batchalign 0.7.6a25__tar.gz → 0.7.6a26__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-0.7.6a25/batchalign.egg-info → batchalign-0.7.6a26}/PKG-INFO +1 -1
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/morphosyntax/ud.py +2 -0
- batchalign-0.7.6a26/batchalign/version +3 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26/batchalign.egg-info}/PKG-INFO +1 -1
- batchalign-0.7.6a25/batchalign/version +0 -3
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/LICENSE +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/MANIFEST.in +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/README.md +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/__main__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/cli/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/cli/cli.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/cli/dispatch.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/constants.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/document.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/errors.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/formats/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/formats/base.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/formats/chat/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/formats/chat/file.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/formats/chat/generator.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/formats/chat/lexer.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/formats/chat/parser.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/formats/chat/utils.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/formats/textgrid/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/formats/textgrid/file.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/formats/textgrid/generator.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/formats/textgrid/parser.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/resolve.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/speaker/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/speaker/config.yaml +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/speaker/infer.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/speaker/utils.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/training/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/training/run.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/training/utils.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/utils.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/utterance/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/utterance/dataset.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/utterance/execute.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/utterance/infer.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/utterance/prep.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/utterance/train.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/whisper/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/whisper/infer_asr.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/models/whisper/infer_fa.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/analysis/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/analysis/eval.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/asr/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/asr/rev.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/asr/utils.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/asr/whisper.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/asr/whisperx.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/base.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/cleanup/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/cleanup/cleanup.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/cleanup/disfluencies.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/cleanup/parse_support.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/cleanup/retrace.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/cleanup/support/filled_pauses.eng +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/cleanup/support/replacements.eng +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/cleanup/support/test.test +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/dispatch.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/fa/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/fa/whisper_fa.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/morphosyntax/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/morphosyntax/coref.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/morphosyntax/en/irr.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/morphosyntax/fr/case.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/morphosyntax/ja/verbforms.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/pipeline.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/speaker/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/speaker/nemo_speaker.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/utr/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/utr/rev_utr.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/utr/utils.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/utr/whisper_utr.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/utterance/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/utterance/ud_utterance.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/conftest.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/formats/chat/test_chat_file.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/formats/chat/test_chat_generator.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/formats/chat/test_chat_lexer.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/formats/chat/test_chat_parser.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/formats/chat/test_chat_utils.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/formats/textgrid/test_textgrid.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/analysis/test_eval.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/asr/test_asr_pipeline.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/asr/test_asr_utils.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/cleanup/test_disfluency.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/cleanup/test_parse_support.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/fa/test_fa_pipeline.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/fixures.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/test_pipeline.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/test_pipeline_models.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/test_document.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/utils/__init__.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/utils/config.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/utils/dp.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/utils/utils.py +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign.egg-info/SOURCES.txt +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign.egg-info/dependency_links.txt +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign.egg-info/entry_points.txt +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign.egg-info/requires.txt +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign.egg-info/top_level.txt +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/setup.cfg +0 -0
- {batchalign-0.7.6a25 → batchalign-0.7.6a26}/setup.py +0 -0
@@ -890,6 +890,7 @@ def morphoanalyze(doc: Document, retokenize:bool, status_hook:callable = None, *
|
|
890
890
|
collected = ""
|
891
891
|
# brrr
|
892
892
|
aligned = align(chunks_chars, ud_chars, tqdm=False)
|
893
|
+
|
893
894
|
for i in aligned:
|
894
895
|
if isinstance(i, Match):
|
895
896
|
if i.reference_payload not in chunks_backplate[i.payload]:
|
@@ -939,6 +940,7 @@ def morphoanalyze(doc: Document, retokenize:bool, status_hook:callable = None, *
|
|
939
940
|
retokenized_ut = retokenized_ut.replace(" @", "@")
|
940
941
|
retokenized_ut = re.sub(r"\*[* ]*", "*", retokenized_ut)
|
941
942
|
retokenized_ut = re.sub(r"\*(.*?)\*", r"*\1* ", retokenized_ut)
|
943
|
+
retokenized_ut = re.sub(r"\[\*(.)\]", r"[* \1]", retokenized_ut)
|
942
944
|
# pray to everyone that it works---this will simply crash and ignore
|
943
945
|
# the utterance if it didn't work, so we are doing this as a sanity
|
944
946
|
# 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
|
File without changes
|
File without changes
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/cleanup/support/filled_pauses.eng
RENAMED
File without changes
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/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
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/pipelines/morphosyntax/ja/verbforms.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
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/formats/chat/test_chat_generator.py
RENAMED
File without changes
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/formats/chat/test_chat_lexer.py
RENAMED
File without changes
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/formats/chat/test_chat_parser.py
RENAMED
File without changes
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/formats/chat/test_chat_utils.py
RENAMED
File without changes
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/formats/textgrid/test_textgrid.py
RENAMED
File without changes
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/analysis/test_eval.py
RENAMED
File without changes
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/asr/test_asr_pipeline.py
RENAMED
File without changes
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/asr/test_asr_utils.py
RENAMED
File without changes
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/cleanup/test_disfluency.py
RENAMED
File without changes
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/cleanup/test_parse_support.py
RENAMED
File without changes
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/batchalign/tests/pipelines/fa/test_fa_pipeline.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.6a25 → batchalign-0.7.6a26}/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
|