batchalign 0.7.3b4__tar.gz → 0.7.3b6__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-0.7.3b4/batchalign.egg-info → batchalign-0.7.3b6}/PKG-INFO +1 -1
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/document.py +7 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/asr/utils.py +1 -0
- batchalign-0.7.3b6/batchalign/version +3 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6/batchalign.egg-info}/PKG-INFO +1 -1
- batchalign-0.7.3b4/batchalign/version +0 -3
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/LICENSE +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/MANIFEST.in +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/README.md +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/__main__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/cli/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/cli/cli.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/cli/dispatch.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/constants.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/errors.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/formats/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/formats/base.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/formats/chat/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/formats/chat/file.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/formats/chat/generator.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/formats/chat/lexer.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/formats/chat/parser.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/formats/chat/utils.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/formats/textgrid/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/formats/textgrid/file.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/formats/textgrid/generator.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/formats/textgrid/parser.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/resolve.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/speaker/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/speaker/config.yaml +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/speaker/infer.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/speaker/utils.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/training/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/training/run.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/training/utils.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/utils.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/utterance/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/utterance/dataset.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/utterance/execute.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/utterance/infer.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/utterance/prep.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/utterance/train.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/whisper/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/whisper/infer_asr.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/models/whisper/infer_fa.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/analysis/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/analysis/eval.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/asr/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/asr/rev.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/asr/whisper.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/asr/whisperx.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/base.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/cleanup/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/cleanup/cleanup.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/cleanup/disfluencies.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/cleanup/parse_support.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/cleanup/retrace.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/cleanup/support/filled_pauses.eng +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/cleanup/support/replacements.eng +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/cleanup/support/test.test +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/dispatch.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/fa/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/fa/whisper_fa.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/morphosyntax/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/morphosyntax/fr/case.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/morphosyntax/ud.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/pipeline.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/speaker/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/speaker/nemo_speaker.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/utr/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/utr/rev_utr.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/utr/utils.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/utr/whisper_utr.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/utterance/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/utterance/ud_utterance.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/conftest.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/formats/chat/test_chat_file.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/formats/chat/test_chat_generator.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/formats/chat/test_chat_lexer.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/formats/chat/test_chat_parser.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/formats/chat/test_chat_utils.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/formats/textgrid/test_textgrid.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/pipelines/analysis/test_eval.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/pipelines/asr/test_asr_pipeline.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/pipelines/asr/test_asr_utils.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/pipelines/cleanup/test_disfluency.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/pipelines/cleanup/test_parse_support.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/pipelines/fa/test_fa_pipeline.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/pipelines/fixures.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/pipelines/test_pipeline.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/pipelines/test_pipeline_models.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/test_document.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/utils/__init__.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/utils/config.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/utils/dp.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/utils/utils.py +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign.egg-info/SOURCES.txt +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign.egg-info/dependency_links.txt +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign.egg-info/entry_points.txt +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign.egg-info/requires.txt +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign.egg-info/top_level.txt +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/setup.cfg +0 -0
- {batchalign-0.7.3b4 → batchalign-0.7.3b6}/setup.py +0 -0
@@ -263,6 +263,13 @@ class Utterance(BaseModel):
|
|
263
263
|
if last_tok in ENDING_PUNCT + MOR_PUNCT:
|
264
264
|
detokenized = detokenized.replace(last_tok, f" {last_tok}")
|
265
265
|
detokenized = detokenized.replace(" ", " ")
|
266
|
+
detokenized = re.sub(r",(\w)", r", \1", detokenized)
|
267
|
+
detokenized = re.sub(r",.", r",", detokenized)
|
268
|
+
detokenized = re.sub(r".,", r",", detokenized)
|
269
|
+
detokenized = re.sub(r"\? !", r"!", detokenized)
|
270
|
+
detokenized = re.sub(r"! \?", r"?", detokenized)
|
271
|
+
detokenized = detokenized.encode().replace(b"\xef\xbf\xbd", b"").decode("utf-8")
|
272
|
+
detokenized = detokenized.encode().replace(b"\xe2\x80\xab", b"").decode("utf-8")
|
266
273
|
|
267
274
|
## TODO deal with angle brackets for retraces
|
268
275
|
# NOTE: we don't use detokenize here to put spaces
|
@@ -75,6 +75,7 @@ def retokenize_with_engine(intermediate_output, engine):
|
|
75
75
|
utterance = [i for i in utterance if i[0].strip() != ""]
|
76
76
|
|
77
77
|
joined = " ".join([i[0] for i in utterance])
|
78
|
+
joined = joined.replace("。", ".")
|
78
79
|
split = engine(joined)
|
79
80
|
|
80
81
|
# align the utterance against original splits and generate final outputs
|
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-0.7.3b4 → batchalign-0.7.3b6}/batchalign/pipelines/cleanup/support/filled_pauses.eng
RENAMED
File without changes
|
{batchalign-0.7.3b4 → batchalign-0.7.3b6}/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-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/formats/chat/test_chat_generator.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/formats/textgrid/test_textgrid.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/pipelines/asr/test_asr_pipeline.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/pipelines/cleanup/test_disfluency.py
RENAMED
File without changes
|
{batchalign-0.7.3b4 → batchalign-0.7.3b6}/batchalign/tests/pipelines/cleanup/test_parse_support.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.3b4 → batchalign-0.7.3b6}/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
|