batchalign 0.7.3b17__tar.gz → 0.7.5a1__tar.gz

{batchalign-0.7.3b17/batchalign.egg-info → batchalign-0.7.5a1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.3b17
+Version: 0.7.5a1
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -11,15 +11,15 @@ 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: 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: transformers>=4.37
 Requires-Dist: tokenizers>=0.14.1
 Requires-Dist: pycountry>=22.3
 Requires-Dist: stanza>=1.7

{batchalign-0.7.3b17 → batchalign-0.7.5a1}/batchalign/cli/cli.py

@@ -49,15 +49,7 @@ def common_options(f):
         click.argument("in_dir",
                        type=click.Path(exists=True, file_okay=False)),
         click.argument("out_dir",
-                       type=click.Path(exists=True, file_okay=False)),
-        click.option("--lang",
-                     help="sample language in three-letter ISO 3166-1 alpha-3 code",
-                     show_default=True,
-                     default="eng",
-                     type=str),
-        click.option("-n", "--num_speakers", type=int,
-                     help="number of speakers in the language sample", default=2),
-        
+                       type=click.Path(exists=True, file_okay=False))
     ]
 
     options.reverse()
@@ -115,8 +107,9 @@ batchalign.add_command(train, "models")
 @common_options
 @click.option("--whisper/--rev",
               default=False, help="For utterance timing recovery, OpenAI Whisper (ASR) instead of Rev.AI (default).")
+
 @click.pass_context
-def align(ctx, in_dir, out_dir, lang, num_speakers, whisper, **kwargs):
+def align(ctx, in_dir, out_dir, whisper, **kwargs):
     """Align transcripts against corresponding media files."""
     def loader(file):
         return CHATFile(path=os.path.abspath(file)).doc
@@ -124,7 +117,7 @@ def align(ctx, in_dir, out_dir, lang, num_speakers, whisper, **kwargs):
     def writer(doc, output):
         CHATFile(doc=doc).write(output)
 
-    _dispatch("align", lang, num_speakers,
+    _dispatch("align", "eng", 1,
               ["cha"], ctx,
               in_dir, out_dir,
               loader, writer, C,
@@ -143,6 +136,12 @@ def align(ctx, in_dir, out_dir, lang, num_speakers, whisper, **kwargs):
               default=False, help="Perform speaker diarization (this flag is ignored with Rev.AI)")
 @click.option("--wor/--nowor",
               default=False, help="Should we write word level alignment line? Default to no.")
+@click.option("--lang",
+              help="sample language in three-letter ISO 3166-1 alpha-3 code",
+              show_default=True,
+              default="eng",
+              type=str)
+@click.option("-n", "--num_speakers", type=int, help="number of speakers in the language sample", default=2)
 @click.pass_context
 def transcribe(ctx, in_dir, out_dir, lang, num_speakers, **kwargs):
     """Create a transcript from audio files."""
@@ -189,7 +188,7 @@ def transcribe(ctx, in_dir, out_dir, lang, num_speakers, **kwargs):
                               file_okay=True, dir_okay=False),
               help="Comma seperated manual lexicon override")
 @click.pass_context
-def morphotag(ctx, in_dir, out_dir, lang, num_speakers, **kwargs):
+def morphotag(ctx, in_dir, out_dir, **kwargs):
     """Perform morphosyntactic analysis on transcripts."""
 
     def loader(file):
@@ -213,7 +212,7 @@ def morphotag(ctx, in_dir, out_dir, lang, num_speakers, **kwargs):
     def writer(doc, output):
         CHATFile(doc=doc, special_mor_=doc.ba_special_.get("special_mor_notation", False)).write(output)
 
-    _dispatch("morphotag", lang, num_speakers, ["cha"], ctx,
+    _dispatch("morphotag", "eng", 1, ["cha"], ctx,
               in_dir, out_dir,
               loader, writer, C)
 
@@ -222,6 +221,12 @@ def morphotag(ctx, in_dir, out_dir, lang, num_speakers, **kwargs):
 
 @batchalign.command()
 @common_options
+@click.option("--lang",
+              help="sample language in three-letter ISO 3166-1 alpha-3 code",
+              show_default=True,
+              default="eng",
+              type=str)
+@click.option("-n", "--num_speakers", type=int, help="number of speakers in the language sample", default=2)
 @click.pass_context
 def utseg(ctx, in_dir, out_dir, lang, num_speakers, **kwargs):
     """Perform morphosyntactic analysis on transcripts."""

batchalign-0.7.5a1/batchalign/version

@@ -0,0 +1,3 @@
+0.7.5-alpha.1
+September 3nd, 2024
+Removes unneeded options

{batchalign-0.7.3b17 → batchalign-0.7.5a1/batchalign.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.3b17
+Version: 0.7.5a1
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -11,15 +11,15 @@ 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: 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: transformers>=4.37
 Requires-Dist: tokenizers>=0.14.1
 Requires-Dist: pycountry>=22.3
 Requires-Dist: stanza>=1.7

{batchalign-0.7.3b17 → batchalign-0.7.5a1}/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-0.7.3b17 → batchalign-0.7.5a1}/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-0.7.3b17/batchalign/version

@@ -1,3 +0,0 @@
-0.7.3-beta.17
-August 21st, 2024
-manual rules with mor