From 817ff41fbc5afbde346db62ad5e28e33178a622a Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 25 三月 2024 12:55:20 +0800
Subject: [PATCH] install requirements automatically

---
 examples/industrial_data_pretraining/paraformer/export.py               |    3 
 examples/industrial_data_pretraining/whisper/demo.py                    |    1 
 examples/industrial_data_pretraining/ct_transformer/export.py           |    2 
 examples/industrial_data_pretraining/bicif_paraformer/export.py         |    3 
 examples/industrial_data_pretraining/campplus_sv/demo.py                |    3 
 examples/common_voice/whisper_lid/demo_funasr.py                        |    2 
 examples/industrial_data_pretraining/fsmn_vad_streaming/demo.sh         |    3 
 examples/industrial_data_pretraining/monotonic_aligner/demo.sh          |    3 
 examples/industrial_data_pretraining/scama/demo.py                      |    2 
 examples/industrial_data_pretraining/paraformer/README_zh.md            |    2 
 examples/industrial_data_pretraining/paraformer_streaming/export.sh     |    3 
 examples/industrial_data_pretraining/contextual_paraformer/demo.sh      |    3 
 examples/industrial_data_pretraining/paraformer_streaming/demo.py       |    2 
 examples/industrial_data_pretraining/paraformer/infer.sh                |    3 
 examples/industrial_data_pretraining/ct_transformer_streaming/demo.py   |    2 
 examples/industrial_data_pretraining/ct_transformer_streaming/export.py |    2 
 docs/tutorial/README_zh.md                                              |    2 
 examples/industrial_data_pretraining/contextual_paraformer/demo.py      |    2 
 examples/README_zh.md                                                   |    2 
 examples/industrial_data_pretraining/seaco_paraformer/demo.sh           |    3 
 examples/industrial_data_pretraining/conformer/demo.py                  |    3 
 examples/industrial_data_pretraining/paraformer_streaming/README_zh.md  |  416 ++++++++++++++++++++++
 examples/industrial_data_pretraining/bicif_paraformer/demo.py           |    4 
 examples/industrial_data_pretraining/fsmn_vad_streaming/export.sh       |    2 
 examples/industrial_data_pretraining/paraformer-zh-spk/demo.sh          |   27 
 examples/industrial_data_pretraining/bicif_paraformer/export.sh         |    2 
 examples/industrial_data_pretraining/paraformer_streaming/finetune.sh   |    3 
 examples/industrial_data_pretraining/ct_transformer/demo.py             |    4 
 examples/industrial_data_pretraining/bicif_paraformer/finetune.sh       |    2 
 examples/industrial_data_pretraining/paraformer/finetune.sh             |    3 
 examples/industrial_data_pretraining/paraformer_streaming/export.py     |    3 
 examples/industrial_data_pretraining/whisper/infer.sh                   |    3 
 examples/common_voice/whisper_lid/demo_modelscope.py                    |    2 
 examples/industrial_data_pretraining/paraformer_streaming/demo.sh       |    3 
 examples/industrial_data_pretraining/emotion2vec/demo.py                |    2 
 examples/industrial_data_pretraining/paraformer/demo.py                 |    8 
 examples/industrial_data_pretraining/scama/demo.sh                      |    3 
 examples/industrial_data_pretraining/uniasr/demo.sh                     |    3 
 examples/industrial_data_pretraining/transducer/demo.py                 |    3 
 examples/industrial_data_pretraining/paraformer/export.sh               |    3 
 examples/industrial_data_pretraining/ct_transformer_streaming/demo.sh   |    3 
 examples/industrial_data_pretraining/ct_transformer/export.sh           |    2 
 examples/industrial_data_pretraining/uniasr/demo.py                     |    4 
 examples/industrial_data_pretraining/paraformer-zh-spk/demo.py          |    4 
 examples/industrial_data_pretraining/contextual_paraformer/finetune.sh  |    2 
 examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py         |    2 
 examples/industrial_data_pretraining/monotonic_aligner/demo.py          |    2 
 examples/industrial_data_pretraining/fsmn_vad_streaming/export.py       |    2 
 examples/industrial_data_pretraining/paraformer-zh-spk/README_zh.md     |  432 ++++++++++++++++++++++++
 examples/industrial_data_pretraining/bicif_paraformer/demo.sh           |    8 
 examples/industrial_data_pretraining/ct_transformer/demo.sh             |    5 
 examples/industrial_data_pretraining/conformer/demo.sh                  |    2 
 examples/industrial_data_pretraining/seaco_paraformer/demo.py           |    4 
 examples/industrial_data_pretraining/ct_transformer_streaming/export.sh |    2 
 examples/industrial_data_pretraining/seaco_paraformer/finetune.sh       |    2 
 55 files changed, 889 insertions(+), 134 deletions(-)

diff --git a/docs/tutorial/README_zh.md b/docs/tutorial/README_zh.md
index 60c3d97..24a20fb 100644
--- a/docs/tutorial/README_zh.md
+++ b/docs/tutorial/README_zh.md
@@ -214,7 +214,6 @@
 ```shell
 funasr/bin/train.py \
 ++model="${model_name_or_model_dir}" \
-++model_revision="${model_revision}" \
 ++train_data_set_list="${train_data}" \
 ++valid_data_set_list="${val_data}" \
 ++dataset_conf.batch_size=20000 \
@@ -232,7 +231,6 @@
 ```
 
 - `model`锛坰tr锛夛細妯″瀷鍚嶅瓧锛堟ā鍨嬩粨搴撲腑鐨処D锛夛紝姝ゆ椂鑴氭湰浼氳嚜鍔ㄤ笅杞芥ā鍨嬪埌鏈锛涙垨鑰呮湰鍦板凡缁忎笅杞藉ソ鐨勬ā鍨嬭矾寰勩��
-- `model_revision`锛坰tr锛夛細褰� `model` 涓烘ā鍨嬪悕瀛楁椂锛屼笅杞芥寚瀹氱増鏈殑妯″瀷銆�
 - `train_data_set_list`锛坰tr锛夛細璁粌鏁版嵁璺緞锛岄粯璁や负jsonl鏍煎紡锛屽叿浣撳弬鑰冿紙[渚嬪瓙](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)锛夈��
 - `valid_data_set_list`锛坰tr锛夛細楠岃瘉鏁版嵁璺緞锛岄粯璁や负jsonl鏍煎紡锛屽叿浣撳弬鑰冿紙[渚嬪瓙](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)锛夈��
 - `dataset_conf.batch_type`锛坰tr锛夛細`example`锛堥粯璁わ級锛宐atch鐨勭被鍨嬨�俙example`琛ㄧず鎸夌収鍥哄畾鏁扮洰batch_size涓牱鏈粍batch锛沗length` or `token` 琛ㄧず鍔ㄦ�佺粍batch锛宐atch鎬婚暱搴︽垨鑰卼oken鏁颁负batch_size銆�
diff --git a/examples/README_zh.md b/examples/README_zh.md
index 60c3d97..24a20fb 100644
--- a/examples/README_zh.md
+++ b/examples/README_zh.md
@@ -214,7 +214,6 @@
 ```shell
 funasr/bin/train.py \
 ++model="${model_name_or_model_dir}" \
-++model_revision="${model_revision}" \
 ++train_data_set_list="${train_data}" \
 ++valid_data_set_list="${val_data}" \
 ++dataset_conf.batch_size=20000 \
@@ -232,7 +231,6 @@
 ```
 
 - `model`锛坰tr锛夛細妯″瀷鍚嶅瓧锛堟ā鍨嬩粨搴撲腑鐨処D锛夛紝姝ゆ椂鑴氭湰浼氳嚜鍔ㄤ笅杞芥ā鍨嬪埌鏈锛涙垨鑰呮湰鍦板凡缁忎笅杞藉ソ鐨勬ā鍨嬭矾寰勩��
-- `model_revision`锛坰tr锛夛細褰� `model` 涓烘ā鍨嬪悕瀛楁椂锛屼笅杞芥寚瀹氱増鏈殑妯″瀷銆�
 - `train_data_set_list`锛坰tr锛夛細璁粌鏁版嵁璺緞锛岄粯璁や负jsonl鏍煎紡锛屽叿浣撳弬鑰冿紙[渚嬪瓙](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)锛夈��
 - `valid_data_set_list`锛坰tr锛夛細楠岃瘉鏁版嵁璺緞锛岄粯璁や负jsonl鏍煎紡锛屽叿浣撳弬鑰冿紙[渚嬪瓙](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)锛夈��
 - `dataset_conf.batch_type`锛坰tr锛夛細`example`锛堥粯璁わ級锛宐atch鐨勭被鍨嬨�俙example`琛ㄧず鎸夌収鍥哄畾鏁扮洰batch_size涓牱鏈粍batch锛沗length` or `token` 琛ㄧず鍔ㄦ�佺粍batch锛宐atch鎬婚暱搴︽垨鑰卼oken鏁颁负batch_size銆�
diff --git a/examples/common_voice/whisper_lid/demo_funasr.py b/examples/common_voice/whisper_lid/demo_funasr.py
index 50f4e2a..5818f4c 100644
--- a/examples/common_voice/whisper_lid/demo_funasr.py
+++ b/examples/common_voice/whisper_lid/demo_funasr.py
@@ -12,7 +12,7 @@
     "example_ko.mp3",
 ]
 
-model = AutoModel(model="iic/speech_whisper-large_lid_multilingual_pytorch", model_revision="master")
+model = AutoModel(model="iic/speech_whisper-large_lid_multilingual_pytorch")
 for wav_id in multilingual_wavs:
     wav_file = f"{model.model_path}/examples/{wav_id}"
     res = model.generate(input=wav_file, data_type="sound", inference_clip_length=250)
diff --git a/examples/common_voice/whisper_lid/demo_modelscope.py b/examples/common_voice/whisper_lid/demo_modelscope.py
index e55a972..f2cc5ea 100644
--- a/examples/common_voice/whisper_lid/demo_modelscope.py
+++ b/examples/common_voice/whisper_lid/demo_modelscope.py
@@ -15,7 +15,7 @@
 
 inference_pipeline = pipeline(
     task=Tasks.auto_speech_recognition,
-    model='iic/speech_whisper-large_lid_multilingual_pytorch', model_revision="master")
+    model='iic/speech_whisper-large_lid_multilingual_pytorch')
 
 for wav in multilingual_wavs:
     rec_result = inference_pipeline(input=wav, inference_clip_length=250)
diff --git a/examples/industrial_data_pretraining/bicif_paraformer/demo.py b/examples/industrial_data_pretraining/bicif_paraformer/demo.py
index 0b17065..03b4479 100644
--- a/examples/industrial_data_pretraining/bicif_paraformer/demo.py
+++ b/examples/industrial_data_pretraining/bicif_paraformer/demo.py
@@ -6,13 +6,9 @@
 from funasr import AutoModel
 
 model = AutoModel(model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
-                  model_revision="master",
                   vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
-                  vad_model_revision="master",
                   punc_model="iic/punc_ct-transformer_cn-en-common-vocab471067-large",
-                  punc_model_revision="master",
                   # spk_model="iic/speech_campplus_sv_zh-cn_16k-common",
-                  # spk_model_revision="v2.0.2",
                   )
 
 res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_vad_punc_example.wav", batch_size_s=300, batch_size_threshold_s=60)
diff --git a/examples/industrial_data_pretraining/bicif_paraformer/demo.sh b/examples/industrial_data_pretraining/bicif_paraformer/demo.sh
index fe44734..7776d78 100644
--- a/examples/industrial_data_pretraining/bicif_paraformer/demo.sh
+++ b/examples/industrial_data_pretraining/bicif_paraformer/demo.sh
@@ -1,23 +1,15 @@
 
 model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="master"
 vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch"
-vad_model_revision="master"
 #punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
 punc_model="iic/punc_ct-transformer_cn-en-common-vocab471067-large"
-punc_model_revision="master"
 spk_model="iic/speech_campplus_sv_zh-cn_16k-common"
-spk_model_revision="v2.0.2"
 
 python funasr/bin/inference.py \
 +model=${model} \
-+model_revision=${model_revision} \
 +vad_model=${vad_model} \
-+vad_model_revision=${vad_model_revision} \
 +punc_model=${punc_model} \
-+punc_model_revision=${punc_model_revision} \
 +spk_model=${spk_model} \
-+spk_model_revision=${spk_model_revision} \
 +input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_vad_punc_example.wav" \
 +output_dir="./outputs/debug" \
 +device="cpu" \
diff --git a/examples/industrial_data_pretraining/bicif_paraformer/export.py b/examples/industrial_data_pretraining/bicif_paraformer/export.py
index 8e45a23..d1b1ea7 100644
--- a/examples/industrial_data_pretraining/bicif_paraformer/export.py
+++ b/examples/industrial_data_pretraining/bicif_paraformer/export.py
@@ -7,8 +7,7 @@
 
 from funasr import AutoModel
 
-model = AutoModel(model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
-                  model_revision="master", device="cpu")
+model = AutoModel(model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch", device="cpu")
 
 res = model.export(type="onnx", quantize=False)
 print(res)
diff --git a/examples/industrial_data_pretraining/bicif_paraformer/export.sh b/examples/industrial_data_pretraining/bicif_paraformer/export.sh
index cf040ec..8511f91 100644
--- a/examples/industrial_data_pretraining/bicif_paraformer/export.sh
+++ b/examples/industrial_data_pretraining/bicif_paraformer/export.sh
@@ -6,11 +6,9 @@
 
 
 model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="master"
 
 python -m funasr.bin.export \
 ++model=${model} \
-++model_revision=${model_revision} \
 ++type="onnx" \
 ++quantize=false \
 ++device="cpu"
diff --git a/examples/industrial_data_pretraining/bicif_paraformer/finetune.sh b/examples/industrial_data_pretraining/bicif_paraformer/finetune.sh
index 9d251a1..08f6f56 100644
--- a/examples/industrial_data_pretraining/bicif_paraformer/finetune.sh
+++ b/examples/industrial_data_pretraining/bicif_paraformer/finetune.sh
@@ -11,7 +11,6 @@
 
