄鏃惰闊宠瘑鍒紝
+       骞朵笖璇磋瘽鍙ュ熬閲囩敤绂荤嚎妯″瀷杩涜绾犻敊銆�
 --chunk_size锛氳〃绀烘祦寮忔ā鍨媗atency閰嶇疆`[5,10,5]`锛岃〃绀哄綋鍓嶉煶棰戣В鐮佺墖娈典负600ms锛屽苟涓斿洖鐪�300ms锛屽彸鐪�300ms銆�
 --audio_in 闇�瑕佽繘琛岃浆鍐欑殑闊抽鏂囦欢锛屾敮鎸佹枃浠惰矾寰勶紝鏂囦欢鍒楄〃wav.scp
 --thread_num 璁剧疆骞跺彂鍙戦�佺嚎绋嬫暟锛岄粯璁や负1
 --ssl 璁剧疆鏄惁寮�鍚痵sl璇佷功鏍￠獙锛岄粯璁�1寮�鍚紝璁剧疆涓�0鍏抽棴+
---hotword 濡傛灉妯″瀷涓虹儹璇嶆ā鍨嬶紝鍙互璁剧疆鐑瘝: *.txt(姣忚涓�涓儹璇�) 鎴栬�呯┖鏍煎垎闅旂殑鐑瘝瀛楃涓� (could be: 闃块噷宸村反 杈炬懇闄�)
+--hotword 濡傛灉妯″瀷涓虹儹璇嶆ā鍨嬶紝鍙互璁剧疆鐑瘝: *.txt(姣忚涓�涓儹璇�) 鎴栬�呯┖鏍煎垎闅旂殑鐑瘝瀛楃涓� (闃块噷宸村反 杈炬懇闄�)
 --use_itn 璁剧疆鏄惁浣跨敤itn锛岄粯璁�1寮�鍚紝璁剧疆涓�0鍏抽棴
 ```
 
 ### cpp-client
 杩涘叆samples/cpp鐩綍鍚庯紝鍙互鐢╟pp杩涜娴嬭瘯锛屾寚浠ゅ涓嬶細
 ```shell
-./funasr-wss-client-2pass --server-ip 127.0.0.1 --port 10095 --mode 2pass --wav-path ../audio/asr_example.wav
+./funasr-wss-client-2pass --server-ip 127.0.0.1 --port 10095 --mode 2pass \
+   --wav-path ../audio/asr_example.wav
 ```
 
 鍛戒护鍙傛暟璇存槑锛�
 
 ```text
---server-ip 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛岄渶瑕佹敼涓洪儴缃叉満鍣╥p
+--server-ip 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛�
+            闇�瑕佹敼涓洪儴缃叉満鍣╥p
 --port 10095 閮ㄧ讲绔彛鍙�
---mode锛歚offline`琛ㄧず鎺ㄧ悊妯″紡涓轰竴鍙ヨ瘽璇嗗埆锛沗online`琛ㄧず鎺ㄧ悊妯″紡涓哄疄鏃惰闊宠瘑鍒紱`2pass`琛ㄧず涓哄疄鏃惰闊宠瘑鍒紝骞朵笖璇磋瘽鍙ュ熬閲囩敤绂荤嚎妯″瀷杩涜绾犻敊銆�
+--mode锛歚offline`琛ㄧず鎺ㄧ悊妯″紡涓轰竴鍙ヨ瘽璇嗗埆锛沗online`琛ㄧず鎺ㄧ悊妯″紡涓哄疄鏃惰闊宠瘑鍒紱`2pass`琛ㄧず涓哄疄鏃惰闊宠瘑鍒紝
+        骞朵笖璇磋瘽鍙ュ熬閲囩敤绂荤嚎妯″瀷杩涜绾犻敊銆�
 --chunk-size锛氳〃绀烘祦寮忔ā鍨媗atency閰嶇疆`[5,10,5]`锛岃〃绀哄綋鍓嶉煶棰戣В鐮佺墖娈典负600ms锛屽苟涓斿洖鐪�300ms锛屽彸鐪�300ms銆�
 --wav-path 闇�瑕佽繘琛岃浆鍐欑殑闊抽鏂囦欢锛屾敮鎸佹枃浠惰矾寰�
 --thread-num 璁剧疆骞跺彂鍙戦�佺嚎绋嬫暟锛岄粯璁や负1
 --is-ssl 璁剧疆鏄惁寮�鍚痵sl璇佷功鏍￠獙锛岄粯璁�1寮�鍚紝璁剧疆涓�0鍏抽棴
---hotword 濡傛灉妯″瀷涓虹儹璇嶆ā鍨嬶紝鍙互璁剧疆鐑瘝: *.txt(姣忚涓�涓儹璇�) 鎴栬�呯┖鏍煎垎闅旂殑鐑瘝瀛楃涓� (could be: 闃块噷宸村反 杈炬懇闄�)
+--hotword 濡傛灉妯″瀷涓虹儹璇嶆ā鍨嬶紝鍙互璁剧疆鐑瘝: *.txt(姣忚涓�涓儹璇�) 鎴栬�呯┖鏍煎垎闅旂殑鐑瘝瀛楃涓� (闃块噷宸村反 杈炬懇闄�)
 --use-itn 璁剧疆鏄惁浣跨敤itn锛岄粯璁�1寮�鍚紝璁剧疆涓�0鍏抽棴
 ```
 
diff --git a/funasr/runtime/docs/SDK_tutorial_zh.md b/funasr/runtime/docs/SDK_tutorial_zh.md
index cdad39b..2c08957 100644
--- a/funasr/runtime/docs/SDK_tutorial_zh.md
+++ b/funasr/runtime/docs/SDK_tutorial_zh.md
@@ -69,13 +69,14 @@
 
 鍛戒护鍙傛暟璇存槑锛�
 ```text
---host 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛岄渶瑕佹敼涓洪儴缃叉満鍣╥p
+--host 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛�
+        闇�瑕佹敼涓洪儴缃叉満鍣╥p
 --port 10095 閮ㄧ讲绔彛鍙�
 --mode offline琛ㄧず绂荤嚎鏂囦欢杞啓
 --audio_in 闇�瑕佽繘琛岃浆鍐欑殑闊抽鏂囦欢锛屾敮鎸佹枃浠惰矾寰勶紝鏂囦欢鍒楄〃wav.scp
 --thread_num 璁剧疆骞跺彂鍙戦�佺嚎绋嬫暟锛岄粯璁や负1
 --ssl 璁剧疆鏄惁寮�鍚痵sl璇佷功鏍￠獙锛岄粯璁�1寮�鍚紝璁剧疆涓�0鍏抽棴
---hotword 濡傛灉妯″瀷涓虹儹璇嶆ā鍨嬶紝鍙互璁剧疆鐑瘝: *.txt(姣忚涓�涓儹璇�) 鎴栬�呯┖鏍煎垎闅旂殑鐑瘝瀛楃涓� (could be: 闃块噷宸村反 杈炬懇闄�)
+--hotword 濡傛灉妯″瀷涓虹儹璇嶆ā鍨嬶紝鍙互璁剧疆鐑瘝: *.txt(姣忚涓�涓儹璇�) 鎴栬�呯┖鏍煎垎闅旂殑鐑瘝瀛楃涓� (闃块噷宸村反 杈炬懇闄�)
 --use_itn 璁剧疆鏄惁浣跨敤itn锛岄粯璁�1寮�鍚紝璁剧疆涓�0鍏抽棴
 ```
 
@@ -88,12 +89,13 @@
 鍛戒护鍙傛暟璇存槑锛�
 
 ```text
---server-ip 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛岄渶瑕佹敼涓洪儴缃叉満鍣╥p
+--server-ip 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛�
+            闇�瑕佹敼涓洪儴缃叉満鍣╥p
 --port 10095 閮ㄧ讲绔彛鍙�
 --wav-path 闇�瑕佽繘琛岃浆鍐欑殑闊抽鏂囦欢锛屾敮鎸佹枃浠惰矾寰�
 --thread_num 璁剧疆骞跺彂鍙戦�佺嚎绋嬫暟锛岄粯璁や负1
 --ssl 璁剧疆鏄惁寮�鍚痵sl璇佷功鏍￠獙锛岄粯璁�1寮�鍚紝璁剧疆涓�0鍏抽棴
