batchalign 0.7.6a28__tar.gz → 0.7.6a30__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-0.7.6a28/batchalign.egg-info → batchalign-0.7.6a30}/PKG-INFO +1 -1
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/morphosyntax/ja/verbforms.py +16 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/morphosyntax/ud.py +10 -2
- batchalign-0.7.6a30/batchalign/version +3 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30/batchalign.egg-info}/PKG-INFO +1 -1
- batchalign-0.7.6a28/batchalign/version +0 -3
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/LICENSE +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/MANIFEST.in +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/README.md +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/__main__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/cli/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/cli/cli.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/cli/dispatch.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/constants.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/document.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/errors.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/formats/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/formats/base.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/formats/chat/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/formats/chat/file.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/formats/chat/generator.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/formats/chat/lexer.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/formats/chat/parser.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/formats/chat/utils.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/formats/textgrid/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/formats/textgrid/file.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/formats/textgrid/generator.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/formats/textgrid/parser.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/resolve.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/speaker/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/speaker/config.yaml +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/speaker/infer.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/speaker/utils.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/training/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/training/run.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/training/utils.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/utils.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/utterance/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/utterance/dataset.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/utterance/execute.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/utterance/infer.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/utterance/prep.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/utterance/train.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/whisper/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/whisper/infer_asr.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/models/whisper/infer_fa.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/analysis/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/analysis/eval.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/asr/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/asr/rev.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/asr/utils.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/asr/whisper.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/asr/whisperx.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/base.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/cleanup/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/cleanup/cleanup.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/cleanup/disfluencies.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/cleanup/parse_support.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/cleanup/retrace.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/cleanup/support/filled_pauses.eng +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/cleanup/support/replacements.eng +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/cleanup/support/test.test +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/dispatch.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/fa/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/fa/whisper_fa.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/morphosyntax/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/morphosyntax/coref.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/morphosyntax/en/irr.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/morphosyntax/fr/case.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/pipeline.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/speaker/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/speaker/nemo_speaker.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/utr/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/utr/rev_utr.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/utr/utils.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/utr/whisper_utr.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/utterance/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/utterance/ud_utterance.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/conftest.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/formats/chat/test_chat_file.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/formats/chat/test_chat_generator.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/formats/chat/test_chat_lexer.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/formats/chat/test_chat_parser.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/formats/chat/test_chat_utils.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/formats/textgrid/test_textgrid.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/analysis/test_eval.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/asr/test_asr_pipeline.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/asr/test_asr_utils.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/cleanup/test_disfluency.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/cleanup/test_parse_support.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/fa/test_fa_pipeline.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/fixures.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/test_pipeline.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/test_pipeline_models.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/test_document.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/utils/__init__.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/utils/config.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/utils/dp.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/utils/utils.py +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign.egg-info/SOURCES.txt +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign.egg-info/dependency_links.txt +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign.egg-info/entry_points.txt +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign.egg-info/requires.txt +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign.egg-info/top_level.txt +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/setup.cfg +0 -0
- {batchalign-0.7.6a28 → batchalign-0.7.6a30}/setup.py +0 -0
{batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/morphosyntax/ja/verbforms.py
RENAMED
@@ -4,6 +4,22 @@ Fix Japanese verb forms.
|
|
4
4
|
"""
|
5
5
|
|
6
6
|
def verbform(upos, target, text):
|
7
|
+
if "ちゃ" in text:
|
8
|
+
return "sconj", "ば"
|
9
|
+
if "なきゃ" in text:
|
10
|
+
return "sconj", "なきゃ"
|
11
|
+
if "じゃ" in text:
|
12
|
+
return "sconj", "ちゃ"
|
13
|
+
if "れる" in text:
|
14
|
+
return "aux", "られる"
|
15
|
+
if "じゃう" in text:
|
16
|
+
return "aux", "ちゃう"
|
17
|
+
if "よう" in text:
|
18
|
+
return "aux", "おう"
|
19
|
+
if "だら" in text:
|
20
|
+
return "aux", "たら"
|
21
|
+
if "だ" in target:
|
22
|
+
return "aux", "た"
|
7
23
|
if "為る" in target and 'さ' == text:
|
8
24
|
return "part", "為る"
|
9
25
|
if "無い" in target:
|
@@ -175,14 +175,20 @@ def handler__DET(word, lang=None):
|
|
175
175
|
return handler(word)
|
176
176
|
|
177
177
|
# get gender and numer
|
178
|
-
|
178
|
+
number = feats.get("Number", "")
|
179
|
+
gender_str = "-"+feats.get("Gender", "" if lang != "fr" else ("" if number == "Plur" else "Masc")).replace(",", "")
|
180
|
+
|
181
|
+
number_psor = feats.get("Number[psor]", "")[:1]
|
182
|
+
person_psor = feats.get("Person[psor]", "")
|
183
|
+
psor = number_psor+person_psor
|
179
184
|
|
180
185
|
# clear defaults
|
181
186
|
if gender_str == "-Com,Neut" or gender_str == "-Com" or gender_str=="-": gender_str=""
|
182
187
|
|
183
188
|
# parse
|
184
189
|
return (handler(word, lang)+gender_str+"-"+
|
185
|
-
feats.get("Definite", "Def") + stringify_feats(
|
190
|
+
feats.get("Definite", "Def") + stringify_feats(
|
191
|
+
feats.get("PronType", ""), number, psor))
|
186
192
|
|
187
193
|
def handler__ADJ(word, lang=None):
|
188
194
|
# get the features
|
@@ -258,6 +264,8 @@ def handler__VERB(word, lang=None):
|
|
258
264
|
res = handler(word, lang)
|
259
265
|
if "sconj" in res:
|
260
266
|
return res
|
267
|
+
elif word.text == "ろ":
|
268
|
+
return res
|
261
269
|
elif "verb" not in res and "aux" not in res:
|
262
270
|
if word.text == "たり":
|
263
271
|
return res+stringify_feats("Inf", "S")
|
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-0.7.6a28 → batchalign-0.7.6a30}/batchalign/pipelines/cleanup/support/filled_pauses.eng
RENAMED
File without changes
|
{batchalign-0.7.6a28 → batchalign-0.7.6a30}/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
|
{batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/formats/chat/test_chat_generator.py
RENAMED
File without changes
|
{batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/formats/chat/test_chat_lexer.py
RENAMED
File without changes
|
{batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/formats/chat/test_chat_parser.py
RENAMED
File without changes
|
{batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/formats/chat/test_chat_utils.py
RENAMED
File without changes
|
{batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/formats/textgrid/test_textgrid.py
RENAMED
File without changes
|
{batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/analysis/test_eval.py
RENAMED
File without changes
|
{batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/asr/test_asr_pipeline.py
RENAMED
File without changes
|
{batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/asr/test_asr_utils.py
RENAMED
File without changes
|
{batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/cleanup/test_disfluency.py
RENAMED
File without changes
|
{batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/cleanup/test_parse_support.py
RENAMED
File without changes
|
{batchalign-0.7.6a28 → batchalign-0.7.6a30}/batchalign/tests/pipelines/fa/test_fa_pipeline.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.6a28 → batchalign-0.7.6a30}/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
|