 ## option 1, download model automatically
 model_name_or_model_dir="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="master"
 
 ## option 2, download model by git
 #local_path_root=${workspace}/modelscope_models
@@ -51,7 +50,6 @@
 --nproc_per_node ${gpu_num} \
 ../../../funasr/bin/train.py \
 ++model="${model_name_or_model_dir}" \
-++model_revision="${model_revision}" \
 ++train_data_set_list="${train_data}" \
 ++valid_data_set_list="${val_data}" \
 ++dataset_conf.batch_size=20000 \
diff --git a/examples/industrial_data_pretraining/campplus_sv/demo.py b/examples/industrial_data_pretraining/campplus_sv/demo.py
index e7c4cc9..c3e9398 100644
--- a/examples/industrial_data_pretraining/campplus_sv/demo.py
+++ b/examples/industrial_data_pretraining/campplus_sv/demo.py
@@ -5,8 +5,7 @@
 
 from funasr import AutoModel
 
-model = AutoModel(model="iic/speech_campplus_sv_zh-cn_16k-common",
-                  model_revision="v2.0.2",
+model = AutoModel(model="iic/speech_campplus_sv_zh-cn_16k-common"
                   )
 
 res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
diff --git a/examples/industrial_data_pretraining/conformer/demo.py b/examples/industrial_data_pretraining/conformer/demo.py
index 1abc7a7..1b07c30 100644
--- a/examples/industrial_data_pretraining/conformer/demo.py
+++ b/examples/industrial_data_pretraining/conformer/demo.py
@@ -5,8 +5,7 @@
 
 from funasr import AutoModel
 
-model = AutoModel(model="iic/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch", model_revision="master",
-                  )
+model = AutoModel(model="iic/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch")
 
 res = model.generate(input="https://modelscope.oss-cn-beijing.aliyuncs.com/test/audios/asr_example.wav")
 print(res)
diff --git a/examples/industrial_data_pretraining/conformer/demo.sh b/examples/industrial_data_pretraining/conformer/demo.sh
index 9cf6cc5..dc1314b 100644
--- a/examples/industrial_data_pretraining/conformer/demo.sh
+++ b/examples/industrial_data_pretraining/conformer/demo.sh
@@ -1,10 +1,8 @@
 
 model="iic/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch"
-model_revision="master"
 
 python funasr/bin/inference.py \
 +model=${model} \
-+model_revision=${model_revision} \
 +input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav" \
 +output_dir="./outputs/debug" \
 +device="cpu" \
diff --git a/examples/industrial_data_pretraining/contextual_paraformer/demo.py b/examples/industrial_data_pretraining/contextual_paraformer/demo.py
index cd93a4f..e7930df 100755
--- a/examples/industrial_data_pretraining/contextual_paraformer/demo.py
+++ b/examples/industrial_data_pretraining/contextual_paraformer/demo.py
@@ -5,7 +5,7 @@
 
 from funasr import AutoModel
 
-model = AutoModel(model="iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404", model_revision="master")
+model = AutoModel(model="iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404")
 
 res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
             hotword='杈炬懇闄� 榄旀惌')
diff --git a/examples/industrial_data_pretraining/contextual_paraformer/demo.sh b/examples/industrial_data_pretraining/contextual_paraformer/demo.sh
index e651338..17b005e 100755
--- a/examples/industrial_data_pretraining/contextual_paraformer/demo.sh
+++ b/examples/industrial_data_pretraining/contextual_paraformer/demo.sh
@@ -1,10 +1,9 @@
 
 model="iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404"
-model_revision="master"
+
 
 python ../../../funasr/bin/inference.py \
 +model=${model} \
-+model_revision=${model_revision} \
 +input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav" \
 +output_dir="./outputs/debug" \
 +device="cpu" \
diff --git a/examples/industrial_data_pretraining/contextual_paraformer/finetune.sh b/examples/industrial_data_pretraining/contextual_paraformer/finetune.sh
index fe12315..25c7330 100644
--- a/examples/industrial_data_pretraining/contextual_paraformer/finetune.sh
+++ b/examples/industrial_data_pretraining/contextual_paraformer/finetune.sh
@@ -11,7 +11,7 @@
 
 ## option 1, download model automatically
 model_name_or_model_dir="iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404"
-model_revision="master"
+
 
 ## option 2, download model by git
 #local_path_root=${workspace}/modelscope_models
diff --git a/examples/industrial_data_pretraining/ct_transformer/demo.py b/examples/industrial_data_pretraining/ct_transformer/demo.py
index 6e6b478..23f3dd7 100644
--- a/examples/industrial_data_pretraining/ct_transformer/demo.py
+++ b/examples/industrial_data_pretraining/ct_transformer/demo.py
@@ -5,7 +5,7 @@
 
 from funasr import AutoModel
 
-model = AutoModel(model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch", model_revision="master")
+model = AutoModel(model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch")
 
 res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt")
 print(res)
@@ -13,7 +13,7 @@
 
 from funasr import AutoModel
 
-model = AutoModel(model="iic/punc_ct-transformer_cn-en-common-vocab471067-large", model_revision="master")
+model = AutoModel(model="iic/punc_ct-transformer_cn-en-common-vocab471067-large")
 
 res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt")
 print(res)
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/ct_transformer/demo.sh b/examples/industrial_data_pretraining/ct_transformer/demo.sh
index 02ee5a8..6c63c02 100644
--- a/examples/industrial_data_pretraining/ct_transformer/demo.sh
+++ b/examples/industrial_data_pretraining/ct_transformer/demo.sh
@@ -1,13 +1,12 @@
 
 #model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
-#model_revision="master"
+#
 
 model="iic/punc_ct-transformer_cn-en-common-vocab471067-large"
-model_revision="master"
+
 
 python funasr/bin/inference.py \
 +model=${model} \
-+model_revision=${model_revision} \
 +input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt" \
 +output_dir="./outputs/debug" \
 +device="cpu"
diff --git a/examples/industrial_data_pretraining/ct_transformer/export.py b/examples/industrial_data_pretraining/ct_transformer/export.py
index 397bb96..c429a2f 100644
--- a/examples/industrial_data_pretraining/ct_transformer/export.py
+++ b/examples/industrial_data_pretraining/ct_transformer/export.py
@@ -8,7 +8,7 @@
 from funasr import AutoModel
 
 model = AutoModel(model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
-                  model_revision="master")
+                  )
 
 res = model.export(type="onnx", quantize=False)
 print(res)
diff --git a/examples/industrial_data_pretraining/ct_transformer/export.sh b/examples/industrial_data_pretraining/ct_transformer/export.sh
index 5f7e4fb..780bcad 100644
--- a/examples/industrial_data_pretraining/ct_transformer/export.sh
+++ b/examples/industrial_data_pretraining/ct_transformer/export.sh
@@ -6,7 +6,7 @@
 
 
 model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
-model_revision="master"
+
 
 python -m funasr.bin.export \
 ++model=${model} \
diff --git a/examples/industrial_data_pretraining/ct_transformer_streaming/demo.py b/examples/industrial_data_pretraining/ct_transformer_streaming/demo.py
index 14edbe4..c27a73b 100644
--- a/examples/industrial_data_pretraining/ct_transformer_streaming/demo.py
+++ b/examples/industrial_data_pretraining/ct_transformer_streaming/demo.py
@@ -5,7 +5,7 @@
 
 from funasr import AutoModel
 
-model = AutoModel(model="iic/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727", model_revision="master")
+model = AutoModel(model="iic/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727")
 
 inputs = "璺ㄥ娌虫祦鏄吇鑲叉部宀竱浜烘皯鐨勭敓鍛戒箣婧愰暱鏈熶互鏉ヤ负甯姪涓嬫父鍦板尯闃茬伨鍑忕伨涓柟鎶�鏈汉鍛榺鍦ㄤ笂娓稿湴鍖烘瀬涓烘伓鍔ｇ殑鑷劧鏉′欢涓嬪厠鏈嶅法澶у洶闅剧敋鑷冲啋鐫�鐢熷懡鍗遍櫓|鍚戝嵃鏂规彁渚涙睕鏈熸按鏂囪祫鏂欏鐞嗙揣鎬ヤ簨浠朵腑鏂归噸瑙嗗嵃鏂瑰湪璺ㄥ娌虫祦闂涓婄殑鍏冲垏|鎰挎剰杩涗竴姝ュ畬鍠勫弻鏂硅仈鍚堝伐浣滄満鍒秥鍑℃槸|涓柟鑳藉仛鐨勬垜浠瑋閮戒細鍘诲仛鑰屼笖浼氬仛寰楁洿濂芥垜璇峰嵃搴︽湅鍙嬩滑鏀惧績涓浗鍦ㄤ笂娓哥殑|浠讳綍寮�鍙戝埄鐢ㄩ兘浼氱粡杩囩瀛瑙勫垝鍜岃璇佸吋椤句笂涓嬫父鐨勫埄鐩�"
 vads = inputs.split("|")
diff --git a/examples/industrial_data_pretraining/ct_transformer_streaming/demo.sh b/examples/industrial_data_pretraining/ct_transformer_streaming/demo.sh
index ad3e3ea..84ab5a2 100644
--- a/examples/industrial_data_pretraining/ct_transformer_streaming/demo.sh
+++ b/examples/industrial_data_pretraining/ct_transformer_streaming/demo.sh
@@ -1,10 +1,9 @@
 
 model="iic/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727"
-model_revision="master"
+
 
 python funasr/bin/inference.py \
 +model=${model} \
-+model_revision=${model_revision} \
 +input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt" \
 +output_dir="./outputs/debug" \
 +device="cpu"
diff --git a/examples/industrial_data_pretraining/ct_transformer_streaming/export.py b/examples/industrial_data_pretraining/ct_transformer_streaming/export.py
index 2e3b172..ec1557b 100644
--- a/examples/industrial_data_pretraining/ct_transformer_streaming/export.py
+++ b/examples/industrial_data_pretraining/ct_transformer_streaming/export.py
@@ -8,7 +8,7 @@
 from funasr import AutoModel
 
 model = AutoModel(model="iic/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727",
-                  model_revision="master")
+                  )
 
 res = model.export(type="onnx", quantize=False)
 print(res)
diff --git a/examples/industrial_data_pretraining/ct_transformer_streaming/export.sh b/examples/industrial_data_pretraining/ct_transformer_streaming/export.sh
index a47f701..eb76978 100644
--- a/examples/industrial_data_pretraining/ct_transformer_streaming/export.sh
+++ b/examples/industrial_data_pretraining/ct_transformer_streaming/export.sh
@@ -6,7 +6,7 @@
 
 
 model="iic/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727"
-model_revision="master"
+
 
 python -m funasr.bin.export \
 ++model=${model} \
diff --git a/examples/industrial_data_pretraining/emotion2vec/demo.py b/examples/industrial_data_pretraining/emotion2vec/demo.py
index 50deda3..9e926ca 100644
--- a/examples/industrial_data_pretraining/emotion2vec/demo.py
+++ b/examples/industrial_data_pretraining/emotion2vec/demo.py
@@ -6,7 +6,7 @@
 from funasr import AutoModel
 
 # model="iic/emotion2vec_base"
-model = AutoModel(model="iic/emotion2vec_base_finetuned", model_revision="master",
+model = AutoModel(model="iic/emotion2vec_base_finetuned",
                   # vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
                   # vad_model_revision="master",
                   # vad_kwargs={"max_single_segment_time": 2000},
diff --git a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
index 61dce49..f131c8c 100644
--- a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
+++ b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
@@ -6,7 +6,7 @@
 from funasr import AutoModel
 wav_file = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav"
 