---hotword 濡傛灉妯″瀷涓虹儹璇嶆ā鍨嬶紝鍙互璁剧疆鐑瘝: *.txt(姣忚涓�涓儹璇�) 鎴栬�呯┖鏍煎垎闅旂殑鐑瘝瀛楃涓� (could be: 闃块噷宸村反 杈炬懇闄�)
+--hotword 濡傛灉妯″瀷涓虹儹璇嶆ā鍨嬶紝鍙互璁剧疆鐑瘝: *.txt(姣忚涓�涓儹璇�) 鎴栬�呯┖鏍煎垎闅旂殑鐑瘝瀛楃涓� (闃块噷宸村反 杈炬懇闄�)
 --use-itn 璁剧疆鏄惁浣跨敤itn锛岄粯璁�1寮�鍚紝璁剧疆涓�0鍏抽棴
 ```
 
diff --git a/funasr/runtime/ios/paraformer_online/paraformer_online.xcodeproj/project.pbxproj b/funasr/runtime/ios/paraformer_online/paraformer_online.xcodeproj/project.pbxproj
index 62b4788..8e7ffaf 100644
--- a/funasr/runtime/ios/paraformer_online/paraformer_online.xcodeproj/project.pbxproj
+++ b/funasr/runtime/ios/paraformer_online/paraformer_online.xcodeproj/project.pbxproj
@@ -90,6 +90,8 @@
 		1A7F0DBE2A2F221C00A6EEB7 /* AudioCapture.mm in Sources */ = {isa = PBXBuildFile; fileRef = 1A7F0DBB2A2F221C00A6EEB7 /* AudioCapture.mm */; };
 		1A7F0DBF2A2F221C00A6EEB7 /* AudioRecorder.m in Sources */ = {isa = PBXBuildFile; fileRef = 1A7F0DBD2A2F221C00A6EEB7 /* AudioRecorder.m */; };
 		1A7F0DC32A2F312D00A6EEB7 /* model in Resources */ = {isa = PBXBuildFile; fileRef = 1A7F0DC22A2F312D00A6EEB7 /* model */; };
+		1ACBFB692AB99D55002FC7C7 /* seg_dict.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 1ACBFB672AB99D55002FC7C7 /* seg_dict.cpp */; };
+		1ACBFB6C2AB9A086002FC7C7 /* encode_converter.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 1ACBFB6B2AB9A086002FC7C7 /* encode_converter.cpp */; };
 		59C4114F365C8D714BD515FB /* Pods_paraformer_online.framework in Frameworks */ = {isa = PBXBuildFile; fileRef = EA7D0713E60886A787BAA0EA /* Pods_paraformer_online.framework */; };
 /* End PBXBuildFile section */
 
@@ -324,6 +326,10 @@
 		1AB8E1EE2AA086F200F4F795 /* model.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = model.h; sourceTree = "<group>"; };
 		1AB8E1EF2AA086F200F4F795 /* offline-stream.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = "offline-stream.h"; sourceTree = "<group>"; };
 		1AB8E1F02AA086F200F4F795 /* vad-model.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = "vad-model.h"; sourceTree = "<group>"; };
+		1ACBFB672AB99D55002FC7C7 /* seg_dict.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = seg_dict.cpp; sourceTree = "<group>"; };
+		1ACBFB682AB99D55002FC7C7 /* seg_dict.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = seg_dict.h; sourceTree = "<group>"; };
+		1ACBFB6A2AB9A086002FC7C7 /* encode_converter.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = encode_converter.h; sourceTree = "<group>"; };
+		1ACBFB6B2AB9A086002FC7C7 /* encode_converter.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = encode_converter.cpp; sourceTree = "<group>"; };
 		B9ED2A36675364C815C03C96 /* Pods-paraformer_online.debug.xcconfig */ = {isa = PBXFileReference; includeInIndex = 1; lastKnownFileType = text.xcconfig; name = "Pods-paraformer_online.debug.xcconfig"; path = "Target Support Files/Pods-paraformer_online/Pods-paraformer_online.debug.xcconfig"; sourceTree = "<group>"; };
