BatchalignHK 0.7.22.post31__tar.gz → 0.7.22.post33__tar.gz

{batchalignhk-0.7.22.post31 → batchalignhk-0.7.22.post33}/BatchalignHK.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: BatchalignHK
-Version: 0.7.22.post31
+Version: 0.7.22.post33
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -61,6 +61,15 @@ Requires-Dist: accelerate~=0.27; extra == "train"
 Provides-Extra: docs
 Requires-Dist: mkdocs-material; extra == "docs"
 Requires-Dist: mkdocs-click; extra == "docs"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: summary
 
 # TalkBank | Batchalign2
 

{batchalignhk-0.7.22.post31 → batchalignhk-0.7.22.post33}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: BatchalignHK
-Version: 0.7.22.post31
+Version: 0.7.22.post33
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -61,6 +61,15 @@ Requires-Dist: accelerate~=0.27; extra == "train"
 Provides-Extra: docs
 Requires-Dist: mkdocs-material; extra == "docs"
 Requires-Dist: mkdocs-click; extra == "docs"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: summary
 
 # TalkBank | Batchalign2
 

{batchalignhk-0.7.22.post31 → batchalignhk-0.7.22.post33}/batchalign/document.py

@@ -206,7 +206,7 @@ class Utterance(BaseModel):
     def __len__(self):
         return len(self.content)
 
-    def tostring(self, always_detokenize=False):
+    def tostring(self, always_detokenize=False, merge_abbrev=False):
         if self.text != None and not always_detokenize:
             t = self.text
         else:
@@ -225,10 +225,11 @@ class Utterance(BaseModel):
         t = re.sub(r" +", " ", t.strip()).strip()
         t = t.replace("+ ,", "+,").strip()
 
-        abbrevs =  [" "+" " .join(list(i))+" " for i in abbrev]
-        for i in abbrevs:
-            t = t.replace(i, " "+i.replace(" ", "")+" ")
-            t = t.replace(i.lower(), " "+i.replace(" ", "")+" ")
+        if merge_abbrev:
+            abbrevs =  [" "+" " .join(list(i))+" " for i in abbrev]
+            for i in abbrevs:
+                t = t.replace(i, " "+i.replace(" ", "")+" ")
+                t = t.replace(i.lower(), " "+i.replace(" ", "")+" ")
 
         return t
 

{batchalignhk-0.7.22.post31 → batchalignhk-0.7.22.post33}/batchalign/formats/chat/file.py

@@ -130,7 +130,8 @@ class CHATFile(BaseFormat):
                 main.append(generate_chat_utterance(i,
                                                     special and doc.langs[0] == "eng",
                                                     write_wor=write_wor,
-                                                    merge_letters="yue" in doc.langs))
+                                                    merge_letters="yue" in doc.langs,
+                                                    merge_abbrev="eng" in doc.langs))
         main.append("@End\n")
 
         raw = "\n".join(main)

{batchalignhk-0.7.22.post31 → batchalignhk-0.7.22.post33}/batchalign/formats/chat/generator.py

@@ -12,7 +12,7 @@ import regex as re
 # document[3].text = None
 # document[3].model_dump()
 
-def generate_chat_utterance(utterance: Utterance, special_mor=False, write_wor=True, merge_letters=False):
+def generate_chat_utterance(utterance: Utterance, special_mor=False, write_wor=True, merge_letters=False, merge_abbrev=False):
     """Converts at Utterance to a CHAT string.
 
     Parameters
@@ -28,7 +28,7 @@ def generate_chat_utterance(utterance: Utterance, special_mor=False, write_wor=T
         The generated string.
     """
     
-    main_line = str(utterance)
+    main_line = utterance.tostring(merge_abbrev=merge_abbrev)
     # last minut ecorrections
     # main_line = re.sub(r"<([\w ]+) \[\/", r"<\1> [/", main_line)
     if merge_letters:
@@ -110,7 +110,7 @@ def generate_chat_utterance(utterance: Utterance, special_mor=False, write_wor=T
 
     #### WOR LINE GENERATION ####
     if has_wor and write_wor:
-        result.append("%wor:\t"+" ".join(wor_elems))
+        result.append(("%wor:\t"+" ".join(wor_elems)).replace("-\x15", "- \x15"))
     if has_coref:
         result.append("%coref:\t"+(", ".join(coref_elems)))
     if utterance.translation != None and utterance.translation.strip() not in ["", ".", "!", "?"]:

{batchalignhk-0.7.22.post31 → batchalignhk-0.7.22.post33}/batchalign/pipelines/asr/utils.py

@@ -230,7 +230,7 @@ def process_generation(output, lang="eng", utterance_engine=None):
                 return i
             try:
                 return num2words(i, lang=lang_2)
-            except NotImplementedError:
+            except (NotImplementedError, AttributeError) as _:
                 try:
                     if lang == "zho":
                         return num2chinese(i)

batchalignhk-0.7.22.post33/batchalign/version

@@ -0,0 +1,3 @@
+0.7.22-post.33
+December 27th, 2025
+fix wor lines

batchalignhk-0.7.22.post31/batchalign/version

@@ -1,3 +0,0 @@
-0.7.22-post.31
-November 28rd, 2025
-Tencent Fixes