Merge branch 'main' of github.com:FunAudioLLM/CosyVoice into main

Author: aluminumbox

README.md

@@ -69,8 +69,6 @@
     ``` sh
     conda create -n cosyvoice -y python=3.10
     conda activate cosyvoice
-    # pynini is required by WeTextProcessing, use conda to install it as it can be executed on all platforms.
-    conda install -y -c conda-forge pynini==2.1.5
     pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
 
     # If you encounter sox compatibility issues
@@ -106,7 +104,7 @@ git clone https://www.modelscope.cn/iic/CosyVoice-ttsfrd.git pretrained_models/C
 
 Optionally, you can unzip `ttsfrd` resource and install `ttsfrd` package for better text normalization performance.
 
-Notice that this step is not necessary. If you do not install `ttsfrd` package, we will use WeTextProcessing by default.
+Notice that this step is not necessary. If you do not install `ttsfrd` package, we will use wetext by default.
 
 ``` sh
 cd pretrained_models/CosyVoice-ttsfrd/

cosyvoice/cli/frontend.py

@@ -28,9 +28,9 @@
     import ttsfrd
     use_ttsfrd = True
 except ImportError:
-    print("failed to import ttsfrd, use WeTextProcessing instead")
-    from tn.chinese.normalizer import Normalizer as ZhNormalizer
-    from tn.english.normalizer import Normalizer as EnNormalizer
+    print("failed to import ttsfrd, use wetext instead")
+    from wetext import Normalizer as ZhNormalizer
+    from wetext import Normalizer as EnNormalizer
     use_ttsfrd = False
 from cosyvoice.utils.file_utils import logging
 from cosyvoice.utils.frontend_utils import contains_chinese, replace_blank, replace_corner_mark, remove_bracket, spell_out_number, split_paragraph, is_only_punctuation
@@ -68,7 +68,7 @@ def __init__(self,
                 'failed to initialize ttsfrd resource'
             self.frd.set_lang_type('pinyinvg')
         else:
-            self.zh_tn_model = ZhNormalizer(remove_erhua=False, full_to_half=False, overwrite_cache=True)
+            self.zh_tn_model = ZhNormalizer(remove_erhua=False)
             self.en_tn_model = EnNormalizer()
             self.inflect_parser = inflect.engine()
 

requirements.txt

@@ -36,5 +36,5 @@ torch==2.3.1
 torchaudio==2.3.1
 transformers==4.40.1
 uvicorn==0.30.0
-WeTextProcessing==1.0.3
+wetext==0.0.4
 wget==3.2