 		EA7D0713E60886A787BAA0EA /* Pods_paraformer_online.framework */ = {isa = PBXFileReference; explicitFileType = wrapper.framework; includeInIndex = 0; path = Pods_paraformer_online.framework; sourceTree = BUILT_PRODUCTS_DIR; };
 /* End PBXFileReference section */
@@ -355,6 +361,8 @@
 				1A6C92FB2A84D64E007E36DC /* ct-transformer.cpp */,
 				1A6C93032A84D64E007E36DC /* ct-transformer.h */,
 				1A6C92F92A84D64E007E36DC /* e2e-vad.h */,
+				1ACBFB6B2AB9A086002FC7C7 /* encode_converter.cpp */,
+				1ACBFB6A2AB9A086002FC7C7 /* encode_converter.h */,
 				1A6C92F72A84D64E007E36DC /* fsmn-vad-online.cpp */,
 				1A6C92E92A84D64E007E36DC /* fsmn-vad-online.h */,
 				1A6C92E82A84D64E007E36DC /* fsmn-vad.cpp */,
@@ -371,6 +379,8 @@
 				1A6C93022A84D64E007E36DC /* punc-model.cpp */,
 				1A6C92ED2A84D64E007E36DC /* resample.cpp */,
 				1A6C92E32A84D64E007E36DC /* resample.h */,
+				1ACBFB672AB99D55002FC7C7 /* seg_dict.cpp */,
+				1ACBFB682AB99D55002FC7C7 /* seg_dict.h */,
 				1A6C93012A84D64E007E36DC /* tensor.h */,
 				1A6C92F02A84D64E007E36DC /* tokenizer.cpp */,
 				1A6C92EF2A84D64E007E36DC /* tokenizer.h */,
@@ -917,6 +927,7 @@
 				1A6C93F72A84D66E007E36DC /* symbolize.cc in Sources */,
 				1A6C93062A84D64E007E36DC /* util.cpp in Sources */,
 				1A6C94222A84D66E007E36DC /* nodebuilder.cpp in Sources */,
+				1ACBFB692AB99D55002FC7C7 /* seg_dict.cpp in Sources */,
 				1A6C94132A84D66E007E36DC /* exp.cpp in Sources */,
 				1A6C930A2A84D64E007E36DC /* vocab.cpp in Sources */,
 				1A6C94012A84D66E007E36DC /* logging.cc in Sources */,
@@ -931,6 +942,7 @@
 				1A6C940F2A84D66E007E36DC /* emitter.cpp in Sources */,
 				1A6C93DE2A84D66E007E36DC /* fftsg.c in Sources */,
 				1A6C940B2A84D66E007E36DC /* ostream_wrapper.cpp in Sources */,
+				1ACBFB6C2AB9A086002FC7C7 /* encode_converter.cpp in Sources */,
 				1A6C93E12A84D66E007E36DC /* log.cc in Sources */,
 				1A6C94092A84D66E007E36DC /* exceptions.cpp in Sources */,
 				1A6C94152A84D66E007E36DC /* node.cpp in Sources */,
@@ -1108,7 +1120,7 @@
 					"@executable_path/Frameworks",
 				);
 				MARKETING_VERSION = 1.0;
-				PRODUCT_BUNDLE_IDENTIFIER = "com.qiuwei.paraformer-online";
+				PRODUCT_BUNDLE_IDENTIFIER = "com.qiuwei.paraformer-online1";
 				PRODUCT_NAME = "$(TARGET_NAME)";
 				SWIFT_EMIT_LOC_STRINGS = YES;
 				TARGETED_DEVICE_FAMILY = "1,2";
@@ -1147,7 +1159,7 @@
 					"@executable_path/Frameworks",
 				);
 				MARKETING_VERSION = 1.0;
-				PRODUCT_BUNDLE_IDENTIFIER = "com.qiuwei.paraformer-online";
+				PRODUCT_BUNDLE_IDENTIFIER = "com.qiuwei.paraformer-online1";
 				PRODUCT_NAME = "$(TARGET_NAME)";
 				SWIFT_EMIT_LOC_STRINGS = YES;
 				TARGETED_DEVICE_FAMILY = "1,2";
diff --git a/funasr/runtime/onnxruntime/include/funasrruntime.h b/funasr/runtime/onnxruntime/include/funasrruntime.h
index 93824fb..14f6122 100644
