batchalign 0.7.5a1__tar.gz → 0.7.5a3__tar.gz

{batchalign-0.7.5a1/batchalign.egg-info → batchalign-0.7.5a3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.5a1
+Version: 0.7.5a3
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -85,15 +85,15 @@ The TalkBank Project, of which Batchalign is a part, is supported by NIH grant H
 The following instructions provide a quick start to installing Batchalign. For most users aiming to process CHAT and audio with Batchalign, we recommend more detailed usage instructions: for [usage](https://talkbank.org/info/BA2-usage.pdf) and [human transcript cleanup](https://talkbank.org/info/BA2-cleanup.pdf). The following provides a quick start guide for the program.
 
 ### Get Python
-- We support Python versions 3.9, 3.10, and 3.11.  
-- **We do not support Python 3.12** (no PyTorch support)
+- We support Python versions 3.9, 3.10, 3.11 and 3.12.  
+- First, check to see if you have Python by running `python`. If it reports any of the versions above, skip the following step.
 - To install Python, follow the instructions...
     -  for macOS
         1. Install Brew: [visit this link](https://brew.sh/)
         2. Install Python: execute `brew install python@3.11`
     -  for Windows
         1.  Install Python 3.11: [via this link](https://www.python.org/ftp/python/3.11.7/python-3.11.7-amd64.exe) 
-        2.  If later commands report `pip module not found`, [this page may help](https://stackoverflow.com/a/15626784)
+        2.  If later commands report `pip module not found`, [this page may help](https://github.com/TalkBank/batchalign2/wiki/Troubleshooting-Tips#get-pip-on-windows)
     -  your distribution's instructions for Linux
 
 ### Install and Update the Package
@@ -156,7 +156,7 @@ batchalign morphotag ~/ba_input ~/ba_output
 #### forced alignment
 
 ```
-batchalign align --lang=eng ~/ba_input ~/ba_output
+batchalign align ~/ba_input ~/ba_output
 ```
 
 

{batchalign-0.7.5a1 → batchalign-0.7.5a3}/README.md

@@ -11,15 +11,15 @@ The TalkBank Project, of which Batchalign is a part, is supported by NIH grant H
 The following instructions provide a quick start to installing Batchalign. For most users aiming to process CHAT and audio with Batchalign, we recommend more detailed usage instructions: for [usage](https://talkbank.org/info/BA2-usage.pdf) and [human transcript cleanup](https://talkbank.org/info/BA2-cleanup.pdf). The following provides a quick start guide for the program.
 
 ### Get Python
-- We support Python versions 3.9, 3.10, and 3.11.  
-- **We do not support Python 3.12** (no PyTorch support)
+- We support Python versions 3.9, 3.10, 3.11 and 3.12.  
+- First, check to see if you have Python by running `python`. If it reports any of the versions above, skip the following step.
 - To install Python, follow the instructions...
     -  for macOS
         1. Install Brew: [visit this link](https://brew.sh/)
         2. Install Python: execute `brew install python@3.11`
     -  for Windows
         1.  Install Python 3.11: [via this link](https://www.python.org/ftp/python/3.11.7/python-3.11.7-amd64.exe) 
-        2.  If later commands report `pip module not found`, [this page may help](https://stackoverflow.com/a/15626784)
+        2.  If later commands report `pip module not found`, [this page may help](https://github.com/TalkBank/batchalign2/wiki/Troubleshooting-Tips#get-pip-on-windows)
     -  your distribution's instructions for Linux
 
 ### Install and Update the Package
@@ -82,7 +82,7 @@ batchalign morphotag ~/ba_input ~/ba_output
 #### forced alignment
 
 ```
-batchalign align --lang=eng ~/ba_input ~/ba_output
+batchalign align ~/ba_input ~/ba_output
 ```
 
 

{batchalign-0.7.5a1 → batchalign-0.7.5a3}/batchalign/formats/chat/utils.py

@@ -146,7 +146,7 @@ def annotation_clean(content, special=False):
     cleaned_word = cleaned_word.replace("~","").replace("&~","")
     cleaned_word = cleaned_word.replace(">","").replace("<","")
     cleaned_word = cleaned_word.replace("〕","").replace("//","").replace(";","")
-    cleaned_word = re.sub(r"@.", '', cleaned_word)
+    cleaned_word = re.sub(r"@[^abcefpoqs]", '', cleaned_word)
     cleaned_word = re.sub(r"&.", '', cleaned_word)
 
     return cleaned_word

{batchalign-0.7.5a1 → batchalign-0.7.5a3}/batchalign/pipelines/asr/rev.py

@@ -63,13 +63,16 @@ class RevEngine(BatchalignEngine):
 
