From eb86f0fe6a7605c1e72fb8307d525ee8b8ebfb1e Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 29 七月 2024 11:34:27 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR merge

---
 funasr/models/llm_asr/model.py                                      |    4 ++--
 examples/industrial_data_pretraining/paraformer/infer_from_local.sh |    2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/examples/industrial_data_pretraining/paraformer/infer_from_local.sh b/examples/industrial_data_pretraining/paraformer/infer_from_local.sh
index 06c9ca6..6c6e849 100644
--- a/examples/industrial_data_pretraining/paraformer/infer_from_local.sh
+++ b/examples/industrial_data_pretraining/paraformer/infer_from_local.sh
@@ -14,7 +14,7 @@
 local_path_root=${workspace}/modelscope_models
 mkdir -p ${local_path_root}
 local_path=${local_path_root}/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
-git clone https://www.modelscope.cn/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git ${local_path}
+git lfs clone https://www.modelscope.cn/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git ${local_path}
 
 device="cuda:0" # "cuda:0" for gpu0, "cuda:1" for gpu1, "cpu"
 
diff --git a/funasr/models/llm_asr/model.py b/funasr/models/llm_asr/model.py
index b4d9e7c..fa1d2c3 100644
--- a/funasr/models/llm_asr/model.py
+++ b/funasr/models/llm_asr/model.py
@@ -812,7 +812,7 @@
             ibest_writer = self.writer[f"{0 + 1}best_recog"]
 
         results = []
-        response_clean = re.sub("[^\w\s\u3000\u4e00-\u9fff]+", "", response)
+        response_clean = re.sub(r"[^\w\s\u3000\u4e00-\u9fff]+", "", response)
         result_i = {"key": key[0], "text": response, "text_tn": response_clean, "label": label}
         if loss is not None:
             result_i["loss"] = loss
@@ -1395,7 +1395,7 @@
             ibest_writer = self.writer[f"{0 + 1}best_recog"]
 
         results = []
-        response_clean = re.sub("[^\w\s\u3000\u4e00-\u9fff]+", "", response)
+        response_clean = re.sub(r"[^\w\s\u3000\u4e00-\u9fff]+", "", response)
         result_i = {"key": key[0], "text": response, "text_tn": response_clean, "label": label}
         if loss is not None:
             result_i["loss"] = loss

--
Gitblit v1.9.1