batchalign 0.7.19.post1__tar.gz → 0.7.19.post4__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.
Potentially problematic release.
This version of batchalign might be problematic. Click here for more details.
- {batchalign-0.7.19.post1/batchalign.egg-info → batchalign-0.7.19.post4}/PKG-INFO +2 -2
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/formats/chat/generator.py +1 -1
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/analysis/eval.py +15 -0
- batchalign-0.7.19.post4/batchalign/utils/names.py +6684 -0
- batchalign-0.7.19.post4/batchalign/version +3 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4/batchalign.egg-info}/PKG-INFO +2 -2
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign.egg-info/SOURCES.txt +1 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign.egg-info/requires.txt +1 -1
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/setup.py +1 -1
- batchalign-0.7.19.post1/batchalign/version +0 -3
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/LICENSE +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/MANIFEST.in +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/README.md +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/__main__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/cli/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/cli/cli.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/cli/dispatch.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/constants.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/document.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/errors.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/formats/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/formats/base.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/formats/chat/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/formats/chat/file.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/formats/chat/lexer.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/formats/chat/parser.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/formats/chat/utils.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/formats/textgrid/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/formats/textgrid/file.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/formats/textgrid/generator.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/formats/textgrid/parser.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/resolve.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/speaker/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/speaker/config.yaml +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/speaker/infer.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/speaker/utils.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/training/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/training/run.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/training/utils.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/utils.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/utterance/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/utterance/cantonese_infer.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/utterance/dataset.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/utterance/execute.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/utterance/infer.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/utterance/prep.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/utterance/train.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/wave2vec/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/wave2vec/infer_fa.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/whisper/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/whisper/infer_asr.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/models/whisper/infer_fa.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/analysis/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/asr/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/asr/num2chinese.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/asr/oai_whisper.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/asr/rev.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/asr/utils.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/asr/whisper.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/asr/whisperx.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/base.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/cleanup/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/cleanup/cleanup.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/cleanup/disfluencies.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/cleanup/parse_support.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/cleanup/retrace.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/cleanup/support/filled_pauses.eng +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/cleanup/support/replacements.eng +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/cleanup/support/test.test +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/dispatch.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/fa/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/fa/wave2vec_fa.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/fa/whisper_fa.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/morphosyntax/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/morphosyntax/coref.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/morphosyntax/en/irr.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/morphosyntax/fr/apm.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/morphosyntax/fr/apmn.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/morphosyntax/fr/case.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/morphosyntax/ja/verbforms.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/morphosyntax/ud.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/pipeline.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/speaker/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/speaker/nemo_speaker.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/translate/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/translate/gtrans.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/translate/seamless.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/translate/utils.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/utr/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/utr/rev_utr.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/utr/utils.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/utr/whisper_utr.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/utterance/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/pipelines/utterance/ud_utterance.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/conftest.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/formats/chat/test_chat_file.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/formats/chat/test_chat_generator.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/formats/chat/test_chat_lexer.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/formats/chat/test_chat_parser.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/formats/chat/test_chat_utils.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/formats/textgrid/test_textgrid.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/pipelines/analysis/test_eval.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/pipelines/asr/test_asr_pipeline.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/pipelines/asr/test_asr_utils.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/pipelines/cleanup/test_disfluency.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/pipelines/cleanup/test_parse_support.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/pipelines/fa/test_fa_pipeline.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/pipelines/fixures.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/pipelines/test_pipeline.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/pipelines/test_pipeline_models.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/tests/test_document.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/utils/__init__.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/utils/config.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/utils/dp.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign/utils/utils.py +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign.egg-info/dependency_links.txt +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign.egg-info/entry_points.txt +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/batchalign.egg-info/top_level.txt +0 -0
- {batchalign-0.7.19.post1 → batchalign-0.7.19.post4}/setup.cfg +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.2
|
|
2
2
|
Name: batchalign
|
|
3
|
-
Version: 0.7.19.
|
|
3
|
+
Version: 0.7.19.post4
|
|
4
4
|
Summary: Python Speech Language Sample Analysis
|
|
5
5
|
Author: Brian MacWhinney, Houjun Liu
|
|
6
6
|
Author-email: macw@cmu.edu, houjun@cmu.edu
|
|
@@ -25,7 +25,7 @@ Requires-Dist: rich~=13.6
|
|
|
25
25
|
Requires-Dist: click~=8.1
|
|
26
26
|
Requires-Dist: matplotlib<4.0.0,>=3.8.0
|
|
27
27
|
Requires-Dist: pyfiglet==1.0.2
|
|
28
|
-
Requires-Dist: setuptools
|
|
28
|
+
Requires-Dist: setuptools>=78.1.1
|
|
29
29
|
Requires-Dist: soundfile~=0.12.0
|
|
30
30
|
Requires-Dist: rich-click>=1.7.0
|
|
31
31
|
Requires-Dist: typing-extensions
|
|
@@ -101,7 +101,7 @@ def generate_chat_utterance(utterance: Utterance, special_mor=False, write_wor=T
|
|
|
101
101
|
result.append("%wor:\t"+" ".join(wor_elems))
|
|
102
102
|
if has_coref:
|
|
103
103
|
result.append("%coref:\t"+(", ".join(coref_elems)))
|
|
104
|
-
if utterance.translation != None:
|
|
104
|
+
if utterance.translation != None and utterance.translation.strip() not in ["", ".", "!", "?"]:
|
|
105
105
|
result.append("%xtra:\t"+utterance.translation)
|
|
106
106
|
|
|
107
107
|
|
|
@@ -10,6 +10,7 @@ from batchalign.pipelines.asr.utils import *
|
|
|
10
10
|
from batchalign.utils.config import config_read
|
|
11
11
|
|
|
12
12
|
from batchalign.utils.dp import align, ExtraType, Extra, Match
|
|
13
|
+
from batchalign.utils.names import names
|
|
13
14
|
|
|
14
15
|
import logging
|
|
15
16
|
L = logging.getLogger("batchalign")
|
|
@@ -26,6 +27,20 @@ def conform(x):
|
|
|
26
27
|
elif "postwar" == i.strip():
|
|
27
28
|
result.append("post")
|
|
28
29
|
result.append("war")
|
|
30
|
+
elif "postwar" == i.strip():
|
|
31
|
+
result.append("post")
|
|
32
|
+
result.append("war")
|
|
33
|
+
elif i.strip() in names:
|
|
34
|
+
result.append("name")
|
|
35
|
+
elif "dunno" == i.strip():
|
|
36
|
+
result.append("don't")
|
|
37
|
+
result.append("know")
|
|
38
|
+
elif "wanna" == i.strip():
|
|
39
|
+
result.append("want")
|
|
40
|
+
result.append("to")
|
|
41
|
+
elif "gotta" == i.strip():
|
|
42
|
+
result.append("got")
|
|
43
|
+
result.append("to")
|
|
29
44
|
elif "farmhouse" == i.strip():
|
|
30
45
|
result.append("farm")
|
|
31
46
|
result.append("house")
|