batchalign 0.7.1b9__tar.gz → 0.7.1b10__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {batchalign-0.7.1b9/batchalign.egg-info → batchalign-0.7.1b10}/PKG-INFO +1 -1
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/document.py +5 -2
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/asr/utils.py +1 -1
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/morphosyntax/ud.py +3 -0
- batchalign-0.7.1b10/batchalign/version +3 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10/batchalign.egg-info}/PKG-INFO +1 -1
- batchalign-0.7.1b9/batchalign/version +0 -3
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/LICENSE +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/MANIFEST.in +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/README.md +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/__main__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/cli/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/cli/cli.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/cli/dispatch.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/constants.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/errors.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/formats/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/formats/base.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/formats/chat/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/formats/chat/file.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/formats/chat/generator.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/formats/chat/lexer.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/formats/chat/parser.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/formats/chat/utils.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/formats/textgrid/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/formats/textgrid/file.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/formats/textgrid/generator.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/formats/textgrid/parser.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/resolve.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/speaker/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/speaker/config.yaml +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/speaker/infer.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/speaker/utils.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/training/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/training/run.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/training/utils.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/utils.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/utterance/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/utterance/dataset.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/utterance/execute.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/utterance/infer.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/utterance/prep.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/utterance/train.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/whisper/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/whisper/infer_asr.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/models/whisper/infer_fa.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/analysis/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/analysis/eval.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/asr/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/asr/rev.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/asr/whisper.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/asr/whisperx.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/base.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/cleanup/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/cleanup/cleanup.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/cleanup/disfluencies.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/cleanup/parse_support.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/cleanup/retrace.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/cleanup/support/filled_pauses.eng +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/cleanup/support/replacements.eng +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/cleanup/support/test.test +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/dispatch.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/fa/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/fa/whisper_fa.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/morphosyntax/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/morphosyntax/fr/case.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/pipeline.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/speaker/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/speaker/nemo_speaker.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/utr/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/utr/rev_utr.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/utr/utils.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/utr/whisper_utr.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/utterance/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/utterance/ud_utterance.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/conftest.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/formats/chat/test_chat_file.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/formats/chat/test_chat_generator.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/formats/chat/test_chat_lexer.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/formats/chat/test_chat_parser.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/formats/chat/test_chat_utils.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/formats/textgrid/test_textgrid.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/pipelines/analysis/test_eval.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/pipelines/asr/test_asr_pipeline.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/pipelines/asr/test_asr_utils.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/pipelines/cleanup/test_disfluency.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/pipelines/cleanup/test_parse_support.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/pipelines/fa/test_fa_pipeline.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/pipelines/fixures.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/pipelines/test_pipeline.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/pipelines/test_pipeline_models.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/test_document.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/utils/__init__.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/utils/config.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/utils/dp.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/utils/utils.py +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign.egg-info/SOURCES.txt +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign.egg-info/dependency_links.txt +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign.egg-info/entry_points.txt +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign.egg-info/requires.txt +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign.egg-info/top_level.txt +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/setup.cfg +0 -0
- {batchalign-0.7.1b9 → batchalign-0.7.1b10}/setup.py +0 -0
@@ -193,9 +193,12 @@ class Utterance(BaseModel):
|
|
193
193
|
|
194
194
|
def __str__(self):
|
195
195
|
if self.text != None:
|
196
|
-
|
196
|
+
t = self.text
|
197
197
|
else:
|
198
|
-
|
198
|
+
t = self._detokenize()
|
199
|
+
|
200
|
+
t = t.replace(". . .", "+...")
|
201
|
+
return t
|
199
202
|
|
200
203
|
def __repr__(self):
|
201
204
|
return str(self)
|
@@ -848,7 +848,10 @@ def morphoanalyze(doc: Document, retokenize:bool, status_hook:callable = None, *
|
|
848
848
|
for j in i]
|
849
849
|
|
850
850
|
retokenized_ut = " ".join(i for i in chunks_backplate if i.strip() not in ["(", ")"])
|
851
|
+
retokenized_ut = retokenized_ut.replace("^", "")
|
851
852
|
retokenized_ut = re.sub(r" +", " ", retokenized_ut)
|
853
|
+
retokenized_ut = retokenized_ut.replace("+ \"", "+\"")
|
854
|
+
retokenized_ut = retokenized_ut.replace(" >", ">")
|
852
855
|
# pray to everyone that it works---this will simply crash and ignore
|
853
856
|
# the utterance if it didn't work, so we are doing this as a sanity
|
854
857
|
# check rather than needing the parsed result
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/cleanup/support/filled_pauses.eng
RENAMED
File without changes
|
{batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/pipelines/cleanup/support/replacements.eng
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/formats/chat/test_chat_generator.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/formats/chat/test_chat_parser.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/formats/textgrid/test_textgrid.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/pipelines/asr/test_asr_pipeline.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/pipelines/cleanup/test_disfluency.py
RENAMED
File without changes
|
{batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/pipelines/cleanup/test_parse_support.py
RENAMED
File without changes
|
{batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/pipelines/fa/test_fa_pipeline.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.1b9 → batchalign-0.7.1b10}/batchalign/tests/pipelines/test_pipeline_models.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|