[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

MANIFEST.in

@@ -1,2 +1 @@
 include ctc_segmentation/ctc_segmentation_dyn.pyx
-

Makefile

@@ -11,7 +11,7 @@ clean:
 
 upload:
 	twine upload dist/*
-  
+
 test:
 	cd tests; python -c "import test_ctc_segmentation as test; test.test_ctc_segmentation()"
 	cd tests; python -c "import test_ctc_segmentation as test; test.test_determine_utterance_segments()"
@@ -23,7 +23,7 @@ test:
 # To test the various installation methods:
 github:
 	cd /; pip install git+https://github.com/lumaku/ctc-segmentation --user
-	
+
 pip:
 	cd /; pip install ctc-segmentation --user
 
@@ -32,4 +32,3 @@ local:
 
 rm:
 	cd /; pip uninstall -y ctc-segmentation
-

README.md

@@ -59,29 +59,29 @@ def align_with_transcript(
     with torch.no_grad():
         logits = model(inputs.input_values).logits.cpu()[0]
         probs = torch.nn.functional.softmax(logits,dim=-1)
-    
+
     # Tokenize transcripts
     vocab = tokenizer.get_vocab()
     inv_vocab = {v:k for k,v in vocab.items()}
     unk_id = vocab["<unk>"]
-    
+
     tokens = []
     for transcript in transcripts:
         assert len(transcript) > 0
         tok_ids = tokenizer(transcript.replace("\n"," ").lower())['input_ids']
         tok_ids = np.array(tok_ids,dtype=np.int)
         tokens.append(tok_ids[tok_ids != unk_id])
-    
+
     # Align
     char_list = [inv_vocab[i] for i in range(len(inv_vocab))]
     config = ctc_segmentation.CtcSegmentationParameters(char_list=char_list)
     config.index_duration = audio.shape[0] / probs.size()[0] / samplerate
-    
+
     ground_truth_mat, utt_begin_indices = ctc_segmentation.prepare_token_list(config, tokens)
     timings, char_probs, state_list = ctc_segmentation.ctc_segmentation(config, probs.numpy(), ground_truth_mat)
     segments = ctc_segmentation.determine_utterance_segments(config, utt_begin_indices, char_probs, timings, transcripts)
     return [{"text" : t, "start" : p[0], "end" : p[1], "conf" : p[2]} for t,p in zip(transcripts, segments)]
-    
+
 def get_word_timestamps(
     audio : np.ndarray,
     samplerate : int = SAMPLERATE,
@@ -95,38 +95,38 @@ def get_word_timestamps(
     with torch.no_grad():
         logits = model(inputs.input_values).logits.cpu()[0]
         probs = torch.nn.functional.softmax(logits,dim=-1)
-        
+
     predicted_ids = torch.argmax(logits, dim=-1)
     pred_transcript = processor.decode(predicted_ids)
-    
+
     # Split the transcription into words
     words = pred_transcript.split(" ")
-    
+
     # Align
     vocab = tokenizer.get_vocab()
     inv_vocab = {v:k for k,v in vocab.items()}
     char_list = [inv_vocab[i] for i in range(len(inv_vocab))]
     config = ctc_segmentation.CtcSegmentationParameters(char_list=char_list)
     config.index_duration = audio.shape[0] / probs.size()[0] / samplerate
-    
+
     ground_truth_mat, utt_begin_indices = ctc_segmentation.prepare_text(config, words)
     timings, char_probs, state_list = ctc_segmentation.ctc_segmentation(config, probs.numpy(), ground_truth_mat)
     segments = ctc_segmentation.determine_utterance_segments(config, utt_begin_indices, char_probs, timings, words)
     return [{"text" : w, "start" : p[0], "end" : p[1], "conf" : p[2]} for w,p in zip(words, segments)]
 
 print(align_with_transcript(audio,transcripts))
-# [{'text': 'A MAN SAID TO THE UNIVERSE', 'start': 0.08124999999999993, 'end': 2.034375, 'conf': 0.0}, 
+# [{'text': 'A MAN SAID TO THE UNIVERSE', 'start': 0.08124999999999993, 'end': 2.034375, 'conf': 0.0},
 #  {'text': 'SIR I EXIST', 'start': 2.3260775862068965, 'end': 4.078771551724138, 'conf': 0.0}]
 