-model = AutoModel(model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch", model_revision="master")
+model = AutoModel(model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch")
 
 res = model.generate(input=wav_file)
 print(res)
diff --git a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.sh b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.sh
index 0248dd0..0d3623c 100644
--- a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.sh
+++ b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.sh
@@ -1,11 +1,10 @@
 
 
 model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch"
-model_revision="master"
+
 
 python funasr/bin/inference.py \
 +model=${model} \
-+model_revision=${model_revision} \
 +input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav" \
 +output_dir="./outputs/debug" \
 +device="cpu" \
diff --git a/examples/industrial_data_pretraining/fsmn_vad_streaming/export.py b/examples/industrial_data_pretraining/fsmn_vad_streaming/export.py
index f45ddee..a3546e1 100644
--- a/examples/industrial_data_pretraining/fsmn_vad_streaming/export.py
+++ b/examples/industrial_data_pretraining/fsmn_vad_streaming/export.py
@@ -8,7 +8,7 @@
 
 from funasr import AutoModel
 
-model = AutoModel(model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch", model_revision="master")
+model = AutoModel(model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch")
 
 res = model.export(type="onnx", quantize=False)
 print(res)
diff --git a/examples/industrial_data_pretraining/fsmn_vad_streaming/export.sh b/examples/industrial_data_pretraining/fsmn_vad_streaming/export.sh
index 9143dc3..e095544 100644
--- a/examples/industrial_data_pretraining/fsmn_vad_streaming/export.sh
+++ b/examples/industrial_data_pretraining/fsmn_vad_streaming/export.sh
@@ -7,7 +7,7 @@
 
 
 model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch"
-model_revision="master"
+
 
 python -m funasr.bin.export \
 ++model=${model} \
diff --git a/examples/industrial_data_pretraining/monotonic_aligner/demo.py b/examples/industrial_data_pretraining/monotonic_aligner/demo.py
index 467de1b..345076e 100644
--- a/examples/industrial_data_pretraining/monotonic_aligner/demo.py
+++ b/examples/industrial_data_pretraining/monotonic_aligner/demo.py
@@ -5,7 +5,7 @@
 
 from funasr import AutoModel
 
-model = AutoModel(model="iic/speech_timestamp_prediction-v1-16k-offline", model_revision="master")
+model = AutoModel(model="iic/speech_timestamp_prediction-v1-16k-offline")
 
 res = model.generate(input=("https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
                    "娆㈣繋澶у鏉ュ埌榄旀惌绀惧尯杩涜浣撻獙"),
diff --git a/examples/industrial_data_pretraining/monotonic_aligner/demo.sh b/examples/industrial_data_pretraining/monotonic_aligner/demo.sh
index 649ce70..8c54265 100644
--- a/examples/industrial_data_pretraining/monotonic_aligner/demo.sh
+++ b/examples/industrial_data_pretraining/monotonic_aligner/demo.sh
@@ -1,10 +1,9 @@
 
 model="iic/speech_timestamp_prediction-v1-16k-offline"
-model_revision="master"
+
 
