batchalign 0.7.6a21__tar.gz → 0.7.6a23__tar.gz

{batchalign-0.7.6a21/batchalign.egg-info → batchalign-0.7.6a23}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.6a21
+Version: 0.7.6a23
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -11,14 +11,13 @@ 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: torch
+Requires-Dist: torchaudio
 Requires-Dist: hmmlearn==0.3.0
-Requires-Dist: eyed3~=0.9.7
-Requires-Dist: pydub<0.26.0,>=0.25.1
+Requires-Dist: eyed3
+Requires-Dist: pydub
 Requires-Dist: imblearn
-Requires-Dist: plotly>=5.18.0
+Requires-Dist: plotly>=5.3.0
 Requires-Dist: transformers>=4.37
 Requires-Dist: tokenizers>=0.14.1
 Requires-Dist: pycountry>=22.3
@@ -36,41 +35,6 @@ 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"
 
 # TalkBank | Batchalign2
 

{batchalign-0.7.6a21 → batchalign-0.7.6a23}/batchalign/pipelines/morphosyntax/ja/verbforms.py

@@ -4,6 +4,12 @@ Fix Japanese verb forms.
 """
 
 def verbform(upos, target, text):
+    if "為る" in target and 'さ' == text:
+        return "part", "為る"
+    if "無い" in target:
+        return "aux", "ない"
+    if "せる" in target:
+        return "aux", "させる"
     if "撮る" in text:
         return "verb", "撮る"
     if "貼る" in text:
@@ -97,7 +103,7 @@ def verbform(upos, target, text):
     if text == "たら":
         return "sconj", "たら"
     if text == "たっ":
-        return "sconj", "たって"
+        return "sconj", "たっ"
     # if text == "て" and upos == "sconj":
     #     return "aux", "て"
     if text == "なさい" and target == "為さる":
@@ -114,6 +120,9 @@ def verbform(upos, target, text):
         return "aux", "よう"
     if text == "ろ" and upos == "aux" and target == "為る":
         return "aux", "ろ"
+    if text == "で":
+        return "sconj", "で"
+
     # if upos == "verb" and "る" in target:
     #     return "verb", target.replace("る","").strip()
 

batchalign-0.7.6a23/batchalign/version

@@ -0,0 +1,3 @@
+0.7.6-alpha.23
+November 8, 2024
+Japanese changes

{batchalign-0.7.6a21 → batchalign-0.7.6a23/batchalign.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.6a21
+Version: 0.7.6a23
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -11,14 +11,13 @@ 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: torch
+Requires-Dist: torchaudio
 Requires-Dist: hmmlearn==0.3.0
-Requires-Dist: eyed3~=0.9.7
-Requires-Dist: pydub<0.26.0,>=0.25.1
+Requires-Dist: eyed3
+Requires-Dist: pydub
 Requires-Dist: imblearn
-Requires-Dist: plotly>=5.18.0
+Requires-Dist: plotly>=5.3.0
 Requires-Dist: transformers>=4.37
 Requires-Dist: tokenizers>=0.14.1
 Requires-Dist: pycountry>=22.3
@@ -36,41 +35,6 @@ 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"
 
 # TalkBank | Batchalign2
 

batchalign-0.7.6a23/batchalign.egg-info/requires.txt

@@ -0,0 +1,29 @@
+pydantic>=2.4
+nltk>=3.8
+praatio<6.1.0,>=6.0.0
+torch
+torchaudio
+hmmlearn==0.3.0
+eyed3
+pydub
+imblearn
+plotly>=5.3.0
+transformers>=4.37
+tokenizers>=0.14.1
+pycountry>=22.3
+stanza[transformers]>=1.9.1
+scipy~=1.11
+rev_ai>=2.18.0
+rich~=13.6
+click~=8.1
+matplotlib<4.0.0,>=3.8.0
+pyfiglet==1.0.2
+soundfile~=0.12.0
+rich-click>=1.7.0
+typing-extensions
+
+[dev]
+pytest
+
+[train]
+accelerate~=0.27