--- a/funasr/runtime/onnxruntime/include/funasrruntime.h
+++ b/funasr/runtime/onnxruntime/include/funasrruntime.h
@@ -105,7 +105,10 @@
 _FUNASRAPI FUNASR_RESULT	FunOfflineInfer(FUNASR_HANDLE handle, const char* sz_filename, FUNASR_MODE mode, 
 											QM_CALLBACK fn_callback, const std::vector<std::vector<float>> &hw_emb, 
 											int sampling_rate=16000, bool itn=true);
+#if !defined(__APPLE__)
 _FUNASRAPI const std::vector<std::vector<float>> CompileHotwordEmbedding(FUNASR_HANDLE handle, std::string &hotwords, ASR_TYPE mode=ASR_OFFLINE);
+#endif
+
 _FUNASRAPI void				FunOfflineUninit(FUNASR_HANDLE handle);
 
 //2passStream
diff --git a/funasr/runtime/onnxruntime/include/model.h b/funasr/runtime/onnxruntime/include/model.h
index 53a7927..8019a07 100644
--- a/funasr/runtime/onnxruntime/include/model.h
+++ b/funasr/runtime/onnxruntime/include/model.h
@@ -17,7 +17,7 @@
     virtual std::string Rescoring() = 0;
     virtual void InitHwCompiler(const std::string &hw_model, int thread_num){};
     virtual void InitSegDict(const std::string &seg_dict_model){};
-    virtual std::vector<std::vector<float>> CompileHotwordEmbedding(std::string &hotwords){};
+    virtual std::vector<std::vector<float>> CompileHotwordEmbedding(std::string &hotwords){return std::vector<std::vector<float>>();};
 };
 
 Model *CreateModel(std::map<std::string, std::string>& model_path, int thread_num=1, ASR_TYPE type=ASR_OFFLINE);
diff --git a/funasr/runtime/onnxruntime/include/offline-stream.h b/funasr/runtime/onnxruntime/include/offline-stream.h
index 21deb36..f63de74 100644
--- a/funasr/runtime/onnxruntime/include/offline-stream.h
+++ b/funasr/runtime/onnxruntime/include/offline-stream.h
@@ -7,7 +7,9 @@
 #include "model.h"
 #include "punc-model.h"
 #include "vad-model.h"
+#if !defined(__APPLE__)
 #include "itn-model.h"
+#endif
 
 namespace funasr {
 class OfflineStream {
@@ -18,7 +20,9 @@
     std::unique_ptr<VadModel> vad_handle= nullptr;
     std::unique_ptr<Model> asr_handle= nullptr;
     std::unique_ptr<PuncModel> punc_handle= nullptr;
+#if !defined(__APPLE__)
     std::unique_ptr<ITNModel> itn_handle = nullptr;
+#endif
     bool UseVad(){return use_vad;};
     bool UsePunc(){return use_punc;}; 
     bool UseITN(){return use_itn;};
diff --git a/funasr/runtime/onnxruntime/include/tpass-stream.h b/funasr/runtime/onnxruntime/include/tpass-stream.h
index 8aacdf1..0276631 100644
--- a/funasr/runtime/onnxruntime/include/tpass-stream.h
+++ b/funasr/runtime/onnxruntime/include/tpass-stream.h
@@ -7,7 +7,9 @@
 #include "model.h"
 #include "punc-model.h"
 #include "vad-model.h"
+#if !defined(__APPLE__)
 #include "itn-model.h"
+#endif
 
 namespace funasr {
 class TpassStream {
@@ -18,7 +20,9 @@
     std::unique_ptr<VadModel> vad_handle = nullptr;
     std::unique_ptr<Model> asr_handle = nullptr;
     std::unique_ptr<PuncModel> punc_online_handle = nullptr;
