batchalign 0.7.2__tar.gz → 0.7.3b1__tar.gz

{batchalign-0.7.2/batchalign.egg-info → batchalign-0.7.3b1}/PKG-INFO

@@ -1,16 +1,76 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.2
+Version: 0.7.3b1
 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
-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-0.7.2 → batchalign-0.7.3b1}/batchalign/document.py

@@ -256,6 +256,7 @@ class Utterance(BaseModel):
         detokenized = " ".join(result)
         # replace suprious spaces caused by edge fudging
         detokenized = re.sub(r"< +", "<", detokenized)
+        detokenized = re.sub(r" >", ">", detokenized)
 
         # check and seperate punct 
         last_tok = result[-1]

{batchalign-0.7.2 → batchalign-0.7.3b1}/batchalign/pipelines/cleanup/retrace.py

@@ -43,6 +43,8 @@ class NgramRetraceEngine(BatchalignEngine):
                         for j in content[begin:begin+n]:
                             if j.type != TokenType.FP:
                                 j.type = TokenType.RETRACE
+                                for p in ENDING_PUNCT + MOR_PUNCT:
+                                    j.text = j.text.replace(p, "").strip()
                         root = root+n
                     # we scan grams forward one by one
                     begin += 1

{batchalign-0.7.2 → batchalign-0.7.3b1}/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", "ara"]:
+        if "utterance" not in packages and resolve("utterance", lang) == None and lang not in ["heb", "fra", "ara", "nld"]:
             packages.append("utterance")
     if "fa" in packages:
         if "utr" not in packages:

{batchalign-0.7.2 → batchalign-0.7.3b1}/batchalign/pipelines/morphosyntax/ud.py

@@ -853,6 +853,13 @@ def morphoanalyze(doc: Document, retokenize:bool, status_hook:callable = None, *
                             pos = "x",
                             feats = ""
                         )]
+
+                poses = [i.morphology[0].pos.upper() for i in ut
+                         if i.morphology
+                         and len(i.morphology) > 0]
+                if set(poses) == {"X", "PUNCT"}:
+                    # we don't tag those if there's no morphologyical content
+                    continue
                 # resolve all the numbers and flatten
                 chunks_backplate = [j if isinstance(j, str) else ut[j].text
                                     for i in chunks_backplate

batchalign-0.7.3b1/batchalign/version

@@ -0,0 +1,3 @@
+0.7.3-beta.1
+June 7, 2024
+bug fixes

{batchalign-0.7.2 → batchalign-0.7.3b1/batchalign.egg-info}/PKG-INFO

@@ -1,16 +1,76 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.2
+Version: 0.7.3b1
 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
-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-0.7.2/batchalign/version

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