batchalign 0.7.3b13__tar.gz → 0.7.3b15__tar.gz

{batchalign-0.7.3b13/batchalign.egg-info → batchalign-0.7.3b15}/PKG-INFO

@@ -1,76 +1,16 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.3b13
+Version: 0.7.3b15
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
 Classifier: Development Status :: 3 - Alpha
 Classifier: Topic :: Utilities
 Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: pydantic>=2.4
-Requires-Dist: nltk>=3.8
-Requires-Dist: praatio<6.1.0,>=6.0.0
-Requires-Dist: torch<2.2.0,>=2.0.1
-Requires-Dist: torchaudio<2.2.0,>=2.1.0
-Requires-Dist: pyAudioAnalysis==0.3.14
-Requires-Dist: hmmlearn==0.3.0
-Requires-Dist: eyed3~=0.9.7
-Requires-Dist: pydub<0.26.0,>=0.25.1
-Requires-Dist: imblearn
-Requires-Dist: plotly>=5.18.0
-Requires-Dist: transformers~=4.37
-Requires-Dist: tokenizers>=0.14.1
-Requires-Dist: pycountry>=22.3
-Requires-Dist: stanza>=1.7
-Requires-Dist: scipy~=1.11
-Requires-Dist: rev_ai>=2.18.0
-Requires-Dist: rich~=13.6
-Requires-Dist: click~=8.1
-Requires-Dist: matplotlib<4.0.0,>=3.8.0
-Requires-Dist: pyfiglet==1.0.2
-Requires-Dist: soundfile~=0.12.0
-Requires-Dist: rich-click>=1.7.0
-Requires-Dist: typing-extensions
 Provides-Extra: dev
-Requires-Dist: pytest; extra == "dev"
 Provides-Extra: train
-Requires-Dist: accelerate~=0.27; extra == "train"
 Provides-Extra: speaker
-Requires-Dist: nemo-toolkit~=1.21.0; extra == "speaker"
-Requires-Dist: omegaconf~=2.3.0; extra == "speaker"
-Requires-Dist: pydub~=0.25.0; extra == "speaker"
-Requires-Dist: braceexpand; extra == "speaker"
-Requires-Dist: editdistance; extra == "speaker"
-Requires-Dist: g2p_en; extra == "speaker"
-Requires-Dist: ipywidgets; extra == "speaker"
-Requires-Dist: jiwer; extra == "speaker"
-Requires-Dist: kaldi-python-io; extra == "speaker"
-Requires-Dist: kaldiio; extra == "speaker"
-Requires-Dist: lhotse>=1.20.0; extra == "speaker"
-Requires-Dist: librosa>=0.10.0; extra == "speaker"
-Requires-Dist: marshmallow; extra == "speaker"
-Requires-Dist: matplotlib; extra == "speaker"
-Requires-Dist: packaging; extra == "speaker"
-Requires-Dist: pyannote.core; extra == "speaker"
-Requires-Dist: pyannote.metrics; extra == "speaker"
-Requires-Dist: pydub; extra == "speaker"
-Requires-Dist: pyloudnorm; extra == "speaker"
-Requires-Dist: resampy; extra == "speaker"
-Requires-Dist: ruamel.yaml; extra == "speaker"
-Requires-Dist: scipy>=0.14; extra == "speaker"
-Requires-Dist: soundfile; extra == "speaker"
-Requires-Dist: sox; extra == "speaker"
-Requires-Dist: texterrors; extra == "speaker"
-Requires-Dist: hydra-core<=1.3.2,>1.3; extra == "speaker"
-Requires-Dist: omegaconf<=2.3; extra == "speaker"
-Requires-Dist: pytorch-lightning>=2.2.1; extra == "speaker"
-Requires-Dist: torchmetrics>=0.11.0; extra == "speaker"
-Requires-Dist: transformers>=4.36.0; extra == "speaker"
-Requires-Dist: wandb; extra == "speaker"
-Requires-Dist: webdataset>=0.2.86; extra == "speaker"
-Requires-Dist: sentencepiece; extra == "speaker"
-Requires-Dist: youtokentome; extra == "speaker"
+License-File: LICENSE
 