{batchalign-0.7.6a21 → batchalign-0.7.6a23}/setup.py

@@ -29,14 +29,14 @@ setup(
         "pydantic>=2.4",
         "nltk>=3.8",
         "praatio>=6.0.0,<6.1.0",
-        "torch>=2.0.1",
-        "torchaudio>=2.1.0",
-        "pyAudioAnalysis==0.3.14",
+        "torch",
+        "torchaudio",
+        # "pyAudioAnalysis",
         "hmmlearn==0.3.0",
-        "eyed3~=0.9.7",
-        "pydub>=0.25.1,<0.26.0",
+        "eyed3",
+        "pydub",
         "imblearn",
-        "plotly>=5.18.0",
+        "plotly>=5.3.0",
         "transformers>=4.37",
         "tokenizers>=0.14.1",
         "pycountry>=22.3",
@@ -58,42 +58,42 @@ setup(
         'train': [
             'accelerate~=0.27',
         ],
-        'speaker': [
-            "nemo-toolkit~=1.21.0",
-            "omegaconf~=2.3.0",
-            "pydub~=0.25.0",
-            "braceexpand",
-            "editdistance",
-            "g2p_en",
-            "ipywidgets",
-            "jiwer",
-            "kaldi-python-io",
-            "kaldiio",
-            "lhotse>=1.20.0",
-            "librosa>=0.10.0",
-            "marshmallow",
-            "matplotlib",
-            "packaging",
-            "pyannote.core",
-            "pyannote.metrics",
-            "pydub",
-            "pyloudnorm",
-            "resampy",
-            "ruamel.yaml",
-            "scipy>=0.14",
-            "soundfile",
-            "sox",
-            "texterrors",
-            "hydra-core>1.3,<=1.3.2",
-            "omegaconf<=2.3",
-            "pytorch-lightning>=2.2.1",
-            "torchmetrics>=0.11.0",
-            "transformers>=4.36.0",
-            "wandb",
-            "webdataset>=0.2.86",
-            "sentencepiece",
-            "youtokentome",
-        ]
+        # 'speaker': [
+        #     "nemo-toolkit~=1.21.0",
+        #     "omegaconf~=2.3.0",
+        #     "pydub~=0.25.0",
+        #     "braceexpand",
+        #     "editdistance",
+        #     "g2p_en",
+        #     "ipywidgets",
+        #     "jiwer",
+        #     "kaldi-python-io",
+        #     "kaldiio",
+        #     "lhotse>=1.20.0",
+        #     "librosa>=0.10.0",
+        #     "marshmallow",
+        #     "matplotlib",
+        #     "packaging",
+        #     "pyannote.core",
+        #     "pyannote.metrics",
+        #     "pydub",
+        #     "pyloudnorm",
+        #     "resampy",
+        #     "ruamel.yaml",
+        #     "scipy>=0.14",
+        #     "soundfile",
+        #     "sox",
+        #     "texterrors",
+        #     "hydra-core>1.3,<=1.3.2",
+        #     "omegaconf<=2.3",
+        #     "pytorch-lightning>=2.2.1",
+        #     "torchmetrics>=0.11.0",
+        #     "transformers>=4.36.0",
+        #     "wandb",
+        #     "webdataset>=0.2.86",
+        #     "sentencepiece",
+        #     "youtokentome",
+        # ]
     },
     include_package_data=True,
     classifiers=[

batchalign-0.7.6a21/batchalign/version

@@ -1,3 +0,0 @@
-0.7.6-alpha.21
-October 16, 2024
-Japanese changes

batchalign-0.7.6a21/batchalign.egg-info/requires.txt

@@ -1,66 +0,0 @@
-pydantic>=2.4
-nltk>=3.8
-praatio<6.1.0,>=6.0.0
-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
-tokenizers>=0.14.1
-pycountry>=22.3
-stanza[transformers]>=1.9.1
-scipy~=1.11
-rev_ai>=2.18.0
-rich~=13.6
-click~=8.1
-matplotlib<4.0.0,>=3.8.0
-pyfiglet==1.0.2
-soundfile~=0.12.0
-rich-click>=1.7.0
-typing-extensions
-
-[dev]
-pytest
-
-[speaker]
-nemo-toolkit~=1.21.0
-omegaconf~=2.3.0
-pydub~=0.25.0
-braceexpand
-editdistance
-g2p_en
-ipywidgets
-jiwer
-kaldi-python-io
-kaldiio
-lhotse>=1.20.0
-librosa>=0.10.0
-marshmallow
-matplotlib
-packaging
-pyannote.core
-pyannote.metrics
-pydub
-pyloudnorm
-resampy
-ruamel.yaml
-scipy>=0.14
-soundfile
-sox
-texterrors
-hydra-core<=1.3.2,>1.3
-omegaconf<=2.3
-pytorch-lightning>=2.2.1
-torchmetrics>=0.11.0
-transformers>=4.36.0
-wandb
-webdataset>=0.2.86
-sentencepiece
-youtokentome
-
-[train]
-accelerate~=0.27