 print(get_word_timestamps(audio))
-# [{'text': 'a', 'start': 0.08124999999999993, 'end': 0.5912715517241378, 'conf': 0.9999501323699951}, 
-# {'text': 'man', 'start': 0.5912715517241378, 'end': 0.9219827586206896, 'conf': 0.9409108982174931}, 
-# {'text': 'said', 'start': 0.9219827586206896, 'end': 1.2326508620689656, 'conf': 0.7700278702302796}, 
-# {'text': 'to', 'start': 1.2326508620689656, 'end': 1.3529094827586206, 'conf': 0.5094435178226225}, 
-# {'text': 'the', 'start': 1.3529094827586206, 'end': 1.4831896551724135, 'conf': 0.4580493446392211}, 
-# {'text': 'universe', 'start': 1.4831896551724135, 'end': 2.034375, 'conf': 0.9285054256219009}, 
-# {'text': 'sir', 'start': 2.3260775862068965, 'end': 3.036530172413793, 'conf': 0.0}, 
-# {'text': 'i', 'start': 3.036530172413793, 'end': 3.347198275862069, 'conf': 0.7995760873559864}, 
+# [{'text': 'a', 'start': 0.08124999999999993, 'end': 0.5912715517241378, 'conf': 0.9999501323699951},
+# {'text': 'man', 'start': 0.5912715517241378, 'end': 0.9219827586206896, 'conf': 0.9409108982174931},
+# {'text': 'said', 'start': 0.9219827586206896, 'end': 1.2326508620689656, 'conf': 0.7700278702302796},
+# {'text': 'to', 'start': 1.2326508620689656, 'end': 1.3529094827586206, 'conf': 0.5094435178226225},
+# {'text': 'the', 'start': 1.3529094827586206, 'end': 1.4831896551724135, 'conf': 0.4580493446392211},
+# {'text': 'universe', 'start': 1.4831896551724135, 'end': 2.034375, 'conf': 0.9285054256219009},
+# {'text': 'sir', 'start': 2.3260775862068965, 'end': 3.036530172413793, 'conf': 0.0},
+# {'text': 'i', 'start': 3.036530172413793, 'end': 3.347198275862069, 'conf': 0.7995760873559864},
 # {'text': 'exist', 'start': 3.347198275862069, 'end': 4.078771551724138, 'conf': 0.0}]
 ```
 
@@ -229,7 +229,7 @@ For examples, see the `prepare_*` functions in `ctc_segmentation.py`, or the exa
 
 ### Segments clean-up
 
-Segments that were written to a `segments` file can be filtered using the confidence score. This is the minium confidence score in log space as described in the paper. 
+Segments that were written to a `segments` file can be filtered using the confidence score. This is the minium confidence score in log space as described in the paper.
 
 Utterances with a low confidence score are discarded in a data clean-up. This parameter may need adjustment depending on dataset, ASR model and used text conversion.
 

ctc_segmentation/__init__.py

@@ -1,8 +1,6 @@
 """Import all functions of the CTC segmentation package."""
-from .ctc_segmentation import ctc_segmentation
-from .ctc_segmentation import CtcSegmentationParameters
-from .ctc_segmentation import determine_utterance_segments
-from .ctc_segmentation import prepare_text
-from .ctc_segmentation import prepare_tokenized_text
-from .ctc_segmentation import prepare_token_list
+
+from .ctc_segmentation import (CtcSegmentationParameters, ctc_segmentation,
+                               determine_utterance_segments, prepare_text,
+                               prepare_token_list, prepare_tokenized_text)
 from .partitioning import get_partitions

ctc_segmentation/ctc_segmentation.py

@@ -18,6 +18,7 @@
 """
 
 import logging
+
 import numpy as np
 
 logger = logging.getLogger("ctc_segmentation")

ctc_segmentation/ctc_segmentation_dyn.pyx

@@ -13,7 +13,9 @@ For a description, see https://arxiv.org/abs/2007.09127
 """
 
 import logging
+
 import numpy as np
+
 cimport numpy as np
 
 

setup.py

@@ -1,25 +1,26 @@
-from setuptools import setup, find_packages, Extension
-from setuptools.command.build_ext import build_ext
 import numpy
-
+from setuptools import Extension, find_packages, setup
+from setuptools.command.build_ext import build_ext
 
 try:
     from Cython.Build import cythonize
+
     USE_CYTHON = True
 except ImportError:
     USE_CYTHON = False
 
 # https://cython.readthedocs.io/en/latest/src/userguide/source_files_and_compilation.html
-ext = '.pyx' if USE_CYTHON else '.c'
+ext = ".pyx" if USE_CYTHON else ".c"
 extensions = [
     Extension(
         name="ctc_segmentation.ctc_segmentation_dyn",
-        sources=["ctc_segmentation/ctc_segmentation_dyn"+ext],
+        sources=["ctc_segmentation/ctc_segmentation_dyn" + ext],
         include_dirs=[numpy.get_include()],
     )
 ]
 if USE_CYTHON:
     from Cython.Build import cythonize
+
     extensions = cythonize(extensions)
 
 package_information = """
@@ -35,22 +36,18 @@
 setup(
     name="ctc_segmentation",
     version="1.7.5",
-
-    python_requires='>=3.9',
+    python_requires=">=3.9",
     packages=find_packages(exclude=["tests"]),
     setup_requires=["numpy"],
     install_requires=["setuptools", "numpy", "Cython"],
     tests_require=["pytest", "torch"],
     zip_safe=False,
     ext_modules=extensions,
-    cmdclass={'build_ext': build_ext},
-
+    cmdclass={"build_ext": build_ext},
     author="Ludwig Kuerzinger <ludwig.kuerzinger@tum.de>, "
-           "Dominik Winkelbauer <dominik.winkelbauer@tum.de>",
-    description="CTC segmentation to align utterances within "
-                "large audio files.",
+    "Dominik Winkelbauer <dominik.winkelbauer@tum.de>",
+    description="CTC segmentation to align utterances within " "large audio files.",
     url="https://github.com/espnet/ctc-segmentation",
-
     long_description_content_type="text/markdown",
     long_description=package_information,
 )

tests/test_ctc_segmentation.py

@@ -7,12 +7,9 @@
 """Test functions for CTC segmentation."""
 import numpy as np
 
-from ctc_segmentation import ctc_segmentation
-from ctc_segmentation import CtcSegmentationParameters
-from ctc_segmentation import determine_utterance_segments
-from ctc_segmentation import prepare_text
-from ctc_segmentation import prepare_tokenized_text
-from ctc_segmentation import prepare_token_list
+from ctc_segmentation import (CtcSegmentationParameters, ctc_segmentation,
+                              determine_utterance_segments, prepare_text,
+                              prepare_token_list, prepare_tokenized_text)
 
 
 def test_ctcsegmentationparameters():