 python funasr/bin/inference.py \
 +model=${model} \
-+model_revision=${model_revision} \
 +input='["https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", "娆㈣繋澶у鏉ュ埌榄旀惌绀惧尯杩涜浣撻獙"]' \
 +data_type='["sound", "text"]' \
 +output_dir="../outputs/debug" \
diff --git a/examples/industrial_data_pretraining/paraformer-zh-spk/README_zh.md b/examples/industrial_data_pretraining/paraformer-zh-spk/README_zh.md
new file mode 100644
index 0000000..24a20fb
--- /dev/null
+++ b/examples/industrial_data_pretraining/paraformer-zh-spk/README_zh.md
@@ -0,0 +1,432 @@
+(绠�浣撲腑鏂噟[English](./README.md))
+
+FunASR寮�婧愪簡澶ч噺鍦ㄥ伐涓氭暟鎹笂棰勮缁冩ā鍨嬶紝鎮ㄥ彲浠ュ湪 [妯″瀷璁稿彲鍗忚](https://github.com/alibaba-damo-academy/FunASR/blob/main/MODEL_LICENSE)涓嬭嚜鐢变娇鐢ㄣ�佸鍒躲�佷慨鏀瑰拰鍒嗕韩FunASR妯″瀷锛屼笅闈㈠垪涓句唬琛ㄦ�х殑妯″瀷锛屾洿澶氭ā鍨嬭鍙傝�� [妯″瀷浠撳簱](https://github.com/alibaba-damo-academy/FunASR/tree/main/model_zoo)銆�
+
+<div align="center">  
+<h4>
+ <a href="#妯″瀷鎺ㄧ悊"> 妯″瀷鎺ㄧ悊 </a>   
+锝�<a href="#妯″瀷璁粌涓庢祴璇�"> 妯″瀷璁粌涓庢祴璇� </a>
+锝�<a href="#妯″瀷瀵煎嚭涓庢祴璇�"> 妯″瀷瀵煎嚭涓庢祴璇� </a>
+</h4>
+</div>
+
+<a name="妯″瀷鎺ㄧ悊"></a>
+## 妯″瀷鎺ㄧ悊
+
+### 蹇�熶娇鐢�
+
+鍛戒护琛屾柟寮忚皟鐢細
+```shell
+funasr ++model=paraformer-zh ++vad_model="fsmn-vad" ++punc_model="ct-punc" ++input=asr_example_zh.wav
+```
+
+python浠ｇ爜璋冪敤锛堟帹鑽愶級
+
+```python
+from funasr import AutoModel
+
+model = AutoModel(model="paraformer-zh")
+
+res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav")
+print(res)
+```
+
+### 鎺ュ彛璇存槑
+
+#### AutoModel 瀹氫箟
+```python
+model = AutoModel(model=[str], device=[str], ncpu=[int], output_dir=[str], batch_size=[int], hub=[str], **kwargs)
+```
+- `model`(str): [妯″瀷浠撳簱](https://github.com/alibaba-damo-academy/FunASR/tree/main/model_zoo) 涓殑妯″瀷鍚嶇О锛屾垨鏈湴纾佺洏涓殑妯″瀷璺緞
+- `device`(str): `cuda:0`锛堥粯璁pu0锛夛紝浣跨敤 GPU 杩涜鎺ㄧ悊锛屾寚瀹氥�傚鏋滀负`cpu`锛屽垯浣跨敤 CPU 杩涜鎺ㄧ悊
+- `ncpu`(int): `4` 锛堥粯璁わ級锛岃缃敤浜� CPU 鍐呴儴鎿嶄綔骞惰鎬х殑绾跨▼鏁�
+- `output_dir`(str): `None` 锛堥粯璁わ級锛屽鏋滆缃紝杈撳嚭缁撴灉鐨勮緭鍑鸿矾寰�
+- `batch_size`(int): `1` 锛堥粯璁わ級锛岃В鐮佹椂鐨勬壒澶勭悊锛屾牱鏈釜鏁�
+- `hub`(str)锛歚ms`锛堥粯璁わ級锛屼粠modelscope涓嬭浇妯″瀷銆傚鏋滀负`hf`锛屼粠huggingface涓嬭浇妯″瀷銆�
+- `**kwargs`(dict): 鎵�鏈夊湪`config.yaml`涓弬鏁帮紝鍧囧彲浠ョ洿鎺ュ湪姝ゅ鎸囧畾锛屼緥濡傦紝vad妯″瀷涓渶澶у垏鍓查暱搴� `max_single_segment_time=6000` 锛堟绉掞級銆�
+
+#### AutoModel 鎺ㄧ悊
+```python
+res = model.generate(input=[str], output_dir=[str])
+```
+- `input`: 瑕佽В鐮佺殑杈撳叆锛屽彲浠ユ槸锛�
+  - wav鏂囦欢璺緞, 渚嬪: asr_example.wav
+  - pcm鏂囦欢璺緞, 渚嬪: asr_example.pcm锛屾鏃堕渶瑕佹寚瀹氶煶棰戦噰鏍风巼fs锛堥粯璁や负16000锛�
+  - 闊抽瀛楄妭鏁版祦锛屼緥濡傦細楹﹀厠椋庣殑瀛楄妭鏁版暟鎹�
+  - wav.scp锛宬aldi 鏍峰紡鐨� wav 鍒楄〃 (`wav_id \t wav_path`), 渚嬪:
+  ```text
+  asr_example1  ./audios/asr_example1.wav
+  asr_example2  ./audios/asr_example2.wav
+  ```
+  鍦ㄨ繖绉嶈緭鍏� `wav.scp` 鐨勬儏鍐典笅锛屽繀椤昏缃� `output_dir` 浠ヤ繚瀛樿緭鍑虹粨鏋�
+  - 闊抽閲囨牱鐐癸紝渚嬪锛歚audio, rate = soundfile.read("asr_example_zh.wav")`, 鏁版嵁绫诲瀷涓� numpy.ndarray銆傛敮鎸乥atch杈撳叆锛岀被鍨嬩负list锛�
+  ```[audio_sample1, audio_sample2, ..., audio_sampleN]```
+  - fbank杈撳叆锛屾敮鎸佺粍batch銆俿hape涓篬batch, frames, dim]锛岀被鍨嬩负torch.Tensor锛屼緥濡�
+- `output_dir`: None 锛堥粯璁わ級锛屽鏋滆缃紝杈撳嚭缁撴灉鐨勮緭鍑鸿矾寰�
+- `**kwargs`(dict): 涓庢ā鍨嬬浉鍏崇殑鎺ㄧ悊鍙傛暟锛屼緥濡傦紝`beam_size=10`锛宍decoding_ctc_weight=0.1`銆�
+
+
+### 鏇村鐢ㄦ硶浠嬬粛
+
+
+#### 闈炲疄鏃惰闊宠瘑鍒�
+```python
+from funasr import AutoModel
+# paraformer-zh is a multi-functional asr model
+# use vad, punc, spk or not as you need
+model = AutoModel(model="paraformer-zh",  
+                  vad_model="fsmn-vad", 
+                  vad_kwargs={"max_single_segment_time": 60000},
+                  punc_model="ct-punc", 
+                  # spk_model="cam++"
+                  )
+wav_file = f"{model.model_path}/example/asr_example.wav"
+res = model.generate(input=wav_file, batch_size_s=300, batch_size_threshold_s=60, hotword='榄旀惌')
+print(res)
+```
+娉ㄦ剰锛�
+- 閫氬父妯″瀷杈撳叆闄愬埗鏃堕暱30s浠ヤ笅锛岀粍鍚坄vad_model`鍚庯紝鏀寔浠绘剰鏃堕暱闊抽杈撳叆锛屼笉灞�闄愪簬paraformer妯″瀷锛屾墍鏈夐煶棰戣緭鍏ユā鍨嬪潎鍙互銆�
+- `model`鐩稿叧鐨勫弬鏁板彲浠ョ洿鎺ュ湪`AutoModel`瀹氫箟涓洿鎺ユ寚瀹氾紱涓巂vad_model`鐩稿叧鍙傛暟鍙互閫氳繃`vad_kwargs`鏉ユ寚瀹氾紝绫诲瀷涓篸ict锛涚被浼肩殑鏈塦punc_kwargs`锛宍spk_kwargs`锛�
+- `max_single_segment_time`: 琛ㄧず`vad_model`鏈�澶у垏鍓查煶棰戞椂闀�, 鍗曚綅鏄绉抦s.
+- `batch_size_s` 琛ㄧず閲囩敤鍔ㄦ�乥atch锛宐atch涓�婚煶棰戞椂闀匡紝鍗曚綅涓虹s銆�
+- `batch_size_threshold_s`: 琛ㄧず`vad_model`鍒囧壊鍚庨煶棰戠墖娈垫椂闀胯秴杩� `batch_size_threshold_s`闃堝�兼椂锛屽皢batch_size鏁拌缃负1, 鍗曚綅涓虹s.
+
+寤鸿锛氬綋鎮ㄨ緭鍏ヤ负闀块煶棰戯紝閬囧埌OOM闂鏃讹紝鍥犱负鏄惧瓨鍗犵敤涓庨煶棰戞椂闀垮憟骞虫柟鍏崇郴澧炲姞锛屽垎涓�3绉嶆儏鍐碉細
+- a)鎺ㄧ悊璧峰闃舵锛屾樉瀛樹富瑕佸彇鍐充簬`batch_size_s`锛岄�傚綋鍑忓皬璇ュ�硷紝鍙互鍑忓皯鏄惧瓨鍗犵敤锛�
+- b)鎺ㄧ悊涓棿闃舵锛岄亣鍒癡AD鍒囧壊鐨勯暱闊抽鐗囨锛屾�籺oken鏁板皬浜巂batch_size_s`锛屼粛鐒跺嚭鐜癘OM锛屽彲浠ラ�傚綋鍑忓皬`batch_size_threshold_s`锛岃秴杩囬槇鍊硷紝寮哄埗batch涓�1; 
+- c)鎺ㄧ悊蹇粨鏉熼樁娈碉紝閬囧埌VAD鍒囧壊鐨勯暱闊抽鐗囨锛屾�籺oken鏁板皬浜巂batch_size_s`锛屼笖瓒呰繃闃堝�糮batch_size_threshold_s`锛屽己鍒禸atch涓�1锛屼粛鐒跺嚭鐜癘OM锛屽彲浠ラ�傚綋鍑忓皬`max_single_segment_time`锛屼娇寰梀AD鍒囧壊闊抽鏃堕暱鍙樼煭銆�
+
+#### 瀹炴椂璇煶璇嗗埆
+
+```python
+from funasr import AutoModel
+
+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
+
+model = AutoModel(model="paraformer-zh-streaming")
+
+import soundfile
+import os
+
+wav_file = os.path.join(model.model_path, "example/asr_example.wav")
+speech, sample_rate = soundfile.read(wav_file)
+chunk_stride = chunk_size[1] * 960 # 600ms
+
+cache = {}
+total_chunk_num = int(len((speech)-1)/chunk_stride+1)
+for i in range(total_chunk_num):
+    speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
+    is_final = i == total_chunk_num - 1
+    res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
+    print(res)
+```
+
+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�
+
+#### 璇煶绔偣妫�娴嬶紙闈炲疄鏃讹級
+```python
+from funasr import AutoModel
+
+model = AutoModel(model="fsmn-vad")
+
+wav_file = f"{model.model_path}/example/asr_example.wav"
+res = model.generate(input=wav_file)
+print(res)
+```
+娉細VAD妯″瀷杈撳嚭鏍煎紡涓猴細`[[beg1, end1], [beg2, end2], .., [begN, endN]]`锛屽叾涓璥begN/endN`琛ㄧず绗琡N`涓湁鏁堥煶棰戠墖娈电殑璧峰鐐�/缁撴潫鐐癸紝
+鍗曚綅涓烘绉掋��
+
+#### 璇煶绔偣妫�娴嬶紙瀹炴椂锛�
+```python
+from funasr import AutoModel
+
+chunk_size = 200 # ms
+model = AutoModel(model="fsmn-vad")
+
+import soundfile
+
+wav_file = f"{model.model_path}/example/vad_example.wav"
+speech, sample_rate = soundfile.read(wav_file)
+chunk_stride = int(chunk_size * sample_rate / 1000)
+
+cache = {}
+total_chunk_num = int(len((speech)-1)/chunk_stride+1)
+for i in range(total_chunk_num):
+    speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
+    is_final = i == total_chunk_num - 1
+    res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
+    if len(res[0]["value"]):
+        print(res)
+```
+娉細娴佸紡VAD妯″瀷杈撳嚭鏍煎紡涓�4绉嶆儏鍐碉細
+- `[[beg1, end1], [beg2, end2], .., [begN, endN]]`锛氬悓涓婄绾縑AD杈撳嚭缁撴灉銆�
+- `[[beg, -1]]`锛氳〃绀哄彧妫�娴嬪埌璧峰鐐广��
+- `[[-1, end]]`锛氳〃绀哄彧妫�娴嬪埌缁撴潫鐐广��
+- `[]`锛氳〃绀烘棦娌℃湁妫�娴嬪埌璧峰鐐癸紝涔熸病鏈夋娴嬪埌缁撴潫鐐�
+杈撳嚭缁撴灉鍗曚綅涓烘绉掞紝浠庤捣濮嬬偣寮�濮嬬殑缁濆鏃堕棿銆�
+
+#### 鏍囩偣鎭㈠
+```python
+from funasr import AutoModel
+
+model = AutoModel(model="ct-punc")
+
+res = model.generate(input="閭ｄ粖澶╃殑浼氬氨鍒拌繖閲屽惂 happy new year 鏄庡勾瑙�")
+print(res)
+```
+
+#### 鏃堕棿鎴抽娴�
+```python
+from funasr import AutoModel
+
+model = AutoModel(model="fa-zh")
+
+wav_file = f"{model.model_path}/example/asr_example.wav"
+text_file = f"{model.model_path}/example/text.txt"
+res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
+print(res)
+```
+鏇村锛圼绀轰緥](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining)锛�
+
+<a name="鏍稿績鍔熻兘"></a>
+## 妯″瀷璁粌涓庢祴璇�
+
+### 蹇�熷紑濮�
+
+鍛戒护琛屾墽琛岋紙鐢ㄤ簬蹇�熸祴璇曪紝涓嶆帹鑽愶級锛�
+```shell
+funasr-train ++model=paraformer-zh ++train_data_set_list=data/list/train.jsonl ++valid_data_set_list=data/list/val.jsonl ++output_dir="./outputs" &> log.txt &
+```
+
+python浠ｇ爜鎵ц锛堝彲浠ュ鏈哄鍗★紝鎺ㄨ崘锛�
+
+```shell
+cd examples/industrial_data_pretraining/paraformer
+bash finetune.sh
+# "log_file: ./outputs/log.txt"
+```
+璇︾粏瀹屾暣鐨勮剼鏈弬鑰� [finetune.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/examples/industrial_data_pretraining/paraformer/finetune.sh)
+
+### 璇︾粏鍙傛暟浠嬬粛
+
+```shell
+funasr/bin/train.py \
+++model="${model_name_or_model_dir}" \
+++train_data_set_list="${train_data}" \
+++valid_data_set_list="${val_data}" \
+++dataset_conf.batch_size=20000 \
+++dataset_conf.batch_type="token" \
+++dataset_conf.num_workers=4 \
+++train_conf.max_epoch=50 \
+++train_conf.log_interval=1 \
+++train_conf.resume=false \
+++train_conf.validate_interval=2000 \
+++train_conf.save_checkpoint_interval=2000 \
+++train_conf.keep_nbest_models=20 \
+++train_conf.avg_nbest_model=5 \
+++optim_conf.lr=0.0002 \
+++output_dir="${output_dir}" &> ${log_file}
+```
+
+- `model`锛坰tr锛夛細妯″瀷鍚嶅瓧锛堟ā鍨嬩粨搴撲腑鐨処D锛夛紝姝ゆ椂鑴氭湰浼氳嚜鍔ㄤ笅杞芥ā鍨嬪埌鏈锛涙垨鑰呮湰鍦板凡缁忎笅杞藉ソ鐨勬ā鍨嬭矾寰勩��
+- `train_data_set_list`锛坰tr锛夛細璁粌鏁版嵁璺緞锛岄粯璁や负jsonl鏍煎紡锛屽叿浣撳弬鑰冿紙[渚嬪瓙](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)锛夈��
+- `valid_data_set_list`锛坰tr锛夛細楠岃瘉鏁版嵁璺緞锛岄粯璁や负jsonl鏍煎紡锛屽叿浣撳弬鑰冿紙[渚嬪瓙](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)锛夈��
+- `dataset_conf.batch_type`锛坰tr锛夛細`example`锛堥粯璁わ級锛宐atch鐨勭被鍨嬨�俙example`琛ㄧず鎸夌収鍥哄畾鏁扮洰batch_size涓牱鏈粍batch锛沗length` or `token` 琛ㄧず鍔ㄦ�佺粍batch锛宐atch鎬婚暱搴︽垨鑰卼oken鏁颁负batch_size銆�
+- `dataset_conf.batch_size`锛坕nt锛夛細涓� `batch_type` 鎼厤浣跨敤锛屽綋 `batch_type=example` 鏃讹紝琛ㄧず鏍锋湰涓暟锛涘綋 `batch_type=length` 鏃讹紝琛ㄧず鏍锋湰涓暱搴︼紝鍗曚綅涓篺bank甯ф暟锛�1甯�10ms锛夋垨鑰呮枃瀛梩oken涓暟銆�
+- `train_conf.max_epoch`锛坕nt锛夛細璁粌鎬籩poch鏁般��
+- `train_conf.log_interval`锛坕nt锛夛細鎵撳嵃鏃ュ織闂撮殧step鏁般��
+- `train_conf.resume`锛坕nt锛夛細鏄惁寮�鍚柇鐐归噸璁��
+- `train_conf.validate_interval`锛坕nt锛夛細璁粌涓仛楠岃瘉娴嬭瘯鐨勯棿闅攕tep鏁般��
+- `train_conf.save_checkpoint_interval`锛坕nt锛夛細璁粌涓ā鍨嬩繚瀛橀棿闅攕tep鏁般��
+- `train_conf.keep_nbest_models`锛坕nt锛夛細淇濈暀鏈�澶у灏戜釜妯″瀷鍙傛暟锛屾寜鐓ч獙璇侀泦acc鎺掑簭锛屼粠楂樺埌搴曚繚鐣欍��
+- `train_conf.avg_nbest_model`锛坕nt锛夛細瀵筧cc鏈�楂樼殑n涓ā鍨嬪彇骞冲潎銆�
+- `optim_conf.lr`锛坒loat锛夛細瀛︿範鐜囥��
+- `output_dir`锛坰tr锛夛細妯″瀷淇濆瓨璺緞銆�
+- `**kwargs`(dict): 鎵�鏈夊湪`config.yaml`涓弬鏁帮紝鍧囧彲浠ョ洿鎺ュ湪姝ゅ鎸囧畾锛屼緥濡傦紝杩囨护20s浠ヤ笂闀块煶棰戯細`dataset_conf.max_token_length=2000`锛屽崟浣嶄负闊抽fbank甯ф暟锛�1甯�10ms锛夋垨鑰呮枃瀛梩oken涓暟銆�
+
+#### 澶歡pu璁粌
+##### 鍗曟満澶歡pu璁粌
+```shell
+export CUDA_VISIBLE_DEVICES="0,1"
+gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+
+torchrun --nnodes 1 --nproc_per_node ${gpu_num} \
+../../../funasr/bin/train.py ${train_args}
+```
+--nnodes 琛ㄧず鍙備笌鐨勮妭鐐规�绘暟锛�--nproc_per_node 琛ㄧず姣忎釜鑺傜偣涓婅繍琛岀殑杩涚▼鏁�
+
+##### 澶氭満澶歡pu璁粌
+
+鍦ㄤ富鑺傜偣涓婏紝鍋囪IP涓�192.168.1.1锛岀鍙ｄ负12345锛屼娇鐢ㄧ殑鏄�2涓狦PU锛屽垯杩愯濡備笅鍛戒护锛�
+```shell
+export CUDA_VISIBLE_DEVICES="0,1"
+gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+
+torchrun --nnodes 2 --nproc_per_node ${gpu_num} --master_addr=192.168.1.1 --master_port=12345 \
+../../../funasr/bin/train.py ${train_args}
+```
+鍦ㄤ粠鑺傜偣涓婏紙鍋囪IP涓�192.168.1.2锛夛紝浣犻渶瑕佺‘淇滿ASTER_ADDR鍜孧ASTER_PORT鐜鍙橀噺涓庝富鑺傜偣璁剧疆鐨勪竴鑷达紝骞惰繍琛屽悓鏍风殑鍛戒护锛�
+```shell
+export CUDA_VISIBLE_DEVICES="0,1"
+gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+
+torchrun --nnodes 2 --nproc_per_node ${gpu_num} --master_addr=192.168.1.1 --master_port=12345 \
+../../../funasr/bin/train.py ${train_args}
+```
+
+--nnodes 琛ㄧず鍙備笌鐨勮妭鐐规�绘暟锛�--nproc_per_node 琛ㄧず姣忎釜鑺傜偣涓婅繍琛岀殑杩涚▼鏁�
+
+#### 鍑嗗鏁版嵁
+
+`jsonl`鏍煎紡鍙互鍙傝�冿紙[渚嬪瓙](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)锛夈��
+鍙互鐢ㄦ寚浠� `scp2jsonl` 浠巜av.scp涓巘ext.txt鐢熸垚銆倃av.scp涓巘ext.txt鍑嗗杩囩▼濡備笅锛�
+
+`train_text.txt`
+
+宸﹁竟涓烘暟鎹敮涓�ID锛岄渶涓巂train_wav.scp`涓殑`ID`涓�涓�瀵瑰簲
+鍙宠竟涓洪煶棰戞枃浠舵爣娉ㄦ枃鏈紝鏍煎紡濡備笅锛�
+
+```bash
+ID0012W0013 褰撳鎴烽闄╂壙鍙楄兘鍔涜瘎浼颁緷鎹彂鐢熷彉鍖栨椂
+ID0012W0014 鎵�鏈夊彧瑕佸鐞� data 涓嶇浣犳槸鍋� machine learning 鍋� deep learning
+ID0012W0015 he tried to think how it could be
+```
+
+
+`train_wav.scp`
+
+宸﹁竟涓烘暟鎹敮涓�ID锛岄渶涓巂train_text.txt`涓殑`ID`涓�涓�瀵瑰簲
+鍙宠竟涓洪煶棰戞枃浠剁殑璺緞锛屾牸寮忓涓�
+
+```bash
+BAC009S0764W0121 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/BAC009S0764W0121.wav
+BAC009S0916W0489 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/BAC009S0916W0489.wav
+ID0012W0015 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cn_en.wav
+```
+
+`鐢熸垚鎸囦护`
+
+```shell
+# generate train.jsonl and val.jsonl from wav.scp and text.txt
+scp2jsonl \
+++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
+++data_type_list='["source", "target"]' \
+++jsonl_file_out="../../../data/list/train.jsonl"
+```
+
+锛堝彲閫夛紝闈炲繀闇�锛夊鏋滈渶瑕佷粠jsonl瑙ｆ瀽鎴恮av.scp涓巘ext.txt锛屽彲浠ヤ娇鐢ㄦ寚浠わ細
+
+```shell
+# generate wav.scp and text.txt from train.jsonl and val.jsonl
+jsonl2scp \
+++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
+++data_type_list='["source", "target"]' \
+++jsonl_file_in="../../../data/list/train.jsonl"
+```
+
+#### 鏌ョ湅璁粌鏃ュ織
+
+##### 鏌ョ湅瀹為獙log
+```shell
+tail log.txt
+[2024-03-21 15:55:52,137][root][INFO] - train, rank: 3, epoch: 0/50, step: 6990/1, total step: 6990, (loss_avg_rank: 0.327), (loss_avg_epoch: 0.409), (ppl_avg_epoch: 1.506), (acc_avg_epoch: 0.795), (lr: 1.165e-04), [('loss_att', 0.259), ('acc', 0.825), ('loss_pre', 0.04), ('loss', 0.299), ('batch_size', 40)], {'data_load': '0.000', 'forward_time': '0.315', 'backward_time': '0.555', 'optim_time': '0.076', 'total_time': '0.947'}, GPU, memory: usage: 3.830 GB, peak: 18.357 GB, cache: 20.910 GB, cache_peak: 20.910 GB