+#if !defined(__APPLE__)
     std::unique_ptr<ITNModel> itn_handle = nullptr;
+#endif
     bool UseVad(){return use_vad;};
     bool UsePunc(){return use_punc;}; 
     bool UseITN(){return use_itn;};
diff --git a/funasr/runtime/onnxruntime/src/funasrruntime.cpp b/funasr/runtime/onnxruntime/src/funasrruntime.cpp
index fdefad9..0d4af5c 100644
--- a/funasr/runtime/onnxruntime/src/funasrruntime.cpp
+++ b/funasr/runtime/onnxruntime/src/funasrruntime.cpp
@@ -285,10 +285,12 @@
 			string punc_res = (offline_stream->punc_handle)->AddPunc((p_result->msg).c_str());
 			p_result->msg = punc_res;
 		}
+#if !defined(__APPLE__)
 		if(offline_stream->UseITN() && itn){
 			string msg_itn = offline_stream->itn_handle->Normalize(p_result->msg);
 			p_result->msg = msg_itn;
 		}
+#endif
 
 		return p_result;
 	}
@@ -364,13 +366,16 @@
 			string punc_res = (offline_stream->punc_handle)->AddPunc((p_result->msg).c_str());
 			p_result->msg = punc_res;
 		}
+#if !defined(__APPLE__)
 		if(offline_stream->UseITN() && itn){
 			string msg_itn = offline_stream->itn_handle->Normalize(p_result->msg);
 			p_result->msg = msg_itn;
 		}
+#endif
 		return p_result;
 	}
 
+#if !defined(__APPLE__)
 	_FUNASRAPI const std::vector<std::vector<float>> CompileHotwordEmbedding(FUNASR_HANDLE handle, std::string &hotwords, ASR_TYPE mode)
 	{
 		if (mode == ASR_OFFLINE){
@@ -394,7 +399,7 @@
 		}
 		
 	}
-
+#endif
 
 	// APIs for 2pass-stream Infer
 	_FUNASRAPI FUNASR_RESULT FunTpassInferBuffer(FUNASR_HANDLE handle, FUNASR_HANDLE online_handle, const char* sz_buf, 
@@ -450,13 +455,13 @@
 					string online_msg = ((funasr::ParaformerOnline*)asr_online_handle)->online_res;
 					string msg_punc = punc_online_handle->AddPunc(online_msg.c_str(), punc_cache[0]);
 					p_result->tpass_msg = msg_punc;
-
+#if !defined(__APPLE__)
 					// ITN
 					if(tpass_stream->UseITN() && itn){
 						string msg_itn = tpass_stream->itn_handle->Normalize(msg_punc);
 						p_result->tpass_msg = msg_itn;
 					}
-
+#endif
 					((funasr::ParaformerOnline*)asr_online_handle)->online_res = "";
 					p_result->msg += msg;
 				}else{
@@ -501,10 +506,12 @@
 				msg_punc += "銆�";
 			}
 			p_result->tpass_msg = msg_punc;
+#if !defined(__APPLE__)
 			if(tpass_stream->UseITN() && itn){
 				string msg_itn = tpass_stream->itn_handle->Normalize(msg_punc);
 				p_result->tpass_msg = msg_itn;
 			}
+#endif
 
 			if(frame != NULL){
 				delete frame;
diff --git a/funasr/runtime/onnxruntime/src/offline-stream.cpp b/funasr/runtime/onnxruntime/src/offline-stream.cpp
index ae09a50..50d0188 100644
--- a/funasr/runtime/onnxruntime/src/offline-stream.cpp
+++ b/funasr/runtime/onnxruntime/src/offline-stream.cpp
@@ -84,7 +84,7 @@
             use_punc = true;
         }
     }
-
+#if !defined(__APPLE__)
     // Optional: ITN, here we just support language_type=MandarinEnglish
