batchalign 0.7.7a1__tar.gz → 0.7.7a3__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-0.7.7a1/batchalign.egg-info → batchalign-0.7.7a3}/PKG-INFO +1 -1
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/morphosyntax/ud.py +1 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/utterance/ud_utterance.py +2 -1
- batchalign-0.7.7a3/batchalign/version +3 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3/batchalign.egg-info}/PKG-INFO +1 -1
- batchalign-0.7.7a1/batchalign/version +0 -3
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/LICENSE +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/MANIFEST.in +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/README.md +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/__main__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/cli/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/cli/cli.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/cli/dispatch.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/constants.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/document.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/errors.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/formats/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/formats/base.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/formats/chat/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/formats/chat/file.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/formats/chat/generator.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/formats/chat/lexer.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/formats/chat/parser.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/formats/chat/utils.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/formats/textgrid/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/formats/textgrid/file.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/formats/textgrid/generator.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/formats/textgrid/parser.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/resolve.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/speaker/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/speaker/config.yaml +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/speaker/infer.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/speaker/utils.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/training/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/training/run.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/training/utils.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/utils.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/utterance/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/utterance/dataset.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/utterance/execute.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/utterance/infer.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/utterance/prep.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/utterance/train.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/whisper/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/whisper/infer_asr.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/models/whisper/infer_fa.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/analysis/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/analysis/eval.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/asr/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/asr/rev.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/asr/utils.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/asr/whisper.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/asr/whisperx.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/base.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/cleanup/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/cleanup/cleanup.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/cleanup/disfluencies.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/cleanup/parse_support.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/cleanup/retrace.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/cleanup/support/filled_pauses.eng +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/cleanup/support/replacements.eng +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/cleanup/support/test.test +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/dispatch.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/fa/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/fa/whisper_fa.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/morphosyntax/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/morphosyntax/coref.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/morphosyntax/en/irr.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/morphosyntax/fr/apm.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/morphosyntax/fr/apmn.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/morphosyntax/fr/case.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/morphosyntax/ja/verbforms.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/pipeline.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/speaker/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/speaker/nemo_speaker.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/utr/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/utr/rev_utr.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/utr/utils.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/utr/whisper_utr.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/utterance/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/conftest.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/formats/chat/test_chat_file.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/formats/chat/test_chat_generator.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/formats/chat/test_chat_lexer.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/formats/chat/test_chat_parser.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/formats/chat/test_chat_utils.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/formats/textgrid/test_textgrid.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/pipelines/analysis/test_eval.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/pipelines/asr/test_asr_pipeline.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/pipelines/asr/test_asr_utils.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/pipelines/cleanup/test_disfluency.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/pipelines/cleanup/test_parse_support.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/pipelines/fa/test_fa_pipeline.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/pipelines/fixures.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/pipelines/test_pipeline.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/pipelines/test_pipeline_models.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/test_document.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/utils/__init__.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/utils/config.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/utils/dp.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/utils/utils.py +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign.egg-info/SOURCES.txt +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign.egg-info/dependency_links.txt +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign.egg-info/entry_points.txt +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign.egg-info/requires.txt +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign.egg-info/top_level.txt +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/setup.cfg +0 -0
- {batchalign-0.7.7a1 → batchalign-0.7.7a3}/setup.py +0 -0
@@ -964,6 +964,7 @@ def morphoanalyze(doc: Document, retokenize:bool, status_hook:callable = None, *
|
|
964
964
|
# the utterance if it didn't work, so we are doing this as a sanity
|
965
965
|
# check rather than needing the parsed result
|
966
966
|
_1, _2 = chat_parse_utterance(retokenized_ut, mor, gra, None, None)
|
967
|
+
retokenized_ut = re.sub(r"⁎ @", r"⁎@", retokenized_ut)
|
967
968
|
doc.content[indx] = Utterance(content=ut,
|
968
969
|
text=retokenized_ut,
|
969
970
|
tier=doc.content[indx].tier,
|
@@ -84,6 +84,7 @@ def parse_tree(subtree):
|
|
84
84
|
for i in stack]
|
85
85
|
|
86
86
|
def process_ut(ut, nlp):
|
87
|
+
|
87
88
|
# remove punct
|
88
89
|
if (ut.content[-1].type == TokenType.PUNCT or
|
89
90
|
ut.content[-1].text in ENDING_PUNCT):
|
@@ -142,7 +143,7 @@ def process_ut(ut, nlp):
|
|
142
143
|
if isinstance(i, Match):
|
143
144
|
matches.append(i)
|
144
145
|
elif i.extra_type == ExtraType.REFERENCE:
|
145
|
-
new_refs.append(ReferenceTarget(key=i.key, payload=i.payload))
|
146
|
+
new_refs.append(ReferenceTarget(key=i.key, payload=i.payload if i.payload else -1))
|
146
147
|
|
147
148
|
# we now sort the references based on their orignial utterance order
|
148
149
|
matches = matches + new_refs
|
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
|
File without changes
|
File without changes
|
{batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/pipelines/cleanup/support/filled_pauses.eng
RENAMED
File without changes
|
{batchalign-0.7.7a1 → batchalign-0.7.7a3}/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
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/formats/chat/test_chat_generator.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/formats/textgrid/test_textgrid.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/pipelines/asr/test_asr_pipeline.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/pipelines/cleanup/test_disfluency.py
RENAMED
File without changes
|
{batchalign-0.7.7a1 → batchalign-0.7.7a3}/batchalign/tests/pipelines/cleanup/test_parse_support.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.7a1 → batchalign-0.7.7a3}/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
|