+[2024-03-21 15:55:52,139][root][INFO] - train, rank: 1, epoch: 0/50, step: 6990/1, total step: 6990, (loss_avg_rank: 0.334), (loss_avg_epoch: 0.409), (ppl_avg_epoch: 1.506), (acc_avg_epoch: 0.795), (lr: 1.165e-04), [('loss_att', 0.285), ('acc', 0.823), ('loss_pre', 0.046), ('loss', 0.331), ('batch_size', 36)], {'data_load': '0.000', 'forward_time': '0.334', 'backward_time': '0.536', 'optim_time': '0.077', 'total_time': '0.948'}, GPU, memory: usage: 3.943 GB, peak: 18.291 GB, cache: 19.619 GB, cache_peak: 19.619 GB
+```
+鎸囨爣瑙ｉ噴锛�
+- `rank`锛氳〃绀篻pu id銆�
+- `epoch`,`step`,`total step`锛氳〃绀哄綋鍓峞poch锛宻tep锛屾�籹tep銆�
+- `loss_avg_rank`锛氳〃绀哄綋鍓峴tep锛屾墍鏈塯pu骞冲潎loss銆�
+- `loss/ppl/acc_avg_epoch`锛氳〃绀哄綋鍓峞poch鍛ㄦ湡锛屾埅姝㈠綋鍓峴tep鏁版椂锛屾�诲钩鍧噇oss/ppl/acc銆俥poch缁撴潫鏃剁殑鏈�鍚庝竴涓猻tep琛ㄧずepoch鎬诲钩鍧噇oss/ppl/acc锛屾帹鑽愪娇鐢╝cc鎸囨爣銆�
+- `lr`锛氬綋鍓峴tep鐨勫涔犵巼銆�
+- `[('loss_att', 0.259), ('acc', 0.825), ('loss_pre', 0.04), ('loss', 0.299), ('batch_size', 40)]`锛氳〃绀哄綋鍓峠pu id鐨勫叿浣撴暟鎹��
+- `total_time`锛氳〃绀哄崟涓猻tep鎬昏�楁椂銆�
+- `GPU, memory`锛氬垎鍒〃绀猴紝妯″瀷浣跨敤/宄板�兼樉瀛橈紝妯″瀷+缂撳瓨浣跨敤/宄板�兼樉瀛樸��
+
+##### tensorboard鍙鍖�
+```bash
+tensorboard --logdir /xxxx/FunASR/examples/industrial_data_pretraining/paraformer/outputs/log/tensorboard
+```
+娴忚鍣ㄤ腑鎵撳紑锛歨ttp://localhost:6006/
+
+### 璁粌鍚庢ā鍨嬫祴璇�
+
+
+#### 鏈塩onfiguration.json
+
+鍋囧畾锛岃缁冩ā鍨嬭矾寰勪负锛�./model_dir锛屽鏋滄敼鐩綍涓嬫湁鐢熸垚configuration.json锛屽彧闇�瑕佸皢 [涓婅堪妯″瀷鎺ㄧ悊鏂规硶](https://github.com/alibaba-damo-academy/FunASR/blob/main/examples/README_zh.md#%E6%A8%A1%E5%9E%8B%E6%8E%A8%E7%90%86) 涓ā鍨嬪悕瀛椾慨鏀逛负妯″瀷璺緞鍗冲彲
+
+渚嬪锛�
+
+浠巗hell鎺ㄧ悊
+```shell
+python -m funasr.bin.inference ++model="./model_dir" ++input=="${input}" ++output_dir="${output_dir}"
+```
+浠巔ython鎺ㄧ悊
+
+```python
+from funasr import AutoModel
+
+model = AutoModel(model="./model_dir")
+
+res = model.generate(input=wav_file)
+print(res)
+```
+
+#### 鏃燾onfiguration.json鏃�
+
+濡傛灉妯″瀷璺緞涓棤configuration.json鏃讹紝闇�瑕佹墜鍔ㄦ寚瀹氬叿浣撻厤缃枃浠惰矾寰勪笌妯″瀷璺緞
+
+```shell
+python -m funasr.bin.inference \
+--config-path "${local_path}" \
+--config-name "${config}" \
+++init_param="${init_param}" \
+++tokenizer_conf.token_list="${tokens}" \
+++frontend_conf.cmvn_file="${cmvn_file}" \
+++input="${input}" \
+++output_dir="${output_dir}" \
+++device="${device}"
+```
+
+鍙傛暟浠嬬粛
+- `config-path`锛氫负瀹為獙涓繚瀛樼殑 `config.yaml`锛屽彲浠ヤ粠瀹為獙杈撳嚭鐩綍涓煡鎵俱��
+- `config-name`锛氶厤缃枃浠跺悕锛屼竴鑸负 `config.yaml`锛屾敮鎸亂aml鏍煎紡涓巎son鏍煎紡锛屼緥濡� `config.json`
+- `init_param`锛氶渶瑕佹祴璇曠殑妯″瀷鍙傛暟锛屼竴鑸负`model.pt`锛屽彲浠ヨ嚜宸遍�夋嫨鍏蜂綋鐨勬ā鍨嬫枃浠�
+- `tokenizer_conf.token_list`锛氳瘝琛ㄦ枃浠惰矾寰勶紝涓�鑸湪 `config.yaml` 鏈夋寚瀹氾紝鏃犻渶鍐嶆墜鍔ㄦ寚瀹氾紝褰� `config.yaml` 涓矾寰勪笉姝ｇ‘鏃讹紝闇�瑕佸湪姝ゅ鎵嬪姩鎸囧畾銆�
+- `frontend_conf.cmvn_file`锛歸av鎻愬彇fbank涓敤鍒扮殑cmvn鏂囦欢锛屼竴鑸湪 `config.yaml` 鏈夋寚瀹氾紝鏃犻渶鍐嶆墜鍔ㄦ寚瀹氾紝褰� `config.yaml` 涓矾寰勪笉姝ｇ‘鏃讹紝闇�瑕佸湪姝ゅ鎵嬪姩鎸囧畾銆�
+
+鍏朵粬鍙傛暟鍚屼笂锛屽畬鏁� [绀轰緥](https://github.com/alibaba-damo-academy/FunASR/blob/main/examples/industrial_data_pretraining/paraformer/infer_from_local.sh)
+
+
+<a name="妯″瀷瀵煎嚭涓庢祴璇�"></a>
+## 妯″瀷瀵煎嚭涓庢祴璇�
+### 浠庡懡浠よ瀵煎嚭
+```shell
+funasr-export ++model=paraformer ++quantize=false
+```
+
+### 浠嶱ython瀵煎嚭
+```python
+from funasr import AutoModel
+
+model = AutoModel(model="paraformer")
+
+res = model.export(quantize=False)
+```
+
+### 娴嬭瘯ONNX
+```python
+# pip3 install -U funasr-onnx
+from funasr_onnx import Paraformer
+model_dir = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+model = Paraformer(model_dir, batch_size=1, quantize=True)
+
+wav_path = ['~/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav']
+
+result = model(wav_path)
+print(result)
+```
+
+鏇村渚嬪瓙璇峰弬鑰� [鏍蜂緥](runtime/python/onnxruntime)
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/paraformer-zh-spk/demo.py b/examples/industrial_data_pretraining/paraformer-zh-spk/demo.py
index 523bb3a..2a83509 100644
--- a/examples/industrial_data_pretraining/paraformer-zh-spk/demo.py
+++ b/examples/industrial_data_pretraining/paraformer-zh-spk/demo.py
@@ -6,13 +6,9 @@
 from funasr import AutoModel
 
 model = AutoModel(model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
-                  model_revision="master",
                   vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
-                  vad_model_revision="master",
                   punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
-                  punc_model_revision="master",
                   # spk_model="iic/speech_campplus_sv_zh-cn_16k-common",
-                  # spk_model_revision="v2.0.2"
                   )
 
 res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
diff --git a/examples/industrial_data_pretraining/paraformer-zh-spk/demo.sh b/examples/industrial_data_pretraining/paraformer-zh-spk/demo.sh
index fb0c4d9..ab94179 100644
--- a/examples/industrial_data_pretraining/paraformer-zh-spk/demo.sh
+++ b/examples/industrial_data_pretraining/paraformer-zh-spk/demo.sh
@@ -1,23 +1,16 @@
 
 model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="master"
 vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch"
-vad_model_revision="master"
-punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
-punc_model_revision="master"
+#punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
+punc_model="iic/punc_ct-transformer_cn-en-common-vocab471067-large"
 spk_model="iic/speech_campplus_sv_zh-cn_16k-common"
-spk_model_revision="v2.0.2"
 
 python funasr/bin/inference.py \
-+model=${model} \
-+model_revision=${model_revision} \
-+vad_model=${vad_model} \
-+vad_model_revision=${vad_model_revision} \
-+punc_model=${punc_model} \
-+punc_model_revision=${punc_model_revision} \
-+spk_model=${spk_model} \
-+spk_model_revision=${spk_model_revision} \
-+input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav" \
-+output_dir="./outputs/debug" \
-+device="cpu" \
-+"hotword='杈炬懇闄� 榄旀惌'"
+++model=${model} \
+++vad_model=${vad_model} \
+++punc_model=${punc_model} \
+++spk_model=${spk_model} \
+++input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav" \
+++output_dir="./outputs/debug" \
+++device="cpu" \
+++"hotword='杈炬懇闄� 榄旀惌'"
diff --git a/examples/industrial_data_pretraining/paraformer/README_zh.md b/examples/industrial_data_pretraining/paraformer/README_zh.md
index 60c3d97..24a20fb 100644
--- a/examples/industrial_data_pretraining/paraformer/README_zh.md
+++ b/examples/industrial_data_pretraining/paraformer/README_zh.md
@@ -214,7 +214,6 @@
 ```shell
 funasr/bin/train.py \
 ++model="${model_name_or_model_dir}" \
-++model_revision="${model_revision}" \
 ++train_data_set_list="${train_data}" \
 ++valid_data_set_list="${val_data}" \
 ++dataset_conf.batch_size=20000 \
@@ -232,7 +231,6 @@
 ```
 
 - `model`锛坰tr锛夛細妯″瀷鍚嶅瓧锛堟ā鍨嬩粨搴撲腑鐨処D锛夛紝姝ゆ椂鑴氭湰浼氳嚜鍔ㄤ笅杞芥ā鍨嬪埌鏈锛涙垨鑰呮湰鍦板凡缁忎笅杞藉ソ鐨勬ā鍨嬭矾寰勩��
-- `model_revision`锛坰tr锛夛細褰� `model` 涓烘ā鍨嬪悕瀛楁椂锛屼笅杞芥寚瀹氱増鏈殑妯″瀷銆�
 - `train_data_set_list`锛坰tr锛夛細璁粌鏁版嵁璺緞锛岄粯璁や负jsonl鏍煎紡锛屽叿浣撳弬鑰冿紙[渚嬪瓙](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)锛夈��
 - `valid_data_set_list`锛坰tr锛夛細楠岃瘉鏁版嵁璺緞锛岄粯璁や负jsonl鏍煎紡锛屽叿浣撳弬鑰冿紙[渚嬪瓙](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)锛夈��
 - `dataset_conf.batch_type`锛坰tr锛夛細`example`锛堥粯璁わ級锛宐atch鐨勭被鍨嬨�俙example`琛ㄧず鎸夌収鍥哄畾鏁扮洰batch_size涓牱鏈粍batch锛沗length` or `token` 琛ㄧず鍔ㄦ�佺粍batch锛宐atch鎬婚暱搴︽垨鑰卼oken鏁颁负batch_size銆�
diff --git a/examples/industrial_data_pretraining/paraformer/demo.py b/examples/industrial_data_pretraining/paraformer/demo.py
index 6cef234..e6bf534 100644
--- a/examples/industrial_data_pretraining/paraformer/demo.py
+++ b/examples/industrial_data_pretraining/paraformer/demo.py
@@ -5,15 +5,11 @@
 
 from funasr import AutoModel
 
-model = AutoModel(model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch", 
-                  model_revision="master",
+model = AutoModel(model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
                   vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
-                  vad_model_revision="master",
                   vad_kwargs={"max_single_segment_time": 60000},
                   punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
-                  punc_model_revision="master",
                   # spk_model="iic/speech_campplus_sv_zh-cn_16k-common",
-                  # spk_model_revision="v2.0.2",
                   )
 
 res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
@@ -23,7 +19,7 @@
 ''' can not use currently
 from funasr import AutoFrontend
 
-frontend = AutoFrontend(model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revision="master")
+frontend = AutoFrontend(model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
 
 fbanks = frontend(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", batch_size=2)
 
diff --git a/examples/industrial_data_pretraining/paraformer/export.py b/examples/industrial_data_pretraining/paraformer/export.py
index 0c181c1..1c86927 100644
--- a/examples/industrial_data_pretraining/paraformer/export.py
+++ b/examples/industrial_data_pretraining/paraformer/export.py
@@ -9,8 +9,7 @@
 
 from funasr import AutoModel
 
-model = AutoModel(model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
-                  model_revision="master")
+model = AutoModel(model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",)
 
 res = model.export(type="onnx", quantize=False)
 print(res)
diff --git a/examples/industrial_data_pretraining/paraformer/export.sh b/examples/industrial_data_pretraining/paraformer/export.sh
index 18d2039..0880829 100644
--- a/examples/industrial_data_pretraining/paraformer/export.sh
+++ b/examples/industrial_data_pretraining/paraformer/export.sh
@@ -6,12 +6,11 @@
 
 
 model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="master"
+
 
 
 python -m funasr.bin.export \
 ++model=${model} \
-++model_revision=${model_revision} \
 ++type="onnx" \
 ++quantize=false
 
diff --git a/examples/industrial_data_pretraining/paraformer/finetune.sh b/examples/industrial_data_pretraining/paraformer/finetune.sh
index 408076b..fe82ecb 100644
--- a/examples/industrial_data_pretraining/paraformer/finetune.sh
+++ b/examples/industrial_data_pretraining/paraformer/finetune.sh
@@ -10,7 +10,7 @@
 
 ## option 1, download model automatically
 model_name_or_model_dir="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="master"
+
 
 ## option 2, download model by git
 #local_path_root=${workspace}/modelscope_models
@@ -50,7 +50,6 @@
 --nproc_per_node ${gpu_num} \
 ../../../funasr/bin/train.py \
 ++model="${model_name_or_model_dir}" \
-++model_revision="${model_revision}" \
 ++train_data_set_list="${train_data}" \
 ++valid_data_set_list="${val_data}" \
 ++dataset_conf.batch_size=20000 \
diff --git a/examples/industrial_data_pretraining/paraformer/infer.sh b/examples/industrial_data_pretraining/paraformer/infer.sh
index 0b0f931..c389163 100644
--- a/examples/industrial_data_pretraining/paraformer/infer.sh
+++ b/examples/industrial_data_pretraining/paraformer/infer.sh
@@ -9,13 +9,12 @@
 output_dir="./outputs/debug"
 
 model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="master"
+
 
 device="cuda:0" # "cuda:0" for gpu0, "cuda:1" for gpu1, "cpu"
 
 python -m funasr.bin.inference \
 ++model=${model} \
-++model_revision=${model_revision} \
 ++input="${input}" \
 ++output_dir="${output_dir}" \
 ++device="${device}" \
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/README_zh.md b/examples/industrial_data_pretraining/paraformer_streaming/README_zh.md
index 8ddb202..24a20fb 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/README_zh.md
+++ b/examples/industrial_data_pretraining/paraformer_streaming/README_zh.md
@@ -1,31 +1,54 @@
 (绠�浣撲腑鏂噟[English](./README.md))
 
-# 璇煶璇嗗埆
+FunASR寮�婧愪簡澶ч噺鍦ㄥ伐涓氭暟鎹笂棰勮缁冩ā鍨嬶紝鎮ㄥ彲浠ュ湪 [妯″瀷璁稿彲鍗忚](https://github.com/alibaba-damo-academy/FunASR/blob/main/MODEL_LICENSE)涓嬭嚜鐢变娇鐢ㄣ�佸鍒躲�佷慨鏀瑰拰鍒嗕韩FunASR妯″瀷锛屼笅闈㈠垪涓句唬琛ㄦ�х殑妯″瀷锛屾洿澶氭ā鍨嬭鍙傝�� [妯″瀷浠撳簱](https://github.com/alibaba-damo-academy/FunASR/tree/main/model_zoo)銆�
 
-> **娉ㄦ剰**:
-> pipeline 鏀寔 [modelscope妯″瀷浠撳簱](https://alibaba-damo-academy.github.io/FunASR/en/model_zoo/modelscope_models.html#pretrained-models-on-modelscope) 涓殑鎵�鏈夋ā鍨嬭繘琛屾帹鐞嗗拰寰皟銆傝繖閲屾垜浠互鍏稿瀷妯″瀷浣滀负绀轰緥鏉ユ紨绀轰娇鐢ㄦ柟娉曘��
+<div align="center">  
+<h4>
+ <a href="#妯″瀷鎺ㄧ悊"> 妯″瀷鎺ㄧ悊 </a>   
+锝�<a href="#妯″瀷璁粌涓庢祴璇�"> 妯″瀷璁粌涓庢祴璇� </a>
+锝�<a href="#妯″瀷瀵煎嚭涓庢祴璇�"> 妯″瀷瀵煎嚭涓庢祴璇� </a>
+</h4>
+</div>
 
-## 鎺ㄧ悊
+<a name="妯″瀷鎺ㄧ悊"></a>
+## 妯″瀷鎺ㄧ悊
 
 ### 蹇�熶娇鐢�
-#### [Paraformer 妯″瀷](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)
+
+鍛戒护琛屾柟寮忚皟鐢細
+```shell
+funasr ++model=paraformer-zh ++vad_model="fsmn-vad" ++punc_model="ct-punc" ++input=asr_example_zh.wav
+```
+
+python浠ｇ爜璋冪敤锛堟帹鑽愶級
+
 ```python
 from funasr import AutoModel
 