     if(model_path.find(ITN_DIR) != model_path.end() && model_path.at(ITN_DIR) != ""){
         string itn_tagger_path = PathAppend(model_path.at(ITN_DIR), ITN_TAGGER_NAME);
@@ -100,6 +100,7 @@
             use_itn = true;
         }
     }
+#endif
 }
 
 OfflineStream *CreateOfflineStream(std::map<std::string, std::string>& model_path, int thread_num)
diff --git a/funasr/runtime/onnxruntime/src/paraformer.cpp b/funasr/runtime/onnxruntime/src/paraformer.cpp
index 763d01e..a2dd038 100644
--- a/funasr/runtime/onnxruntime/src/paraformer.cpp
+++ b/funasr/runtime/onnxruntime/src/paraformer.cpp
@@ -684,7 +684,7 @@
                 return "";
             }
             //PrintMat(hw_emb, "input_clas_emb");
-            const int64_t hotword_shape[3] = {1, hw_emb.size(), hw_emb[0].size()};
+            const int64_t hotword_shape[3] = {1, static_cast<int64_t>(hw_emb.size()), static_cast<int64_t>(hw_emb[0].size())};
             embedding.reserve(hw_emb.size() * hw_emb[0].size());
             for (auto item : hw_emb) {
                 embedding.insert(embedding.end(), item.begin(), item.end());
diff --git a/funasr/runtime/onnxruntime/src/precomp.h b/funasr/runtime/onnxruntime/src/precomp.h
index 768d05d..59e594e 100644
--- a/funasr/runtime/onnxruntime/src/precomp.h
+++ b/funasr/runtime/onnxruntime/src/precomp.h
@@ -24,6 +24,8 @@
 #else
 #include "onnxruntime_run_options_config_keys.h"
 #include "onnxruntime_cxx_api.h"
+#include "itn-model.h"
+#include "itn-processor.h"
 #endif
 
 #include "kaldi-native-fbank/csrc/feature-fbank.h"
@@ -38,11 +40,9 @@
 #include "model.h"
 #include "vad-model.h"
 #include "punc-model.h"
-#include "itn-model.h"
 #include "tokenizer.h"
 #include "ct-transformer.h"
 #include "ct-transformer-online.h"
-#include "itn-processor.h"
 #include "e2e-vad.h"
 #include "fsmn-vad.h"
 #include "encode_converter.h"
diff --git a/funasr/runtime/onnxruntime/src/tpass-stream.cpp b/funasr/runtime/onnxruntime/src/tpass-stream.cpp
index 31ddde5..47734af 100644
--- a/funasr/runtime/onnxruntime/src/tpass-stream.cpp
+++ b/funasr/runtime/onnxruntime/src/tpass-stream.cpp
@@ -89,7 +89,7 @@
             use_punc = true;
         }
     }
-
+#if !defined(__APPLE__)
     // Optional: ITN, here we just support language_type=MandarinEnglish
     if(model_path.find(ITN_DIR) != model_path.end()){
         string itn_tagger_path = PathAppend(model_path.at(ITN_DIR), ITN_TAGGER_NAME);
@@ -105,6 +105,7 @@
             use_itn = true;
         }
     }
+#endif
       
 }
 
@@ -114,4 +115,4 @@
     mm = new TpassStream(model_path, thread_num);
     return mm;
 }
-} // namespace funasr
\ No newline at end of file
+} // namespace funasr
diff --git a/funasr/runtime/python/websocket/funasr_client_api.py b/funasr/runtime/python/websocket/funasr_client_api.py
index aa573c0..d0992ff 100644
--- a/funasr/runtime/python/websocket/funasr_client_api.py
