Re-run linter over files after update

bin/import_atthack.py

@@ -280,13 +280,13 @@ def get_sample_size(population_size):
     margin_of_error = 0.01
     fraction_picking = 0.50
     z_score = 2.58  # Corresponds to confidence level 99%
-    numerator = (z_score ** 2 * fraction_picking * (1 - fraction_picking)) / (
-        margin_of_error ** 2
+    numerator = (z_score**2 * fraction_picking * (1 - fraction_picking)) / (
+        margin_of_error**2
     )
     sample_size = 0
     for train_size in range(population_size, 0, -1):
-        denominator = 1 + (z_score ** 2 * fraction_picking * (1 - fraction_picking)) / (
-            margin_of_error ** 2 * train_size
+        denominator = 1 + (z_score**2 * fraction_picking * (1 - fraction_picking)) / (
+            margin_of_error**2 * train_size
         )
         sample_size = int(numerator / denominator)
         if 2 * sample_size + train_size <= population_size:

bin/import_ccpmf.py

@@ -754,13 +754,13 @@ def get_sample_size(population_size):
     margin_of_error = 0.01
     fraction_picking = 0.50
     z_score = 2.58  # Corresponds to confidence level 99%
-    numerator = (z_score ** 2 * fraction_picking * (1 - fraction_picking)) / (
-        margin_of_error ** 2
+    numerator = (z_score**2 * fraction_picking * (1 - fraction_picking)) / (
+        margin_of_error**2
     )
     sample_size = 0
     for train_size in range(population_size, 0, -1):
-        denominator = 1 + (z_score ** 2 * fraction_picking * (1 - fraction_picking)) / (
-            margin_of_error ** 2 * train_size
+        denominator = 1 + (z_score**2 * fraction_picking * (1 - fraction_picking)) / (
+            margin_of_error**2 * train_size
         )
         sample_size = int(numerator / denominator)
         if 2 * sample_size + train_size <= population_size:

bin/import_cv2.py

@@ -59,7 +59,7 @@ def init_worker(params):
 
 
 def one_sample(sample):
-    """ Take an audio file, and optionally convert it to 16kHz WAV """
+    """Take an audio file, and optionally convert it to 16kHz WAV"""
     mp3_filename = sample[0]
     if not os.path.splitext(mp3_filename.lower())[1] == ".mp3":
         mp3_filename += ".mp3"

bin/import_cv_personal.py

@@ -59,7 +59,7 @@ def init_worker(params):
 
 
 def one_sample(sample):
-    """ Take an audio file, and optionally convert it to 16kHz WAV """
+    """Take an audio file, and optionally convert it to 16kHz WAV"""
     mp3_filename = sample[0]
     # Storing wav files next to the mp3 ones - just with a different suffix
     wav_filename = os.path.splitext(mp3_filename)[0] + ".wav"

bin/import_fisher.py

@@ -264,13 +264,13 @@ def get_sample_size(population_size):
     margin_of_error = 0.01
     fraction_picking = 0.50
     z_score = 2.58  # Corresponds to confidence level 99%
-    numerator = (z_score ** 2 * fraction_picking * (1 - fraction_picking)) / (
-        margin_of_error ** 2
+    numerator = (z_score**2 * fraction_picking * (1 - fraction_picking)) / (
+        margin_of_error**2
     )
     sample_size = 0
     for train_size in range(population_size, 0, -1):
-        denominator = 1 + (z_score ** 2 * fraction_picking * (1 - fraction_picking)) / (
-            margin_of_error ** 2 * train_size
+        denominator = 1 + (z_score**2 * fraction_picking * (1 - fraction_picking)) / (
+            margin_of_error**2 * train_size
         )
         sample_size = int(numerator / denominator)
         if 2 * sample_size + train_size <= population_size:

bin/import_lingua_libre.py

@@ -57,7 +57,7 @@ def _maybe_extract(target_dir, extracted_data, archive_path):
 
 
 def one_sample(sample):
-    """ Take a audio file, and optionally convert it to 16kHz WAV """
+    """Take a audio file, and optionally convert it to 16kHz WAV"""
     ogg_filename = sample[0]
     # Storing wav files next to the ogg ones - just with a different suffix
     wav_filename = os.path.splitext(ogg_filename)[0] + ".wav"

bin/import_swb.py

@@ -318,13 +318,13 @@ def get_sample_size(population_size):
     margin_of_error = 0.01
     fraction_picking = 0.50
     z_score = 2.58  # Corresponds to confidence level 99%
-    numerator = (z_score ** 2 * fraction_picking * (1 - fraction_picking)) / (
-        margin_of_error ** 2
+    numerator = (z_score**2 * fraction_picking * (1 - fraction_picking)) / (
+        margin_of_error**2
     )
     sample_size = 0
     for train_size in range(population_size, 0, -1):
-        denominator = 1 + (z_score ** 2 * fraction_picking * (1 - fraction_picking)) / (
-            margin_of_error ** 2 * train_size
+        denominator = 1 + (z_score**2 * fraction_picking * (1 - fraction_picking)) / (
+            margin_of_error**2 * train_size
         )
         sample_size = int(numerator / denominator)
         if 2 * sample_size + train_size <= population_size:

bin/import_swc.py

@@ -103,13 +103,13 @@ def get_sample_size(population_size):
     margin_of_error = 0.01
     fraction_picking = 0.50
     z_score = 2.58  # Corresponds to confidence level 99%
-    numerator = (z_score ** 2 * fraction_picking * (1 - fraction_picking)) / (
-        margin_of_error ** 2
+    numerator = (z_score**2 * fraction_picking * (1 - fraction_picking)) / (
+        margin_of_error**2
     )
     sample_size = 0
     for train_size in range(population_size, 0, -1):
-        denominator = 1 + (z_score ** 2 * fraction_picking * (1 - fraction_picking)) / (
-            margin_of_error ** 2 * train_size
+        denominator = 1 + (z_score**2 * fraction_picking * (1 - fraction_picking)) / (
+            margin_of_error**2 * train_size
         )
         sample_size = int(numerator / denominator)
         if 2 * sample_size + train_size <= population_size:

data/lm/generate_lm.py

@@ -9,7 +9,7 @@
 
 
 def convert_and_filter_topk(args):
-    """ Convert to lowercase, count word occurrences and save top-k words to a file """
+    """Convert to lowercase, count word occurrences and save top-k words to a file"""
 
     counter = Counter()
     data_lower = os.path.join(args.output_dir, "lower.txt.gz")

doc/conf.py

@@ -51,7 +51,7 @@
 
 # -- Project information -----------------------------------------------------
 
-project = u"Coqui STT"
+project = "Coqui STT"
 copyright = "2021 Coqui GmbH, 2020 DeepSpeech authors, 2019-2020 Mozilla Corporation"
 author = "Coqui GmbH"
 
@@ -179,15 +179,15 @@
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-    (master_doc, "STT.tex", u"Coqui STT Documentation", u"Coqui GmbH", "manual"),
+    (master_doc, "STT.tex", "Coqui STT Documentation", "Coqui GmbH", "manual"),
 ]
 
 
 # -- Options for manual page output ---------------------------------------
 
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
-man_pages = [(master_doc, "stt", u"Coqui STT Documentation", [author], 1)]
+man_pages = [(master_doc, "stt", "Coqui STT Documentation", [author], 1)]
 
 
 # -- Options for Texinfo output -------------------------------------------
@@ -199,7 +199,7 @@
     (
         master_doc,
         "STT",
-        u"Coqui STT Documentation",
+        "Coqui STT Documentation",
         author,
         "STT",
         "One line description of project.",

training/coqui_stt_training/util/auto_input.py

@@ -32,13 +32,13 @@ def _get_sample_size(population_size):
     margin_of_error = 0.01
     fraction_picking = 0.50
     z_score = 2.58  # Corresponds to confidence level 99%
-    numerator = (z_score ** 2 * fraction_picking * (1 - fraction_picking)) / (
-        margin_of_error ** 2
+    numerator = (z_score**2 * fraction_picking * (1 - fraction_picking)) / (
+        margin_of_error**2
     )
     sample_size = 0
     for train_size in range(population_size, 0, -1):
-        denominator = 1 + (z_score ** 2 * fraction_picking * (1 - fraction_picking)) / (
-            margin_of_error ** 2 * train_size
+        denominator = 1 + (z_score**2 * fraction_picking * (1 - fraction_picking)) / (
+            margin_of_error**2 * train_size
         )
         sample_size = int(numerator / denominator)
         if 2 * sample_size + train_size <= population_size:

training/coqui_stt_training/util/config.py

@@ -872,7 +872,7 @@ def initialize_globals_from_args(**override_args):
 
 
 def initialize_globals_from_instance(config):
-    """ Initialize Config singleton from an existing instance """
+    """Initialize Config singleton from an existing instance"""
     _ConfigSingleton._config = config  # pylint: disable=protected-access
 
 

training/coqui_stt_training/util/evaluate_tools.py

@@ -95,7 +95,7 @@ def calculate_and_print_report(
 
 
 def print_report(samples, losses, wer, cer, dataset_name, report_count=5):
-    """ Print a report summary and samples of best, median and worst results """
+    """Print a report summary and samples of best, median and worst results"""
 
     # Print summary
     mean_loss = np.mean(losses)

training/coqui_stt_training/util/lm_optimize.py

@@ -57,7 +57,7 @@ def compute_lm_optimization() -> dict:
     study = optuna.create_study()
     study.set_user_attr("is_character_based", is_character_based)
     study.optimize(objective, n_jobs=1, n_trials=Config.n_trials)
-    
+
     return {
         "lm_alpha": study.best_params.get("lm_alpha"),
         "lm_beta": study.best_params.get("lm_beta"),