batchalign 0.7.3b5__tar.gz → 0.7.3b7__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-0.7.3b5/batchalign.egg-info → batchalign-0.7.3b7}/PKG-INFO +1 -1
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/document.py +3 -0
- batchalign-0.7.3b7/batchalign/version +3 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7/batchalign.egg-info}/PKG-INFO +1 -1
- batchalign-0.7.3b5/batchalign/version +0 -3
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/LICENSE +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/MANIFEST.in +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/README.md +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/__main__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/cli/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/cli/cli.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/cli/dispatch.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/constants.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/errors.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/formats/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/formats/base.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/formats/chat/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/formats/chat/file.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/formats/chat/generator.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/formats/chat/lexer.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/formats/chat/parser.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/formats/chat/utils.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/formats/textgrid/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/formats/textgrid/file.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/formats/textgrid/generator.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/formats/textgrid/parser.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/resolve.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/speaker/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/speaker/config.yaml +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/speaker/infer.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/speaker/utils.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/training/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/training/run.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/training/utils.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/utils.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/utterance/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/utterance/dataset.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/utterance/execute.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/utterance/infer.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/utterance/prep.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/utterance/train.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/whisper/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/whisper/infer_asr.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/models/whisper/infer_fa.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/analysis/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/analysis/eval.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/asr/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/asr/rev.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/asr/utils.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/asr/whisper.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/asr/whisperx.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/base.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/cleanup/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/cleanup/cleanup.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/cleanup/disfluencies.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/cleanup/parse_support.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/cleanup/retrace.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/cleanup/support/filled_pauses.eng +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/cleanup/support/replacements.eng +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/cleanup/support/test.test +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/dispatch.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/fa/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/fa/whisper_fa.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/morphosyntax/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/morphosyntax/fr/case.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/morphosyntax/ud.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/pipeline.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/speaker/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/speaker/nemo_speaker.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/utr/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/utr/rev_utr.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/utr/utils.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/utr/whisper_utr.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/utterance/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/utterance/ud_utterance.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/conftest.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/formats/chat/test_chat_file.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/formats/chat/test_chat_generator.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/formats/chat/test_chat_lexer.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/formats/chat/test_chat_parser.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/formats/chat/test_chat_utils.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/formats/textgrid/test_textgrid.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/pipelines/analysis/test_eval.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/pipelines/asr/test_asr_pipeline.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/pipelines/asr/test_asr_utils.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/pipelines/cleanup/test_disfluency.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/pipelines/cleanup/test_parse_support.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/pipelines/fa/test_fa_pipeline.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/pipelines/fixures.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/pipelines/test_pipeline.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/pipelines/test_pipeline_models.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/test_document.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/utils/__init__.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/utils/config.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/utils/dp.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/utils/utils.py +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign.egg-info/SOURCES.txt +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign.egg-info/dependency_links.txt +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign.egg-info/entry_points.txt +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign.egg-info/requires.txt +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign.egg-info/top_level.txt +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/setup.cfg +0 -0
- {batchalign-0.7.3b5 → batchalign-0.7.3b7}/setup.py +0 -0
@@ -198,6 +198,7 @@ class Utterance(BaseModel):
|
|
198
198
|
t = self._detokenize()
|
199
199
|
|
200
200
|
t = t.replace(". . .", "+...")
|
201
|
+
t = re.sub(r"^\+\.\.\.", "", t).strip()
|
201
202
|
return t
|
202
203
|
|
203
204
|
def __repr__(self):
|
@@ -268,6 +269,8 @@ class Utterance(BaseModel):
|
|
268
269
|
detokenized = re.sub(r".,", r",", detokenized)
|
269
270
|
detokenized = re.sub(r"\? !", r"!", detokenized)
|
270
271
|
detokenized = re.sub(r"! \?", r"?", detokenized)
|
272
|
+
detokenized = detokenized.encode().replace(b"\xef\xbf\xbd", b"").decode("utf-8")
|
273
|
+
detokenized = detokenized.encode().replace(b"\xe2\x80\xab", b"").decode("utf-8")
|
271
274
|
|
272
275
|
## TODO deal with angle brackets for retraces
|
273
276
|
# NOTE: we don't use detokenize here to put spaces
|
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-0.7.3b5 → batchalign-0.7.3b7}/batchalign/pipelines/cleanup/support/filled_pauses.eng
RENAMED
File without changes
|
{batchalign-0.7.3b5 → batchalign-0.7.3b7}/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
|
{batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/formats/chat/test_chat_generator.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/formats/textgrid/test_textgrid.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/pipelines/asr/test_asr_pipeline.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/pipelines/cleanup/test_disfluency.py
RENAMED
File without changes
|
{batchalign-0.7.3b5 → batchalign-0.7.3b7}/batchalign/tests/pipelines/cleanup/test_parse_support.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.3b5 → batchalign-0.7.3b7}/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
|