+++ b/funasr/runtime/python/websocket/funasr_client_api.py
@@ -51,7 +51,8 @@
         stride = int(60 *  chunk_size[1]/  chunk_interval / 1000 * 16000 * 2)
         chunk_num = (len(audio_bytes) - 1) // stride + 1
        
-        message = json.dumps({"mode":  mode, "chunk_size":  chunk_size, "chunk_interval":  chunk_interval,
+        message = json.dumps({"mode": args.mode, "chunk_size": args.chunk_size, "encoder_chunk_look_back": 4,
+                              "decoder_chunk_look_back": 1, "chunk_interval": args.chunk_interval, 
                               "wav_name": wav_name, "is_speaking": True})
  
         self.websocket.send(message)
@@ -131,4 +132,4 @@
     print("text",text)
  
     
-            
\ No newline at end of file
+            
diff --git a/funasr/runtime/python/websocket/funasr_wss_client.py b/funasr/runtime/python/websocket/funasr_wss_client.py
index bed0081..f4f35bb 100644
--- a/funasr/runtime/python/websocket/funasr_wss_client.py
+++ b/funasr/runtime/python/websocket/funasr_wss_client.py
@@ -29,6 +29,14 @@
                     type=str,
                     default="5, 10, 5",
                     help="chunk")
+parser.add_argument("--encoder_chunk_look_back",
+                    type=int,
+                    default=4,
+                    help="number of chunks to lookback for encoder self-attention")
+parser.add_argument("--decoder_chunk_look_back",
+                    type=int,
+                    default=1,
+                    help="number of encoder chunks to lookback for decoder cross-attention")
 parser.add_argument("--chunk_interval",
                     type=int,
                     default=10,
@@ -99,7 +107,8 @@
                     input=True,
                     frames_per_buffer=CHUNK)
 
-    message = json.dumps({"mode": args.mode, "chunk_size": args.chunk_size, "chunk_interval": args.chunk_interval,
+    message = json.dumps({"mode": args.mode, "chunk_size": args.chunk_size, "encoder_chunk_look_back": args.encoder_chunk_look_back,
+                          "decoder_chunk_look_back": args.decoder_chunk_look_back, "chunk_interval": args.chunk_interval, 
                           "wav_name": "microphone", "is_speaking": True})
     #voices.put(message)
     await websocket.send(message)
diff --git a/funasr/runtime/python/websocket/funasr_wss_server.py b/funasr/runtime/python/websocket/funasr_wss_server.py
index 57f7584..b74f225 100644
--- a/funasr/runtime/python/websocket/funasr_wss_server.py
+++ b/funasr/runtime/python/websocket/funasr_wss_server.py
@@ -103,8 +103,8 @@
     model=args.asr_model_online,
     ngpu=args.ngpu,
     ncpu=args.ncpu,
-    model_revision='v1.0.4',
-    update_model='v1.0.4',
+    model_revision='v1.0.7',
+    update_model='v1.0.7',
     mode='paraformer_streaming')
 
 print("model loaded! only support one client at the same time now!!!!")
