batchalign 0.7.17.post4__tar.gz → 0.7.17.post5__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.post4/batchalign.egg-info → batchalign-0.7.17.post5}/PKG-INFO +1 -1
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/asr/utils.py +7 -4
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/asr/whisper.py +4 -1
- batchalign-0.7.17.post5/batchalign/version +3 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5/batchalign.egg-info}/PKG-INFO +1 -1
- batchalign-0.7.17.post4/batchalign/version +0 -3
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/LICENSE +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/MANIFEST.in +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/README.md +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/__main__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/cli/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/cli/cli.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/cli/dispatch.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/constants.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/document.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/errors.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/formats/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/formats/base.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/formats/chat/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/formats/chat/file.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/formats/chat/generator.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/formats/chat/lexer.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/formats/chat/parser.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/formats/chat/utils.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/formats/textgrid/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/formats/textgrid/file.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/formats/textgrid/generator.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/formats/textgrid/parser.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/resolve.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/speaker/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/speaker/config.yaml +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/speaker/infer.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/speaker/utils.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/training/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/training/run.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/training/utils.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/utils.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/utterance/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/utterance/cantonese_infer.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/utterance/dataset.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/utterance/execute.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/utterance/infer.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/utterance/prep.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/utterance/train.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/wave2vec/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/wave2vec/infer_fa.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/whisper/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/whisper/infer_asr.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/models/whisper/infer_fa.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/analysis/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/analysis/eval.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/asr/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/asr/num2chinese.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/asr/rev.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/asr/whisperx.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/base.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/cleanup/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/cleanup/cleanup.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/cleanup/disfluencies.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/cleanup/parse_support.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/cleanup/retrace.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/cleanup/support/filled_pauses.eng +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/cleanup/support/replacements.eng +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/cleanup/support/test.test +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/dispatch.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/fa/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/fa/wave2vec_fa.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/fa/whisper_fa.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/morphosyntax/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/morphosyntax/coref.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/morphosyntax/en/irr.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/morphosyntax/fr/apm.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/morphosyntax/fr/apmn.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/morphosyntax/fr/case.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/morphosyntax/ja/verbforms.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/morphosyntax/ud.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/pipeline.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/speaker/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/speaker/nemo_speaker.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/translate/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/translate/seamless.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/utr/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/utr/rev_utr.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/utr/utils.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/utr/whisper_utr.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/utterance/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/utterance/ud_utterance.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/conftest.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/formats/chat/test_chat_file.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/formats/chat/test_chat_generator.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/formats/chat/test_chat_lexer.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/formats/chat/test_chat_parser.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/formats/chat/test_chat_utils.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/formats/textgrid/test_textgrid.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/pipelines/analysis/test_eval.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/pipelines/asr/test_asr_pipeline.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/pipelines/asr/test_asr_utils.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/pipelines/cleanup/test_disfluency.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/pipelines/cleanup/test_parse_support.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/pipelines/fa/test_fa_pipeline.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/pipelines/fixures.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/pipelines/test_pipeline.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/pipelines/test_pipeline_models.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/test_document.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/utils/__init__.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/utils/config.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/utils/dp.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/utils/utils.py +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign.egg-info/SOURCES.txt +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign.egg-info/dependency_links.txt +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign.egg-info/entry_points.txt +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign.egg-info/requires.txt +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign.egg-info/top_level.txt +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/setup.cfg +0 -0
- {batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/setup.py +0 -0
@@ -98,10 +98,13 @@ def retokenize_with_engine(intermediate_output, engine):
|
|
98
98
|
tmp = []
|
99
99
|
|
100
100
|
for s in new_ut:
|
101
|
-
|
102
|
-
|
103
|
-
|
104
|
-
|
101
|
+
if current_index < len(utterance):
|
102
|
+
# Use current element and move index forward
|
103
|
+
tmp.append((s, utterance[current_index][1]))
|
104
|
+
current_index += 1
|
105
|
+
else:
|
106
|
+
# Append with default timestamp if utterance is exhausted
|
107
|
+
tmp.append((s, [None, None]))
|
105
108
|
|
106
109
|
final_outputs.append((speaker, tmp+[[delim, [None, None]]]))
|
107
110
|
|
@@ -33,7 +33,10 @@ class WhisperEngine(BatchalignEngine):
|
|
33
33
|
model = "openai/whisper-large-v3"
|
34
34
|
base = "openai/whisper-large-v3"
|
35
35
|
|
36
|
-
|
36
|
+
if lang == "mys":
|
37
|
+
language = "Malay"
|
38
|
+
else:
|
39
|
+
language = pycountry.languages.get(alpha_3=lang).name
|
37
40
|
if language == "Yue Chinese":
|
38
41
|
language = "Cantonese"
|
39
42
|
if "greek" in language.lower():
|
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.post4 → batchalign-0.7.17.post5}/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.post4 → batchalign-0.7.17.post5}/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.post4 → batchalign-0.7.17.post5}/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
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/cleanup/__init__.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/cleanup/disfluencies.py
RENAMED
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/cleanup/parse_support.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/cleanup/support/test.test
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/morphosyntax/__init__.py
RENAMED
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/morphosyntax/coref.py
RENAMED
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/morphosyntax/en/irr.py
RENAMED
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/morphosyntax/fr/apm.py
RENAMED
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/morphosyntax/fr/apmn.py
RENAMED
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/morphosyntax/fr/case.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/speaker/__init__.py
RENAMED
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/speaker/nemo_speaker.py
RENAMED
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/translate/__init__.py
RENAMED
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/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.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/utterance/__init__.py
RENAMED
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/pipelines/utterance/ud_utterance.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/formats/chat/test_chat_file.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/formats/chat/test_chat_lexer.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/formats/chat/test_chat_utils.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/batchalign/tests/pipelines/analysis/test_eval.py
RENAMED
File without changes
|
File without changes
|
{batchalign-0.7.17.post4 → batchalign-0.7.17.post5}/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.post4 → batchalign-0.7.17.post5}/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.post4 → batchalign-0.7.17.post5}/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
|