 # TalkBank | Batchalign2
 
@@ -102,13 +42,13 @@ You can get Batchalign from PyPi, and you can update the package in the same way
 macOS/Linux:
 
 ```
-pip3 install -U batchalign
+pip install -U batchalign
 ```
 
 Windows:
 
 ```
-py -m pip3 install -U batchalign
+py -m pip install -U batchalign
 ```
 
 ### Rock and Roll

{batchalign-0.7.3b13 → batchalign-0.7.3b15}/README.md

@@ -28,13 +28,13 @@ You can get Batchalign from PyPi, and you can update the package in the same way
 macOS/Linux:
 
 ```
-pip3 install -U batchalign
+pip install -U batchalign
 ```
 
 Windows:
 
 ```
-py -m pip3 install -U batchalign
+py -m pip install -U batchalign
 ```
 
 ### Rock and Roll

{batchalign-0.7.3b13 → batchalign-0.7.3b15}/batchalign/document.py

@@ -208,6 +208,7 @@ class Utterance(BaseModel):
         # t = re.sub(r"^[^\w\d\s<]+", "", t.strip()).strip()
         t = re.sub(r",", " , ", t.strip()).strip()
         t = re.sub(r" +", " ", t.strip()).strip()
+        t = t.replace("+ ,", "+,").strip()
         return t
 
     def __repr__(self):

{batchalign-0.7.3b13 → batchalign-0.7.3b15}/batchalign/formats/chat/file.py

@@ -129,7 +129,13 @@ class CHATFile(BaseFormat):
                                                     write_wor=write_wor))
         main.append("@End\n")
 
-        return "\n".join(main)
+        raw = "\n".join(main)
+
+        # correct for unicode problems
+        corrected = raw
+        corrected = corrected.replace(u"\u202b", u"\u200f")
+
+        return corrected
 
     @property
     def doc(self):

{batchalign-0.7.3b13 → batchalign-0.7.3b15}/batchalign/pipelines/morphosyntax/ud.py

@@ -883,6 +883,7 @@ def morphoanalyze(doc: Document, retokenize:bool, status_hook:callable = None, *
                 retokenized_ut = retokenized_ut.replace(" >", ">")
                 retokenized_ut = retokenized_ut.replace("< ", "<")
                 retokenized_ut = retokenized_ut.replace(" :", ":")
+                retokenized_ut = retokenized_ut.replace("+ ,", "+,")
                 retokenized_ut = retokenized_ut.replace(": <", ": <")
                 retokenized_ut = retokenized_ut.replace(" ↑", "↑")
                 retokenized_ut = re.sub(r"@ ?w ?p", "@wp", retokenized_ut)

batchalign-0.7.3b15/batchalign/version

@@ -0,0 +1,3 @@
+0.7.3-beta.15
+July 29th, 2024
+Correct Unicode Escapes?