         L.info(f"Uploading '{pathlib.Path(f).stem}'...")
         # we will send the file for processing
-        job = client.submit_job_local_file(f,
-                                           metadata=f"batchalign2_{pathlib.Path(f).stem}",
-                                           language=lang,
-                                           # some languages don't have postprocessors, so this option
-                                           # raises an exception
-                                           skip_postprocessing=(True if resolve("utterance", self.__lang_code) and lang in ["en", "fr"] else False),
-                                           speakers_count=self.__num_speakers)
+        if "en" not in lang and "es" not in lang:
+            job = client.submit_job_local_file(f,
+                                               metadata=f"batchalign2_{pathlib.Path(f).stem}",
+                                               language=lang)
+        else:
+            job = client.submit_job_local_file(f,
+                                               metadata=f"batchalign2_{pathlib.Path(f).stem}",
+                                               language=lang,
+                                               skip_postprocessing=(True if resolve("utterance", self.__lang_code) and lang in ["en", "fr"] else False),
+                                               speakers_count=self.__num_speakers)
 
         # we will wait untitl job finishes
         status = client.get_job_details(job.id).status

{batchalign-0.7.5a1 → batchalign-0.7.5a3}/batchalign/pipelines/morphosyntax/ud.py

@@ -212,7 +212,7 @@ def handler__NOUN(word, lang=None):
 def handler__PROPN(word, lang=None):
     # code as noun
     parsed = handler__NOUN(word)
-    return parsed.replace("propn", "noun")
+    return parsed.replace("noun", "propn")
 
 def handler__VERB(word, lang=None):
     # get the features
@@ -635,7 +635,9 @@ def tokenizer_processor(tokenized, lang, sent):
             before,after = conform(i).split("'")
             res.append((f'{before}\'', False))
             res.append((after, False))
-        elif ("en" in lang) and matches_in(i, "'"):
+        elif (("en" in lang) and matches_in(i, "'") and
+              not (len(conform(i).split("'")) > 1 and
+                   conform(i).split("'")[0].strip() == "o")):
             res.append((conform(i), True))
         elif ("nl" in lang) and conform(i).endswith("'s"):
             res.append((conform(i), False))

batchalign-0.7.5a3/batchalign/version

@@ -0,0 +1,3 @@
+0.7.5-alpha.3
+September 3nd, 2024
+fix rev for mandarin

{batchalign-0.7.5a1 → batchalign-0.7.5a3/batchalign.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.5a1
+Version: 0.7.5a3
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -85,15 +85,15 @@ The TalkBank Project, of which Batchalign is a part, is supported by NIH grant H
 The following instructions provide a quick start to installing Batchalign. For most users aiming to process CHAT and audio with Batchalign, we recommend more detailed usage instructions: for [usage](https://talkbank.org/info/BA2-usage.pdf) and [human transcript cleanup](https://talkbank.org/info/BA2-cleanup.pdf). The following provides a quick start guide for the program.
 
 ### Get Python
-- We support Python versions 3.9, 3.10, and 3.11.  
-- **We do not support Python 3.12** (no PyTorch support)
+- We support Python versions 3.9, 3.10, 3.11 and 3.12.  
+- First, check to see if you have Python by running `python`. If it reports any of the versions above, skip the following step.
 - To install Python, follow the instructions...
     -  for macOS
         1. Install Brew: [visit this link](https://brew.sh/)
         2. Install Python: execute `brew install python@3.11`
     -  for Windows
         1.  Install Python 3.11: [via this link](https://www.python.org/ftp/python/3.11.7/python-3.11.7-amd64.exe) 
-        2.  If later commands report `pip module not found`, [this page may help](https://stackoverflow.com/a/15626784)
+        2.  If later commands report `pip module not found`, [this page may help](https://github.com/TalkBank/batchalign2/wiki/Troubleshooting-Tips#get-pip-on-windows)
     -  your distribution's instructions for Linux
 
 ### Install and Update the Package
@@ -156,7 +156,7 @@ batchalign morphotag ~/ba_input ~/ba_output
 #### forced alignment
 
 ```
-batchalign align --lang=eng ~/ba_input ~/ba_output
+batchalign align ~/ba_input ~/ba_output
 ```
 
 

batchalign-0.7.5a1/batchalign/version

@@ -1,3 +0,0 @@
-0.7.5-alpha.1
-September 3nd, 2024
-Removes unneeded options