@@ -159,6 +159,10 @@
                     websocket.wav_name = messagejson.get("wav_name")
                 if "chunk_size" in messagejson:
                     websocket.param_dict_asr_online["chunk_size"] = messagejson["chunk_size"]
+                if "encoder_chunk_look_back" in messagejson:
+                    websocket.param_dict_asr_online["encoder_chunk_look_back"] = messagejson["encoder_chunk_look_back"]
+                if "decoder_chunk_look_back" in messagejson:
+                    websocket.param_dict_asr_online["decoder_chunk_look_back"] = messagejson["decoder_chunk_look_back"]
                 if "mode" in messagejson:
                     websocket.mode = messagejson["mode"]
             if len(frames_asr_online) > 0 or len(frames_asr) > 0 or not isinstance(message, str):
diff --git a/funasr/runtime/readme.md b/funasr/runtime/readme.md
index af3d7e4..bbc96aa 100644
--- a/funasr/runtime/readme.md
+++ b/funasr/runtime/readme.md
@@ -30,9 +30,9 @@
 
 ### latest version & image ID
 
-| image version                |  image ID | INFO |
-|------------------------------|-----|------|
-| funasr-runtime-sdk-cpu-0.2.1 |  1ad3d19e0707   |      |
+| image version                       |  image ID | INFO |
+|-------------------------------------|-----|------|
+| funasr-runtime-sdk-online-cpu-0.1.2 |  7222c5319bcf   |      |
 
 ## File Transcription Service, Mandarin (CPU)
 
@@ -53,6 +53,6 @@
 The documentation mainly targets advanced developers who require modifications and customization of the service. It supports downloading model deployments from modelscope and also supports deploying models that users have fine-tuned. For detailed information, please refer to the documentation available by [docs](./docs/SDK_advanced_guide_offline.md)
 
 ### latest version & image ID
-|  image version   |  image ID | INFO |
-|-----|-----|------|
-|   funasr-runtime-sdk-online-cpu-0.1.1  |  bdbdd0b27dee   |      |
+| image version                |  image ID | INFO |
+|------------------------------|-----|------|
+| funasr-runtime-sdk-cpu-0.2.2 |  2c5286be13e9   |      |
diff --git a/funasr/runtime/readme_cn.md b/funasr/runtime/readme_cn.md
index 299a08f..47aee86 100644
--- a/funasr/runtime/readme_cn.md
+++ b/funasr/runtime/readme_cn.md
@@ -31,9 +31,9 @@
 
 ### 鏈�鏂扮増鏈強image ID
 
-| image version                |  image ID | INFO |
-|------------------------------|-----|------|
-| funasr-runtime-sdk-cpu-0.2.1 |   1ad3d19e0707  |      |
+| image version                       |  image ID | INFO |
+|-------------------------------------|-----|------|
+| funasr-runtime-sdk-online-cpu-0.1.2 |   7222c5319bcf  |      |
 
 
 ## 涓枃绂荤嚎鏂囦欢杞啓鏈嶅姟锛圕PU鐗堟湰锛�
@@ -55,6 +55,6 @@
 鏂囨。浠嬬粛浜嗚儗鍚庢妧鏈師鐞嗭紝璇嗗埆鍑嗙‘鐜囷紝璁＄畻鏁堢巼绛夛紝浠ュ強鏍稿績浼樺娍浠嬬粛锛氫究鎹枫�侀珮绮惧害銆侀珮鏁堢巼銆侀暱闊抽閾捐矾锛岃缁嗘枃妗ｅ弬鑰冿紙[鐐瑰嚮姝ゅ](https://mp.weixin.qq.com/s/DHQwbgdBWcda0w_L60iUww)锛�
 
 ### 鏈�鏂扮増鏈強image ID
-|  image version   |  image ID | INFO |
-|-----|-----|------|
-|   funasr-runtime-sdk-online-cpu-0.1.1  |  bdbdd0b27dee   |      |
+| image version                |  image ID | INFO |
+|------------------------------|-----|------|
+| funasr-runtime-sdk-cpu-0.2.2 |  2c5286be13e9   |      |

--
Gitblit v1.9.1