-model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
+model = AutoModel(model="paraformer-zh")
 
-res = model(input="/Users/zhifu/Downloads/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav")
+res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav")
 print(res)
 ```
 
-### API鎺ュ彛璇存槑
+### 鎺ュ彛璇存槑
+
 #### AutoModel 瀹氫箟
-- `model`: [妯″瀷浠撳簱](https://alibaba-damo-academy.github.io/FunASR/en/model_zoo/modelscope_models.html#pretrained-models-on-modelscope) 涓殑妯″瀷鍚嶇О锛屾垨鏈湴纾佺洏涓殑妯″瀷璺緞
-- `device`: `cuda`锛堥粯璁わ級锛屼娇鐢� GPU 杩涜鎺ㄧ悊銆傚鏋滀负`cpu`锛屽垯浣跨敤 CPU 杩涜鎺ㄧ悊
-- `ncpu`: `None` 锛堥粯璁わ級锛岃缃敤浜� CPU 鍐呴儴鎿嶄綔骞惰鎬х殑绾跨▼鏁�
-- `output_dir`: `None` 锛堥粯璁わ級锛屽鏋滆缃紝杈撳嚭缁撴灉鐨勮緭鍑鸿矾寰�
-- `batch_size`: `1` 锛堥粯璁わ級锛岃В鐮佹椂鐨勬壒澶勭悊澶у皬
+```python
+model = AutoModel(model=[str], device=[str], ncpu=[int], output_dir=[str], batch_size=[int], hub=[str], **kwargs)
+```
+- `model`(str): [妯″瀷浠撳簱](https://github.com/alibaba-damo-academy/FunASR/tree/main/model_zoo) 涓殑妯″瀷鍚嶇О锛屾垨鏈湴纾佺洏涓殑妯″瀷璺緞
+- `device`(str): `cuda:0`锛堥粯璁pu0锛夛紝浣跨敤 GPU 杩涜鎺ㄧ悊锛屾寚瀹氥�傚鏋滀负`cpu`锛屽垯浣跨敤 CPU 杩涜鎺ㄧ悊
+- `ncpu`(int): `4` 锛堥粯璁わ級锛岃缃敤浜� CPU 鍐呴儴鎿嶄綔骞惰鎬х殑绾跨▼鏁�
+- `output_dir`(str): `None` 锛堥粯璁わ級锛屽鏋滆缃紝杈撳嚭缁撴灉鐨勮緭鍑鸿矾寰�
+- `batch_size`(int): `1` 锛堥粯璁わ級锛岃В鐮佹椂鐨勬壒澶勭悊锛屾牱鏈釜鏁�
+- `hub`(str)锛歚ms`锛堥粯璁わ級锛屼粠modelscope涓嬭浇妯″瀷銆傚鏋滀负`hf`锛屼粠huggingface涓嬭浇妯″瀷銆�
+- `**kwargs`(dict): 鎵�鏈夊湪`config.yaml`涓弬鏁帮紝鍧囧彲浠ョ洿鎺ュ湪姝ゅ鎸囧畾锛屼緥濡傦紝vad妯″瀷涓渶澶у垏鍓查暱搴� `max_single_segment_time=6000` 锛堟绉掞級銆�
+
 #### AutoModel 鎺ㄧ悊
+```python
+res = model.generate(input=[str], output_dir=[str])
+```
 - `input`: 瑕佽В鐮佺殑杈撳叆锛屽彲浠ユ槸锛�
   - wav鏂囦欢璺緞, 渚嬪: asr_example.wav
   - pcm鏂囦欢璺緞, 渚嬪: asr_example.pcm锛屾鏃堕渶瑕佹寚瀹氶煶棰戦噰鏍风巼fs锛堥粯璁や负16000锛�
@@ -40,3 +63,370 @@
   ```[audio_sample1, audio_sample2, ..., audio_sampleN]```
   - fbank杈撳叆锛屾敮鎸佺粍batch銆俿hape涓篬batch, frames, dim]锛岀被鍨嬩负torch.Tensor锛屼緥濡�
 - `output_dir`: None 锛堥粯璁わ級锛屽鏋滆缃紝杈撳嚭缁撴灉鐨勮緭鍑鸿矾寰�
+- `**kwargs`(dict): 涓庢ā鍨嬬浉鍏崇殑鎺ㄧ悊鍙傛暟锛屼緥濡傦紝`beam_size=10`锛宍decoding_ctc_weight=0.1`銆�
+
+
+### 鏇村鐢ㄦ硶浠嬬粛
+
+
+#### 闈炲疄鏃惰闊宠瘑鍒�
+```python
+from funasr import AutoModel
+# paraformer-zh is a multi-functional asr model
+# use vad, punc, spk or not as you need
+model = AutoModel(model="paraformer-zh",  
+                  vad_model="fsmn-vad", 
+                  vad_kwargs={"max_single_segment_time": 60000},
+                  punc_model="ct-punc", 
+                  # spk_model="cam++"
+                  )
+wav_file = f"{model.model_path}/example/asr_example.wav"
+res = model.generate(input=wav_file, batch_size_s=300, batch_size_threshold_s=60, hotword='榄旀惌')
+print(res)
+```
+娉ㄦ剰锛�
+- 閫氬父妯″瀷杈撳叆闄愬埗鏃堕暱30s浠ヤ笅锛岀粍鍚坄vad_model`鍚庯紝鏀寔浠绘剰鏃堕暱闊抽杈撳叆锛屼笉灞�闄愪簬paraformer妯″瀷锛屾墍鏈夐煶棰戣緭鍏ユā鍨嬪潎鍙互銆�
+- `model`鐩稿叧鐨勫弬鏁板彲浠ョ洿鎺ュ湪`AutoModel`瀹氫箟涓洿鎺ユ寚瀹氾紱涓巂vad_model`鐩稿叧鍙傛暟鍙互閫氳繃`vad_kwargs`鏉ユ寚瀹氾紝绫诲瀷涓篸ict锛涚被浼肩殑鏈塦punc_kwargs`锛宍spk_kwargs`锛�
+- `max_single_segment_time`: 琛ㄧず`vad_model`鏈�澶у垏鍓查煶棰戞椂闀�, 鍗曚綅鏄绉抦s.
+- `batch_size_s` 琛ㄧず閲囩敤鍔ㄦ�乥atch锛宐atch涓�婚煶棰戞椂闀匡紝鍗曚綅涓虹s銆�
+- `batch_size_threshold_s`: 琛ㄧず`vad_model`鍒囧壊鍚庨煶棰戠墖娈垫椂闀胯秴杩� `batch_size_threshold_s`闃堝�兼椂锛屽皢batch_size鏁拌缃负1, 鍗曚綅涓虹s.
+
+寤鸿锛氬綋鎮ㄨ緭鍏ヤ负闀块煶棰戯紝閬囧埌OOM闂鏃讹紝鍥犱负鏄惧瓨鍗犵敤涓庨煶棰戞椂闀垮憟骞虫柟鍏崇郴澧炲姞锛屽垎涓�3绉嶆儏鍐碉細
+- a)鎺ㄧ悊璧峰闃舵锛屾樉瀛樹富瑕佸彇鍐充簬`batch_size_s`锛岄�傚綋鍑忓皬璇ュ�硷紝鍙互鍑忓皯鏄惧瓨鍗犵敤锛�
+- b)鎺ㄧ悊涓棿闃舵锛岄亣鍒癡AD鍒囧壊鐨勯暱闊抽鐗囨锛屾�籺oken鏁板皬浜巂batch_size_s`锛屼粛鐒跺嚭鐜癘OM锛屽彲浠ラ�傚綋鍑忓皬`batch_size_threshold_s`锛岃秴杩囬槇鍊硷紝寮哄埗batch涓�1; 
+- c)鎺ㄧ悊蹇粨鏉熼樁娈碉紝閬囧埌VAD鍒囧壊鐨勯暱闊抽鐗囨锛屾�籺oken鏁板皬浜巂batch_size_s`锛屼笖瓒呰繃闃堝�糮batch_size_threshold_s`锛屽己鍒禸atch涓�1锛屼粛鐒跺嚭鐜癘OM锛屽彲浠ラ�傚綋鍑忓皬`max_single_segment_time`锛屼娇寰梀AD鍒囧壊闊抽鏃堕暱鍙樼煭銆�
+
+#### 瀹炴椂璇煶璇嗗埆
+
+```python
+from funasr import AutoModel
+
+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
+
+model = AutoModel(model="paraformer-zh-streaming")
+
+import soundfile
+import os
+
+wav_file = os.path.join(model.model_path, "example/asr_example.wav")
+speech, sample_rate = soundfile.read(wav_file)
+chunk_stride = chunk_size[1] * 960 # 600ms
+
+cache = {}
+total_chunk_num = int(len((speech)-1)/chunk_stride+1)
+for i in range(total_chunk_num):
+    speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
+    is_final = i == total_chunk_num - 1
+    res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
+    print(res)
+```
+
+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�
+
+#### 璇煶绔偣妫�娴嬶紙闈炲疄鏃讹級
+```python
+from funasr import AutoModel
+
+model = AutoModel(model="fsmn-vad")
+
+wav_file = f"{model.model_path}/example/asr_example.wav"
+res = model.generate(input=wav_file)
+print(res)
+```
+娉細VAD妯″瀷杈撳嚭鏍煎紡涓猴細`[[beg1, end1], [beg2, end2], .., [begN, endN]]`锛屽叾涓璥begN/endN`琛ㄧず绗琡N`涓湁鏁堥煶棰戠墖娈电殑璧峰鐐�/缁撴潫鐐癸紝
+鍗曚綅涓烘绉掋��
+
+#### 璇煶绔偣妫�娴嬶紙瀹炴椂锛�
+```python
+from funasr import AutoModel
+
+chunk_size = 200 # ms
+model = AutoModel(model="fsmn-vad")
+
+import soundfile
+
+wav_file = f"{model.model_path}/example/vad_example.wav"
+speech, sample_rate = soundfile.read(wav_file)
+chunk_stride = int(chunk_size * sample_rate / 1000)
+
+cache = {}
+total_chunk_num = int(len((speech)-1)/chunk_stride+1)
+for i in range(total_chunk_num):
+    speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
+    is_final = i == total_chunk_num - 1
+    res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
+    if len(res[0]["value"]):
+        print(res)
+```
+娉細娴佸紡VAD妯″瀷杈撳嚭鏍煎紡涓�4绉嶆儏鍐碉細
+- `[[beg1, end1], [beg2, end2], .., [begN, endN]]`锛氬悓涓婄绾縑AD杈撳嚭缁撴灉銆�
+- `[[beg, -1]]`锛氳〃绀哄彧妫�娴嬪埌璧峰鐐广��
+- `[[-1, end]]`锛氳〃绀哄彧妫�娴嬪埌缁撴潫鐐广��
+- `[]`锛氳〃绀烘棦娌℃湁妫�娴嬪埌璧峰鐐癸紝涔熸病鏈夋娴嬪埌缁撴潫鐐�
+杈撳嚭缁撴灉鍗曚綅涓烘绉掞紝浠庤捣濮嬬偣寮�濮嬬殑缁濆鏃堕棿銆�
+
+#### 鏍囩偣鎭㈠
+```python
+from funasr import AutoModel
+
+model = AutoModel(model="ct-punc")
+
+res = model.generate(input="閭ｄ粖澶╃殑浼氬氨鍒拌繖閲屽惂 happy new year 鏄庡勾瑙�")
+print(res)
+```
+
+#### 鏃堕棿鎴抽娴�
+```python
+from funasr import AutoModel
+
+model = AutoModel(model="fa-zh")
+
+wav_file = f"{model.model_path}/example/asr_example.wav"
+text_file = f"{model.model_path}/example/text.txt"
+res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
+print(res)
+```
+鏇村锛圼绀轰緥](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining)锛�
+
+<a name="鏍稿績鍔熻兘"></a>
+## 妯″瀷璁粌涓庢祴璇�
+
+### 蹇�熷紑濮�
+
+鍛戒护琛屾墽琛岋紙鐢ㄤ簬蹇�熸祴璇曪紝涓嶆帹鑽愶級锛�
+```shell
+funasr-train ++model=paraformer-zh ++train_data_set_list=data/list/train.jsonl ++valid_data_set_list=data/list/val.jsonl ++output_dir="./outputs" &> log.txt &
+```
+
+python浠ｇ爜鎵ц锛堝彲浠ュ鏈哄鍗★紝鎺ㄨ崘锛�
+
+```shell
+cd examples/industrial_data_pretraining/paraformer
+bash finetune.sh
+# "log_file: ./outputs/log.txt"
+```
+璇︾粏瀹屾暣鐨勮剼鏈弬鑰� [finetune.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/examples/industrial_data_pretraining/paraformer/finetune.sh)
+
+### 璇︾粏鍙傛暟浠嬬粛
+
+```shell
+funasr/bin/train.py \
+++model="${model_name_or_model_dir}" \
+++train_data_set_list="${train_data}" \
+++valid_data_set_list="${val_data}" \
+++dataset_conf.batch_size=20000 \
+++dataset_conf.batch_type="token" \
+++dataset_conf.num_workers=4 \
+++train_conf.max_epoch=50 \
+++train_conf.log_interval=1 \
+++train_conf.resume=false \
+++train_conf.validate_interval=2000 \
+++train_conf.save_checkpoint_interval=2000 \
+++train_conf.keep_nbest_models=20 \
+++train_conf.avg_nbest_model=5 \
+++optim_conf.lr=0.0002 \
+++output_dir="${output_dir}" &> ${log_file}
+```
+
+- `model`锛坰tr锛夛細妯″瀷鍚嶅瓧锛堟ā鍨嬩粨搴撲腑鐨処D锛夛紝姝ゆ椂鑴氭湰浼氳嚜鍔ㄤ笅杞芥ā鍨嬪埌鏈锛涙垨鑰呮湰鍦板凡缁忎笅杞藉ソ鐨勬ā鍨嬭矾寰勩��
+- `train_data_set_list`锛坰tr锛夛細璁粌鏁版嵁璺緞锛岄粯璁や负jsonl鏍煎紡锛屽叿浣撳弬鑰冿紙[渚嬪瓙](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)锛夈��
+- `valid_data_set_list`锛坰tr锛夛細楠岃瘉鏁版嵁璺緞锛岄粯璁や负jsonl鏍煎紡锛屽叿浣撳弬鑰冿紙[渚嬪瓙](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)锛夈��
+- `dataset_conf.batch_type`锛坰tr锛夛細`example`锛堥粯璁わ級锛宐atch鐨勭被鍨嬨�俙example`琛ㄧず鎸夌収鍥哄畾鏁扮洰batch_size涓牱鏈粍batch锛沗length` or `token` 琛ㄧず鍔ㄦ�佺粍batch锛宐atch鎬婚暱搴︽垨鑰卼oken鏁颁负batch_size銆�
+- `dataset_conf.batch_size`锛坕nt锛夛細涓� `batch_type` 鎼厤浣跨敤锛屽綋 `batch_type=example` 鏃讹紝琛ㄧず鏍锋湰涓暟锛涘綋 `batch_type=length` 鏃讹紝琛ㄧず鏍锋湰涓暱搴︼紝鍗曚綅涓篺bank甯ф暟锛�1甯�10ms锛夋垨鑰呮枃瀛梩oken涓暟銆�
+- `train_conf.max_epoch`锛坕nt锛夛細璁粌鎬籩poch鏁般��
+- `train_conf.log_interval`锛坕nt锛夛細鎵撳嵃鏃ュ織闂撮殧step鏁般��
+- `train_conf.resume`锛坕nt锛夛細鏄惁寮�鍚柇鐐归噸璁��
+- `train_conf.validate_interval`锛坕nt锛夛細璁粌涓仛楠岃瘉娴嬭瘯鐨勯棿闅攕tep鏁般��
+- `train_conf.save_checkpoint_interval`锛坕nt锛夛細璁粌涓ā鍨嬩繚瀛橀棿闅攕tep鏁般��
+- `train_conf.keep_nbest_models`锛坕nt锛夛細淇濈暀鏈�澶у灏戜釜妯″瀷鍙傛暟锛屾寜鐓ч獙璇侀泦acc鎺掑簭锛屼粠楂樺埌搴曚繚鐣欍��
+- `train_conf.avg_nbest_model`锛坕nt锛夛細瀵筧cc鏈�楂樼殑n涓ā鍨嬪彇骞冲潎銆�
+- `optim_conf.lr`锛坒loat锛夛細瀛︿範鐜囥��
+- `output_dir`锛坰tr锛夛細妯″瀷淇濆瓨璺緞銆�
+- `**kwargs`(dict): 鎵�鏈夊湪`config.yaml`涓弬鏁帮紝鍧囧彲浠ョ洿鎺ュ湪姝ゅ鎸囧畾锛屼緥濡傦紝杩囨护20s浠ヤ笂闀块煶棰戯細`dataset_conf.max_token_length=2000`锛屽崟浣嶄负闊抽fbank甯ф暟锛�1甯�10ms锛夋垨鑰呮枃瀛梩oken涓暟銆�
+
+#### 澶歡pu璁粌
+##### 鍗曟満澶歡pu璁粌
+```shell
+export CUDA_VISIBLE_DEVICES="0,1"
+gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+
+torchrun --nnodes 1 --nproc_per_node ${gpu_num} \
+../../../funasr/bin/train.py ${train_args}
+```
+--nnodes 琛ㄧず鍙備笌鐨勮妭鐐规�绘暟锛�--nproc_per_node 琛ㄧず姣忎釜鑺傜偣涓婅繍琛岀殑杩涚▼鏁�
+
+##### 澶氭満澶歡pu璁粌
+
+鍦ㄤ富鑺傜偣涓婏紝鍋囪IP涓�192.168.1.1锛岀鍙ｄ负12345锛屼娇鐢ㄧ殑鏄�2涓狦PU锛屽垯杩愯濡備笅鍛戒护锛�
+```shell
+export CUDA_VISIBLE_DEVICES="0,1"
+gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+
+torchrun --nnodes 2 --nproc_per_node ${gpu_num} --master_addr=192.168.1.1 --master_port=12345 \
+../../../funasr/bin/train.py ${train_args}
+```
+鍦ㄤ粠鑺傜偣涓婏紙鍋囪IP涓�192.168.1.2锛夛紝浣犻渶瑕佺‘淇滿ASTER_ADDR鍜孧ASTER_PORT鐜鍙橀噺涓庝富鑺傜偣璁剧疆鐨勪竴鑷达紝骞惰繍琛屽悓鏍风殑鍛戒护锛�
+```shell
+export CUDA_VISIBLE_DEVICES="0,1"
+gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+
+torchrun --nnodes 2 --nproc_per_node ${gpu_num} --master_addr=192.168.1.1 --master_port=12345 \
+../../../funasr/bin/train.py ${train_args}
+```
+
+--nnodes 琛ㄧず鍙備笌鐨勮妭鐐规�绘暟锛�--nproc_per_node 琛ㄧず姣忎釜鑺傜偣涓婅繍琛岀殑杩涚▼鏁�
+
+#### 鍑嗗鏁版嵁
+
+`jsonl`鏍煎紡鍙互鍙傝�冿紙[渚嬪瓙](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)锛夈��
+鍙互鐢ㄦ寚浠� `scp2jsonl` 浠巜av.scp涓巘ext.txt鐢熸垚銆倃av.scp涓巘ext.txt鍑嗗杩囩▼濡備笅锛�
+
+`train_text.txt`
+
+宸﹁竟涓烘暟鎹敮涓�ID锛岄渶涓巂train_wav.scp`涓殑`ID`涓�涓�瀵瑰簲
+鍙宠竟涓洪煶棰戞枃浠舵爣娉ㄦ枃鏈紝鏍煎紡濡備笅锛�
+
+```bash
+ID0012W0013 褰撳鎴烽闄╂壙鍙楄兘鍔涜瘎浼颁緷鎹彂鐢熷彉鍖栨椂
+ID0012W0014 鎵�鏈夊彧瑕佸鐞� data 涓嶇浣犳槸鍋� machine learning 鍋� deep learning
+ID0012W0015 he tried to think how it could be
+```
+
+
+`train_wav.scp`
+
+宸﹁竟涓烘暟鎹敮涓�ID锛岄渶涓巂train_text.txt`涓殑`ID`涓�涓�瀵瑰簲
+鍙宠竟涓洪煶棰戞枃浠剁殑璺緞锛屾牸寮忓涓�
+
+```bash
+BAC009S0764W0121 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/BAC009S0764W0121.wav
+BAC009S0916W0489 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/BAC009S0916W0489.wav
+ID0012W0015 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cn_en.wav
+```
+
+`鐢熸垚鎸囦护`
+
+```shell
+# generate train.jsonl and val.jsonl from wav.scp and text.txt
+scp2jsonl \
+++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
+++data_type_list='["source", "target"]' \
+++jsonl_file_out="../../../data/list/train.jsonl"
+```
+
+锛堝彲閫夛紝闈炲繀闇�锛夊鏋滈渶瑕佷粠jsonl瑙ｆ瀽鎴恮av.scp涓巘ext.txt锛屽彲浠ヤ娇鐢ㄦ寚浠わ細
+
+```shell
+# generate wav.scp and text.txt from train.jsonl and val.jsonl
+jsonl2scp \
+++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
+++data_type_list='["source", "target"]' \
+++jsonl_file_in="../../../data/list/train.jsonl"
+```
+
+#### 鏌ョ湅璁粌鏃ュ織
+
+##### 鏌ョ湅瀹為獙log
+```shell
+tail log.txt
+[2024-03-21 15:55:52,137][root][INFO] - train, rank: 3, epoch: 0/50, step: 6990/1, total step: 6990, (loss_avg_rank: 0.327), (loss_avg_epoch: 0.409), (ppl_avg_epoch: 1.506), (acc_avg_epoch: 0.795), (lr: 1.165e-04), [('loss_att', 0.259), ('acc', 0.825), ('loss_pre', 0.04), ('loss', 0.299), ('batch_size', 40)], {'data_load': '0.000', 'forward_time': '0.315', 'backward_time': '0.555', 'optim_time': '0.076', 'total_time': '0.947'}, GPU, memory: usage: 3.830 GB, peak: 18.357 GB, cache: 20.910 GB, cache_peak: 20.910 GB
+[2024-03-21 15:55:52,139][root][INFO] - train, rank: 1, epoch: 0/50, step: 6990/1, total step: 6990, (loss_avg_rank: 0.334), (loss_avg_epoch: 0.409), (ppl_avg_epoch: 1.506), (acc_avg_epoch: 0.795), (lr: 1.165e-04), [('loss_att', 0.285), ('acc', 0.823), ('loss_pre', 0.046), ('loss', 0.331), ('batch_size', 36)], {'data_load': '0.000', 'forward_time': '0.334', 'backward_time': '0.536', 'optim_time': '0.077', 'total_time': '0.948'}, GPU, memory: usage: 3.943 GB, peak: 18.291 GB, cache: 19.619 GB, cache_peak: 19.619 GB
+```
+鎸囨爣瑙ｉ噴锛�
+- `rank`锛氳〃绀篻pu id銆�
+- `epoch`,`step`,`total step`锛氳〃绀哄綋鍓峞poch锛宻tep锛屾�籹tep銆�
+- `loss_avg_rank`锛氳〃绀哄綋鍓峴tep锛屾墍鏈塯pu骞冲潎loss銆�
+- `loss/ppl/acc_avg_epoch`锛氳〃绀哄綋鍓峞poch鍛ㄦ湡锛屾埅姝㈠綋鍓峴tep鏁版椂锛屾�诲钩鍧噇oss/ppl/acc銆俥poch缁撴潫鏃剁殑鏈�鍚庝竴涓猻tep琛ㄧずepoch鎬诲钩鍧噇oss/ppl/acc锛屾帹鑽愪娇鐢╝cc鎸囨爣銆�
+- `lr`锛氬綋鍓峴tep鐨勫涔犵巼銆�
+- `[('loss_att', 0.259), ('acc', 0.825), ('loss_pre', 0.04), ('loss', 0.299), ('batch_size', 40)]`锛氳〃绀哄綋鍓峠pu id鐨勫叿浣撴暟鎹��
+- `total_time`锛氳〃绀哄崟涓猻tep鎬昏�楁椂銆�
+- `GPU, memory`锛氬垎鍒〃绀猴紝妯″瀷浣跨敤/宄板�兼樉瀛橈紝妯″瀷+缂撳瓨浣跨敤/宄板�兼樉瀛樸��
+
+##### tensorboard鍙鍖�
+```bash
+tensorboard --logdir /xxxx/FunASR/examples/industrial_data_pretraining/paraformer/outputs/log/tensorboard
+```
+娴忚鍣ㄤ腑鎵撳紑锛歨ttp://localhost:6006/
+
+### 璁粌鍚庢ā鍨嬫祴璇�
+
+
+#### 鏈塩onfiguration.json
+
+鍋囧畾锛岃缁冩ā鍨嬭矾寰勪负锛�./model_dir锛屽鏋滄敼鐩綍涓嬫湁鐢熸垚configuration.json锛屽彧闇�瑕佸皢 [涓婅堪妯″瀷鎺ㄧ悊鏂规硶](https://github.com/alibaba-damo-academy/FunASR/blob/main/examples/README_zh.md#%E6%A8%A1%E5%9E%8B%E6%8E%A8%E7%90%86) 涓ā鍨嬪悕瀛椾慨鏀逛负妯″瀷璺緞鍗冲彲
+
+渚嬪锛�
+
+浠巗hell鎺ㄧ悊
+```shell
+python -m funasr.bin.inference ++model="./model_dir" ++input=="${input}" ++output_dir="${output_dir}"
+```
+浠巔ython鎺ㄧ悊
+
+```python
+from funasr import AutoModel
+
+model = AutoModel(model="./model_dir")
+
+res = model.generate(input=wav_file)
+print(res)
+```
+
+#### 鏃燾onfiguration.json鏃�
+
+濡傛灉妯″瀷璺緞涓棤configuration.json鏃讹紝闇�瑕佹墜鍔ㄦ寚瀹氬叿浣撻厤缃枃浠惰矾寰勪笌妯″瀷璺緞
+
+```shell
+python -m funasr.bin.inference \
+--config-path "${local_path}" \
+--config-name "${config}" \
+++init_param="${init_param}" \
+++tokenizer_conf.token_list="${tokens}" \
+++frontend_conf.cmvn_file="${cmvn_file}" \
+++input="${input}" \
+++output_dir="${output_dir}" \
+++device="${device}"
+```
+
+鍙傛暟浠嬬粛
+- `config-path`锛氫负瀹為獙涓繚瀛樼殑 `config.yaml`锛屽彲浠ヤ粠瀹為獙杈撳嚭鐩綍涓煡鎵俱��
+- `config-name`锛氶厤缃枃浠跺悕锛屼竴鑸负 `config.yaml`锛屾敮鎸亂aml鏍煎紡涓巎son鏍煎紡锛屼緥濡� `config.json`
+- `init_param`锛氶渶瑕佹祴璇曠殑妯″瀷鍙傛暟锛屼竴鑸负`model.pt`锛屽彲浠ヨ嚜宸遍�夋嫨鍏蜂綋鐨勬ā鍨嬫枃浠�
+- `tokenizer_conf.token_list`锛氳瘝琛ㄦ枃浠惰矾寰勶紝涓�鑸湪 `config.yaml` 鏈夋寚瀹氾紝鏃犻渶鍐嶆墜鍔ㄦ寚瀹氾紝褰� `config.yaml` 涓矾寰勪笉姝ｇ‘鏃讹紝闇�瑕佸湪姝ゅ鎵嬪姩鎸囧畾銆�
+- `frontend_conf.cmvn_file`锛歸av鎻愬彇fbank涓敤鍒扮殑cmvn鏂囦欢锛屼竴鑸湪 `config.yaml` 鏈夋寚瀹氾紝鏃犻渶鍐嶆墜鍔ㄦ寚瀹氾紝褰� `config.yaml` 涓矾寰勪笉姝ｇ‘鏃讹紝闇�瑕佸湪姝ゅ鎵嬪姩鎸囧畾銆�
+
+鍏朵粬鍙傛暟鍚屼笂锛屽畬鏁� [绀轰緥](https://github.com/alibaba-damo-academy/FunASR/blob/main/examples/industrial_data_pretraining/paraformer/infer_from_local.sh)
+
+
+<a name="妯″瀷瀵煎嚭涓庢祴璇�"></a>
+## 妯″瀷瀵煎嚭涓庢祴璇�
+### 浠庡懡浠よ瀵煎嚭
+```shell
+funasr-export ++model=paraformer ++quantize=false
+```
+
+### 浠嶱ython瀵煎嚭
+```python
+from funasr import AutoModel
+
+model = AutoModel(model="paraformer")
+
+res = model.export(quantize=False)
+```
+
+### 娴嬭瘯ONNX
+```python
+# pip3 install -U funasr-onnx
+from funasr_onnx import Paraformer
+model_dir = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+model = Paraformer(model_dir, batch_size=1, quantize=True)
+
+wav_path = ['~/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav']
+
+result = model(wav_path)
+print(result)
+```
+
+鏇村渚嬪瓙璇峰弬鑰� [鏍蜂緥](runtime/python/onnxruntime)
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/demo.py b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
index 94e5200..57356b8 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/demo.py
+++ b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
@@ -10,7 +10,7 @@
 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
-model = AutoModel(model="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online", model_revision="master")
+model = AutoModel(model="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online")
 
