batchalign 0.7.6a9__tar.gz → 0.7.6a12__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-0.7.6a9/batchalign.egg-info → batchalign-0.7.6a12}/PKG-INFO +1 -1
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/morphosyntax/ud.py +4 -1
- batchalign-0.7.6a12/batchalign/version +3 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12/batchalign.egg-info}/PKG-INFO +1 -1
- batchalign-0.7.6a9/batchalign/version +0 -3
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/LICENSE +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/MANIFEST.in +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/README.md +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/__main__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/cli/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/cli/cli.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/cli/dispatch.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/constants.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/document.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/errors.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/formats/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/formats/base.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/formats/chat/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/formats/chat/file.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/formats/chat/generator.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/formats/chat/lexer.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/formats/chat/parser.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/formats/chat/utils.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/formats/textgrid/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/formats/textgrid/file.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/formats/textgrid/generator.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/formats/textgrid/parser.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/resolve.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/speaker/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/speaker/config.yaml +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/speaker/infer.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/speaker/utils.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/training/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/training/run.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/training/utils.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/utils.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/utterance/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/utterance/dataset.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/utterance/execute.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/utterance/infer.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/utterance/prep.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/utterance/train.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/whisper/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/whisper/infer_asr.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/models/whisper/infer_fa.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/analysis/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/analysis/eval.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/asr/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/asr/rev.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/asr/utils.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/asr/whisper.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/asr/whisperx.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/base.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/cleanup/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/cleanup/cleanup.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/cleanup/disfluencies.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/cleanup/parse_support.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/cleanup/retrace.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/cleanup/support/filled_pauses.eng +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/cleanup/support/replacements.eng +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/cleanup/support/test.test +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/dispatch.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/fa/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/fa/whisper_fa.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/morphosyntax/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/morphosyntax/coref.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/morphosyntax/fr/case.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/morphosyntax/ja/verbforms.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/pipeline.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/speaker/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/speaker/nemo_speaker.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/utr/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/utr/rev_utr.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/utr/utils.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/utr/whisper_utr.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/utterance/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/utterance/ud_utterance.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/conftest.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/formats/chat/test_chat_file.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/formats/chat/test_chat_generator.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/formats/chat/test_chat_lexer.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/formats/chat/test_chat_parser.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/formats/chat/test_chat_utils.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/formats/textgrid/test_textgrid.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/pipelines/analysis/test_eval.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/pipelines/asr/test_asr_pipeline.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/pipelines/asr/test_asr_utils.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/pipelines/cleanup/test_disfluency.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/pipelines/cleanup/test_parse_support.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/pipelines/fa/test_fa_pipeline.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/pipelines/fixures.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/pipelines/test_pipeline.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/pipelines/test_pipeline_models.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/test_document.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/utils/__init__.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/utils/config.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/utils/dp.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/utils/utils.py +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign.egg-info/SOURCES.txt +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign.egg-info/dependency_links.txt +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign.egg-info/entry_points.txt +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign.egg-info/requires.txt +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign.egg-info/top_level.txt +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/setup.cfg +0 -0
- {batchalign-0.7.6a9 → batchalign-0.7.6a12}/setup.py +0 -0
@@ -139,6 +139,7 @@ def handler(word, lang=None):
|
|
139
139
|
if lang == "ja":
|
140
140
|
from batchalign.pipelines.morphosyntax.ja.verbforms import verbform
|
141
141
|
pos,target = verbform(pos,target,word.text)
|
142
|
+
target = target.replace(',', 'cm')
|
142
143
|
|
143
144
|
return f"{'' if not unknown else '0'}{pos}|{target}"
|
144
145
|
|
@@ -279,6 +280,8 @@ def handler__PUNCT(word, lang=None):
|
|
279
280
|
# instead of the lemma, which maybe entirely weird
|
280
281
|
if word.text == "もん":
|
281
282
|
return f"part|{word.text}"
|
283
|
+
if word.text == ",":
|
284
|
+
return f"cm|cm"
|
282
285
|
else:
|
283
286
|
return f"x|{word.text}"
|
284
287
|
|
@@ -421,7 +424,7 @@ def parse_sentence(sentence, delimiter=".", special_forms=[], lang="$nospecial$"
|
|
421
424
|
# specivl forms: recall the special form marker is xbxxx
|
422
425
|
if "xbxxx" in word.text.strip():
|
423
426
|
form = special_forms.pop(0)
|
424
|
-
mor.append(f"x|{form.strip()}")
|
427
|
+
mor.append(f"x|{form.strip().replace(',', 'cm')}")
|
425
428
|
special_form_ids.append(word.id)
|
426
429
|
else:
|
427
430
|
mor.append(mor_word)
|
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-0.7.6a9 → batchalign-0.7.6a12}/batchalign/pipelines/cleanup/support/filled_pauses.eng
RENAMED
File without changes
|
{batchalign-0.7.6a9 → batchalign-0.7.6a12}/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
|
{batchalign-0.7.6a9 → batchalign-0.7.6a12}/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-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/formats/chat/test_chat_generator.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/formats/chat/test_chat_parser.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/formats/textgrid/test_textgrid.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/pipelines/asr/test_asr_pipeline.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/pipelines/cleanup/test_disfluency.py
RENAMED
File without changes
|
{batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/pipelines/cleanup/test_parse_support.py
RENAMED
File without changes
|
{batchalign-0.7.6a9 → batchalign-0.7.6a12}/batchalign/tests/pipelines/fa/test_fa_pipeline.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.6a9 → batchalign-0.7.6a12}/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
|