batchalign 0.7.17.post7__tar.gz → 0.7.17.post8__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-0.7.17.post7/batchalign.egg-info → batchalign-0.7.17.post8}/PKG-INFO +1 -1
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/fa/wave2vec_fa.py +3 -2
- batchalign-0.7.17.post8/batchalign/version +3 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8/batchalign.egg-info}/PKG-INFO +1 -1
- batchalign-0.7.17.post7/batchalign/version +0 -3
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/LICENSE +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/MANIFEST.in +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/README.md +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/__main__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/cli/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/cli/cli.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/cli/dispatch.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/constants.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/document.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/errors.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/formats/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/formats/base.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/formats/chat/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/formats/chat/file.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/formats/chat/generator.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/formats/chat/lexer.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/formats/chat/parser.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/formats/chat/utils.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/formats/textgrid/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/formats/textgrid/file.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/formats/textgrid/generator.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/formats/textgrid/parser.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/resolve.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/speaker/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/speaker/config.yaml +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/speaker/infer.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/speaker/utils.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/training/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/training/run.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/training/utils.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/utils.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/utterance/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/utterance/cantonese_infer.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/utterance/dataset.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/utterance/execute.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/utterance/infer.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/utterance/prep.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/utterance/train.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/wave2vec/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/wave2vec/infer_fa.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/whisper/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/whisper/infer_asr.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/whisper/infer_fa.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/analysis/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/analysis/eval.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/asr/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/asr/num2chinese.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/asr/rev.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/asr/utils.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/asr/whisper.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/asr/whisperx.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/base.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/cleanup/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/cleanup/cleanup.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/cleanup/disfluencies.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/cleanup/parse_support.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/cleanup/retrace.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/cleanup/support/filled_pauses.eng +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/cleanup/support/replacements.eng +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/cleanup/support/test.test +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/dispatch.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/fa/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/fa/whisper_fa.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/morphosyntax/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/morphosyntax/coref.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/morphosyntax/en/irr.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/morphosyntax/fr/apm.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/morphosyntax/fr/apmn.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/morphosyntax/fr/case.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/morphosyntax/ja/verbforms.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/morphosyntax/ud.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/pipeline.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/speaker/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/speaker/nemo_speaker.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/translate/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/translate/seamless.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/utr/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/utr/rev_utr.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/utr/utils.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/utr/whisper_utr.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/utterance/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/utterance/ud_utterance.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/conftest.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/formats/chat/test_chat_file.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/formats/chat/test_chat_generator.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/formats/chat/test_chat_lexer.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/formats/chat/test_chat_parser.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/formats/chat/test_chat_utils.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/formats/textgrid/test_textgrid.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/pipelines/analysis/test_eval.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/pipelines/asr/test_asr_pipeline.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/pipelines/asr/test_asr_utils.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/pipelines/cleanup/test_disfluency.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/pipelines/cleanup/test_parse_support.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/pipelines/fa/test_fa_pipeline.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/pipelines/fixures.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/pipelines/test_pipeline.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/pipelines/test_pipeline_models.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/test_document.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/utils/__init__.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/utils/config.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/utils/dp.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/utils/utils.py +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign.egg-info/SOURCES.txt +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign.egg-info/dependency_links.txt +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign.egg-info/entry_points.txt +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign.egg-info/requires.txt +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign.egg-info/top_level.txt +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/setup.cfg +0 -0
- {batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/setup.py +0 -0
@@ -51,7 +51,7 @@ class Wave2VecFAEngine(BatchalignEngine):
|
|
51
51
|
continue
|
52
52
|
|
53
53
|
# pop the previous group onto the stack
|
54
|
-
if (i.alignment[-1] - seg_start) >
|
54
|
+
if (i.alignment[-1] - seg_start) > 15*1000:
|
55
55
|
groups.append(group)
|
56
56
|
group = []
|
57
57
|
seg_start = i.alignment[0]
|
@@ -78,7 +78,8 @@ class Wave2VecFAEngine(BatchalignEngine):
|
|
78
78
|
transcript = [i.replace("_", " ") for i in transcript if i.strip() != p]
|
79
79
|
# if "noone's" in detokenized:
|
80
80
|
# breakpoint()
|
81
|
-
|
81
|
+
if (grp[-1][1][1] - grp[0][1][0]) < 20*1000:
|
82
|
+
res = self.__wav2vec(audio=f.chunk(grp[0][1][0], grp[-1][1][1]), text=transcript)
|
82
83
|
except (IndexError, RuntimeError) as e:
|
83
84
|
# utterance contains nothing
|
84
85
|
continue
|
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-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/formats/textgrid/generator.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-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/models/utterance/cantonese_infer.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
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/analysis/__init__.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
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/cleanup/__init__.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/cleanup/disfluencies.py
RENAMED
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/cleanup/parse_support.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/cleanup/support/test.test
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/morphosyntax/__init__.py
RENAMED
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/morphosyntax/coref.py
RENAMED
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/morphosyntax/en/irr.py
RENAMED
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/morphosyntax/fr/apm.py
RENAMED
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/morphosyntax/fr/apmn.py
RENAMED
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/morphosyntax/fr/case.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/speaker/__init__.py
RENAMED
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/speaker/nemo_speaker.py
RENAMED
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/translate/__init__.py
RENAMED
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/translate/seamless.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/utterance/__init__.py
RENAMED
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/pipelines/utterance/ud_utterance.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/formats/chat/test_chat_file.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/formats/chat/test_chat_lexer.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/formats/chat/test_chat_utils.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/pipelines/analysis/test_eval.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/pipelines/asr/test_asr_utils.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign/tests/pipelines/test_pipeline.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
|
{batchalign-0.7.17.post7 → batchalign-0.7.17.post8}/batchalign.egg-info/dependency_links.txt
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|