batchalign 0.7.1b14__tar.gz → 0.7.2__tar.gz

{batchalign-0.7.1b14/batchalign.egg-info → batchalign-0.7.2}/PKG-INFO

@@ -1,76 +1,16 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.1b14
+Version: 0.7.2
 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
 

{batchalign-0.7.1b14 → batchalign-0.7.2}/batchalign/formats/chat/file.py

@@ -53,7 +53,7 @@ class CHATFile(BaseFormat):
 
         if path:
             # read in the resulting file
-            with open(path, "r") as df:
+            with open(path, "r", encoding="utf-8") as df:
                 # get alignment result
                 data = df.readlines()
             # conform result with tab-seperated beginnings
@@ -104,7 +104,7 @@ class CHATFile(BaseFormat):
         
         str_doc = self.__generate(self.__doc, self.__special_mor, write_wor=write_wor)
 
-        with open(path, 'w') as df:
+        with open(path, 'w', encoding="utf-8") as df:
             df.write(str_doc)
 
     @staticmethod

{batchalign-0.7.1b14 → batchalign-0.7.2}/batchalign/pipelines/dispatch.py

@@ -73,7 +73,7 @@ def dispatch_pipeline(pkg_str, lang, num_speakers=None, **arg_overrides):
             packages.append("disfluency")
         if "retracing" not in packages:
             packages.append("retracing")
-        if "utterance" not in packages and resolve("utterance", lang) == None and lang not in ["heb", "fra"]:
+        if "utterance" not in packages and resolve("utterance", lang) == None and lang not in ["heb", "fra", "ara"]:
             packages.append("utterance")
     if "fa" in packages:
         if "utr" not in packages:

batchalign-0.7.2/batchalign/version

@@ -0,0 +1,3 @@
+0.7.2
+June 02nd, 2024
+force UTF-8 encoding

{batchalign-0.7.1b14 → batchalign-0.7.2/batchalign.egg-info}/PKG-INFO

@@ -1,76 +1,16 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.1b14
+Version: 0.7.2
 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
 

batchalign-0.7.1b14/batchalign/version

@@ -1,3 +0,0 @@
-0.7.1-beta.14
-June 02nd, 2024
-more UD bugs, superceeds v0.7.1-beta.13