batchalign 0.7.3b16__tar.gz → 0.7.4__tar.gz

{batchalign-0.7.3b16/batchalign.egg-info → batchalign-0.7.4}/PKG-INFO

@@ -1,16 +1,76 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.3b16
+Version: 0.7.4
 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>=2.0.1
+Requires-Dist: torchaudio>=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
-License-File: LICENSE
+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"
 
 # TalkBank | Batchalign2
 

{batchalign-0.7.3b16 → batchalign-0.7.4}/batchalign/formats/chat/utils.py

@@ -43,17 +43,8 @@ def chat_parse_mor(mor_str):
     if mor_str in ENDING_PUNCT:
         return [Morphology(lemma=mor_str, pos="PUNCT", feats="")]
 
-    # JANK handle + forms
-    if "+" in mor_str:
-        pos, rest = mor_str.split("+", maxsplit=1)
-        return [Morphology.model_validate({
-            "lemma": "+"+rest,
-            "pos": pos.strip("|"),
-            "feats": "",
-        })]
-
     try:
-        mors = [i.split("|") for i in re.split("[~$]", mor_str)]
+        mors = [i.split("|", maxsplit=1) for i in re.split("[~$]", mor_str)]
         # TODO epic jank: backwards compatibility check: if a form
         # uses a lot of dashes, its probably because its old-style
         # dash seperated; if it doesn't; it probably is new-style
@@ -67,11 +58,32 @@ def chat_parse_mor(mor_str):
     except:
         raise CHATValidationException(f"mor parser recieved invalid mor string: '{mor_str}'")
 
-    mors = [Morphology.model_validate({
-        "lemma": l,
-        "pos": p,
-        "feats": f,
-    }) for p,l,f in zip(pos, lemmas, feats)]
+
+    mors = []
+    for p,l,f in zip(pos, lemmas, feats):
+        # if "+" not in mor_str:
+        mors.append(Morphology.model_validate({
+            "lemma": l,
+            "pos": p,
+            "feats": f,
+        }))
+        # else:
+        #     breakpoint()
+        #     pos, rest = mor_str.split("+", maxsplit=1)
+
+
+
+    # # JANK handle + forms
+    # if "+" in mor_str:
+    #     pos, rest = mor_str.split("+", maxsplit=1)
+    #     return [Morphology.model_validate({
+    #         "lemma": "+"+rest,
+    #         "pos": pos.strip("|"),
+    #         "feats": "",
+    #     })]
+
+
+    # mors = [ ]
 
     return mors
     

{batchalign-0.7.3b16 → batchalign-0.7.4}/batchalign/pipelines/morphosyntax/ud.py

@@ -890,6 +890,7 @@ 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 = re.sub(r"@ ?w ?p", "@wp", retokenized_ut)
                 retokenized_ut = retokenized_ut.replace(" @", "@")

batchalign-0.7.4/batchalign/version

@@ -0,0 +1,3 @@
+0.7.4
+September 2nd, 2024
+Bumping BA Major + Python

{batchalign-0.7.3b16 → batchalign-0.7.4/batchalign.egg-info}/PKG-INFO

@@ -1,16 +1,76 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.3b16
+Version: 0.7.4
 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>=2.0.1
+Requires-Dist: torchaudio>=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
-License-File: LICENSE
+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"
 
 # TalkBank | Batchalign2
 

{batchalign-0.7.3b16 → batchalign-0.7.4}/batchalign.egg-info/requires.txt

@@ -1,15 +1,15 @@
 pydantic>=2.4
 nltk>=3.8
 praatio<6.1.0,>=6.0.0
-torch<2.2.0,>=2.0.1
-torchaudio<2.2.0,>=2.1.0
+torch>=2.0.1
+torchaudio>=2.1.0
 pyAudioAnalysis==0.3.14
 hmmlearn==0.3.0
 eyed3~=0.9.7
 pydub<0.26.0,>=0.25.1
 imblearn
 plotly>=5.18.0
-transformers~=4.37
+transformers>=4.37
 tokenizers>=0.14.1
 pycountry>=22.3
 stanza>=1.7

{batchalign-0.7.3b16 → batchalign-0.7.4}/setup.py

@@ -29,15 +29,15 @@ setup(
         "pydantic>=2.4",
         "nltk>=3.8",
         "praatio>=6.0.0,<6.1.0",
-        "torch>=2.0.1,<2.2.0",
-        "torchaudio>=2.1.0,<2.2.0",
+        "torch>=2.0.1",
+        "torchaudio>=2.1.0",
         "pyAudioAnalysis==0.3.14",
         "hmmlearn==0.3.0",
         "eyed3~=0.9.7",
         "pydub>=0.25.1,<0.26.0",
         "imblearn",
         "plotly>=5.18.0",
-        "transformers~=4.37",
+        "transformers>=4.37",
         "tokenizers>=0.14.1",
         "pycountry>=22.3",
         "stanza>=1.7",

batchalign-0.7.3b16/batchalign/version

@@ -1,3 +0,0 @@
-0.7.3-beta.16
-August 3rd, 2024
-more Japanese hand-parse rules