{batchalign-0.7.3b13 → batchalign-0.7.3b15/batchalign.egg-info}/PKG-INFO

@@ -1,76 +1,16 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.3b13
+Version: 0.7.3b15
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
 Classifier: Development Status :: 3 - Alpha
 Classifier: Topic :: Utilities
 Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: pydantic>=2.4
-Requires-Dist: nltk>=3.8
-Requires-Dist: praatio<6.1.0,>=6.0.0
-Requires-Dist: torch<2.2.0,>=2.0.1
-Requires-Dist: torchaudio<2.2.0,>=2.1.0
-Requires-Dist: pyAudioAnalysis==0.3.14
-Requires-Dist: hmmlearn==0.3.0
-Requires-Dist: eyed3~=0.9.7
-Requires-Dist: pydub<0.26.0,>=0.25.1
-Requires-Dist: imblearn
-Requires-Dist: plotly>=5.18.0
-Requires-Dist: transformers~=4.37
-Requires-Dist: tokenizers>=0.14.1
-Requires-Dist: pycountry>=22.3
-Requires-Dist: stanza>=1.7
-Requires-Dist: scipy~=1.11
-Requires-Dist: rev_ai>=2.18.0
-Requires-Dist: rich~=13.6
-Requires-Dist: click~=8.1
-Requires-Dist: matplotlib<4.0.0,>=3.8.0
-Requires-Dist: pyfiglet==1.0.2
-Requires-Dist: soundfile~=0.12.0
-Requires-Dist: rich-click>=1.7.0
-Requires-Dist: typing-extensions
 Provides-Extra: dev
-Requires-Dist: pytest; extra == "dev"
 Provides-Extra: train
-Requires-Dist: accelerate~=0.27; extra == "train"
 Provides-Extra: speaker
-Requires-Dist: nemo-toolkit~=1.21.0; extra == "speaker"
-Requires-Dist: omegaconf~=2.3.0; extra == "speaker"
-Requires-Dist: pydub~=0.25.0; extra == "speaker"
-Requires-Dist: braceexpand; extra == "speaker"
-Requires-Dist: editdistance; extra == "speaker"
-Requires-Dist: g2p_en; extra == "speaker"
-Requires-Dist: ipywidgets; extra == "speaker"
-Requires-Dist: jiwer; extra == "speaker"
-Requires-Dist: kaldi-python-io; extra == "speaker"
-Requires-Dist: kaldiio; extra == "speaker"
-Requires-Dist: lhotse>=1.20.0; extra == "speaker"
-Requires-Dist: librosa>=0.10.0; extra == "speaker"
-Requires-Dist: marshmallow; extra == "speaker"
-Requires-Dist: matplotlib; extra == "speaker"
-Requires-Dist: packaging; extra == "speaker"
-Requires-Dist: pyannote.core; extra == "speaker"
-Requires-Dist: pyannote.metrics; extra == "speaker"
-Requires-Dist: pydub; extra == "speaker"
-Requires-Dist: pyloudnorm; extra == "speaker"
-Requires-Dist: resampy; extra == "speaker"
-Requires-Dist: ruamel.yaml; extra == "speaker"
-Requires-Dist: scipy>=0.14; extra == "speaker"
-Requires-Dist: soundfile; extra == "speaker"
-Requires-Dist: sox; extra == "speaker"
-Requires-Dist: texterrors; extra == "speaker"
-Requires-Dist: hydra-core<=1.3.2,>1.3; extra == "speaker"
-Requires-Dist: omegaconf<=2.3; extra == "speaker"
-Requires-Dist: pytorch-lightning>=2.2.1; extra == "speaker"
-Requires-Dist: torchmetrics>=0.11.0; extra == "speaker"
-Requires-Dist: transformers>=4.36.0; extra == "speaker"
-Requires-Dist: wandb; extra == "speaker"
-Requires-Dist: webdataset>=0.2.86; extra == "speaker"
-Requires-Dist: sentencepiece; extra == "speaker"
-Requires-Dist: youtokentome; extra == "speaker"
+License-File: LICENSE
 
 # TalkBank | Batchalign2
 
@@ -102,13 +42,13 @@ You can get Batchalign from PyPi, and you can update the package in the same way
 macOS/Linux:
 
 ```
-pip3 install -U batchalign
+pip install -U batchalign
 ```
 
 Windows:
 
 ```
-py -m pip3 install -U batchalign
+py -m pip install -U batchalign
 ```
 
 ### Rock and Roll

batchalign-0.7.3b13/batchalign/version

@@ -1,3 +0,0 @@
-0.7.3-beta.13
-July 6th, 2024
-UD Fixes