 wav_file = os.path.join(model.model_path, "example/asr_example.wav")
 res = model.generate(input=wav_file,
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/demo.sh b/examples/industrial_data_pretraining/paraformer_streaming/demo.sh
index a316aaf..a025345 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/demo.sh
+++ b/examples/industrial_data_pretraining/paraformer_streaming/demo.sh
@@ -1,10 +1,9 @@
 
 model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online"
-model_revision="master"
+
 
 python funasr/bin/inference.py \
 +model=${model} \
-+model_revision=${model_revision} \
 +input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav" \
 +output_dir="./outputs/debug" \
 +device="cpu" \
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/export.py b/examples/industrial_data_pretraining/paraformer_streaming/export.py
index 06cec31..95cc56b 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/export.py
+++ b/examples/industrial_data_pretraining/paraformer_streaming/export.py
@@ -9,8 +9,7 @@
 
 from funasr import AutoModel
 
-model = AutoModel(model="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online",
-                  model_revision="master")
+model = AutoModel(model="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online", )
 
 res = model.export(type="onnx", quantize=False)
 print(res)
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/export.sh b/examples/industrial_data_pretraining/paraformer_streaming/export.sh
index 25ac513..cf3e7f4 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/export.sh
+++ b/examples/industrial_data_pretraining/paraformer_streaming/export.sh
@@ -6,12 +6,11 @@
 
 
 model="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online"
-model_revision="master"
+
 
 
 python -m funasr.bin.export \
 ++model=${model} \
-++model_revision=${model_revision} \
 ++type="onnx" \
 ++quantize=false \
 ++device="cpu"
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/finetune.sh b/examples/industrial_data_pretraining/paraformer_streaming/finetune.sh
index 1e4537a..54bc2d1 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/finetune.sh
+++ b/examples/industrial_data_pretraining/paraformer_streaming/finetune.sh
@@ -10,7 +10,7 @@
 
 ## option 1, download model automatically
 model_name_or_model_dir="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online"
-model_revision="master"
+
 
 ## option 2, download model by git
 #local_path_root=${workspace}/modelscope_models
@@ -50,7 +50,6 @@
 --nproc_per_node ${gpu_num} \
 ../../../funasr/bin/train.py \
 ++model="${model_name_or_model_dir}" \
-++model_revision="${model_revision}" \
 ++train_data_set_list="${train_data}" \
 ++valid_data_set_list="${val_data}" \
 ++dataset_conf.batch_size=20000 \
diff --git a/examples/industrial_data_pretraining/scama/demo.py b/examples/industrial_data_pretraining/scama/demo.py
index 075039a..9d458ab 100644
--- a/examples/industrial_data_pretraining/scama/demo.py
+++ b/examples/industrial_data_pretraining/scama/demo.py
@@ -9,7 +9,7 @@
 encoder_chunk_look_back = 0 #number of chunks to lookback for encoder self-attention
 decoder_chunk_look_back = 0 #number of encoder chunks to lookback for decoder cross-attention
 
-model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/speech_SCAMA_asr-zh-cn-16k-common-vocab8358-streaming", model_revision="master")
+model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/speech_SCAMA_asr-zh-cn-16k-common-vocab8358-streaming")
 cache = {}
 res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
             chunk_size=chunk_size,
diff --git a/examples/industrial_data_pretraining/scama/demo.sh b/examples/industrial_data_pretraining/scama/demo.sh
index a316aaf..a025345 100644
--- a/examples/industrial_data_pretraining/scama/demo.sh
+++ b/examples/industrial_data_pretraining/scama/demo.sh
@@ -1,10 +1,9 @@
 
 model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online"
-model_revision="master"
+
 
 python funasr/bin/inference.py \
 +model=${model} \
-+model_revision=${model_revision} \
 +input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav" \
 +output_dir="./outputs/debug" \
 +device="cpu" \
diff --git a/examples/industrial_data_pretraining/seaco_paraformer/demo.py b/examples/industrial_data_pretraining/seaco_paraformer/demo.py
index c12b279..c7f78d3 100644
--- a/examples/industrial_data_pretraining/seaco_paraformer/demo.py
+++ b/examples/industrial_data_pretraining/seaco_paraformer/demo.py
@@ -6,13 +6,9 @@
 from funasr import AutoModel
 
 model = AutoModel(model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
-                  model_revision="master",
                   # vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
-                  # vad_model_revision="master",
                   # punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
-                  # punc_model_revision="master",
                   # spk_model="iic/speech_campplus_sv_zh-cn_16k-common",
-                  # spk_model_revision="v2.0.2",
                   )
 
 
diff --git a/examples/industrial_data_pretraining/seaco_paraformer/demo.sh b/examples/industrial_data_pretraining/seaco_paraformer/demo.sh
index 65847c7..e9efc4b 100644
--- a/examples/industrial_data_pretraining/seaco_paraformer/demo.sh
+++ b/examples/industrial_data_pretraining/seaco_paraformer/demo.sh
@@ -1,6 +1,6 @@
 
 model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="master"
+
 vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch"
 vad_model_revision="master"
 punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
@@ -8,7 +8,6 @@
 
 python funasr/bin/inference.py \
 +model=${model} \
-+model_revision=${model_revision} \
 +vad_model=${vad_model} \
 +vad_model_revision=${vad_model_revision} \
 +punc_model=${punc_model} \
diff --git a/examples/industrial_data_pretraining/seaco_paraformer/finetune.sh b/examples/industrial_data_pretraining/seaco_paraformer/finetune.sh
index 5614f44..8df6061 100644
--- a/examples/industrial_data_pretraining/seaco_paraformer/finetune.sh
+++ b/examples/industrial_data_pretraining/seaco_paraformer/finetune.sh
@@ -10,7 +10,6 @@
 
 ## option 1, download model automatically
 model_name_or_model_dir="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="v2.0.7"
 
 ## option 2, download model by git
 #local_path_root=${workspace}/modelscope_models
@@ -50,7 +49,6 @@
 --nproc_per_node ${gpu_num} \
 ../../../funasr/bin/train.py \
 ++model="${model_name_or_model_dir}" \
-++model_revision="${model_revision}" \
 ++train_data_set_list="${train_data}" \
 ++valid_data_set_list="${val_data}" \
 ++dataset_conf.batch_size=20000 \
diff --git a/examples/industrial_data_pretraining/transducer/demo.py b/examples/industrial_data_pretraining/transducer/demo.py
index ef12aac..5a4aa42 100644
--- a/examples/industrial_data_pretraining/transducer/demo.py
+++ b/examples/industrial_data_pretraining/transducer/demo.py
@@ -7,8 +7,7 @@
 
 # Transducer, BAT and RWKV_BAT models are just same to use, use the correct model_revision
 # https://modelscope.cn/models?name=transducer&page=1&tasks=auto-speech-recognition&type=audio
-model = AutoModel(model="iic/speech_bat_asr-zh-cn-16k-aishell1-vocab4234-pytorch", 
-                  model_revision="v2.0.2",
+model = AutoModel(model="iic/speech_bat_asr-zh-cn-16k-aishell1-vocab4234-pytorch",
                  )
 
 res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
diff --git a/examples/industrial_data_pretraining/uniasr/demo.py b/examples/industrial_data_pretraining/uniasr/demo.py
index 0df06e2..774f42f 100644
--- a/examples/industrial_data_pretraining/uniasr/demo.py
+++ b/examples/industrial_data_pretraining/uniasr/demo.py
@@ -6,7 +6,7 @@
 from funasr import AutoModel
 
 
-model = AutoModel(model="iic/speech_UniASR-large_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline", model_revision="master",)
+model = AutoModel(model="iic/speech_UniASR-large_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline",)
 
 
 res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
@@ -16,7 +16,7 @@
 ''' can not use currently
 from funasr import AutoFrontend
 
-frontend = AutoFrontend(model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revision="master")
+frontend = AutoFrontend(model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
 
 fbanks = frontend(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", batch_size=2)
 
diff --git a/examples/industrial_data_pretraining/uniasr/demo.sh b/examples/industrial_data_pretraining/uniasr/demo.sh
index e38f974..f191ce6 100644
--- a/examples/industrial_data_pretraining/uniasr/demo.sh
+++ b/examples/industrial_data_pretraining/uniasr/demo.sh
@@ -1,10 +1,9 @@
 
 model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="master"
+
 
 python funasr/bin/inference.py \
 +model=${model} \
-+model_revision=${model_revision} \
 +input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav" \
 +output_dir="./outputs/debug" \
 +device="cpu" \
diff --git a/examples/industrial_data_pretraining/whisper/demo.py b/examples/industrial_data_pretraining/whisper/demo.py
index e1e1aad..3d317f8 100644
--- a/examples/industrial_data_pretraining/whisper/demo.py
+++ b/examples/industrial_data_pretraining/whisper/demo.py
@@ -8,7 +8,6 @@
 from funasr import AutoModel
 
 model = AutoModel(model="iic/Whisper-large-v3",
-                  model_revision="v2.0.5",
                   vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
 				  vad_kwargs={"max_single_segment_time": 30000},
                   )
diff --git a/examples/industrial_data_pretraining/whisper/infer.sh b/examples/industrial_data_pretraining/whisper/infer.sh
index 6e8f247..71811e2 100644
--- a/examples/industrial_data_pretraining/whisper/infer.sh
+++ b/examples/industrial_data_pretraining/whisper/infer.sh
@@ -11,13 +11,12 @@
 output_dir="./outputs/debug"
 
 model="iic/speech_whisper-large_asr_multilingual"
-model_revision="master"
+
 
 device="cuda:0" # "cuda:0" for gpu0, "cuda:1" for gpu1, "cpu"
 
 python -m funasr.bin.inference \
 ++model=${model} \
-++model_revision=${model_revision} \
 ++input="${input}" \
 ++output_dir="${output_dir}" \
 ++device="${device}" \

--
Gitblit v1.9.1