experiments/STT
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge pull request #3045 from ricky-cck/master

Browse Source 
Fix csv writer parameter
This commit is contained in:
Reuben Morais 2020-06-08 14:01:15 +02:00 committed by GitHub
commit fdf5700d37
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
8 changed files with 16 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
bin/import_cv.py
View File

@ -127,7 +127,7 @@ def _maybe_convert_set(extracted_dir, source_csv, target_csv):
pool.join()
print('Writing "%s"...' % target_csv)
with open(target_csv, "w") as target_csv_file:
with open(target_csv, "w", encoding="utf-8", newline="") as target_csv_file:
writer = csv.DictWriter(target_csv_file, fieldnames=FIELDNAMES)
writer.writeheader()
bar = progressbar.ProgressBar(max_value=len(rows), widgets=SIMPLE_BAR)

2
bin/import_cv2.py
View File

@ -127,7 +127,7 @@ def _maybe_convert_set(dataset, tsv_dir, audio_dir, filter_obj, space_after_ever
output_csv = os.path.join(os.path.abspath(audio_dir), dataset + ".csv")
print("Saving new DeepSpeech-formatted CSV file to: ", output_csv)
with open(output_csv, "w", encoding="utf-8") as output_csv_file:
with open(output_csv, "w", encoding="utf-8", newline="") as output_csv_file:
print("Writing CSV file for DeepSpeech.py as: ", output_csv)
writer = csv.DictWriter(output_csv_file, fieldnames=FIELDNAMES)
writer.writeheader()

6
bin/import_lingua_libre.py
View File

@ -136,9 +136,9 @@ def _maybe_convert_sets(target_dir, extracted_data):
pool.close()
pool.join()
with open(target_csv_template.format("train"), "w") as train_csv_file: # 80%
with open(target_csv_template.format("dev"), "w") as dev_csv_file: # 10%
with open(target_csv_template.format("test"), "w") as test_csv_file: # 10%
with open(target_csv_template.format("train"), "w", encoding="utf-8", newline="") as train_csv_file: # 80%
with open(target_csv_template.format("dev"), "w", encoding="utf-8", newline="") as dev_csv_file: # 10%
with open(target_csv_template.format("test"), "w", encoding="utf-8", newline="") as test_csv_file: # 10%
train_writer = csv.DictWriter(train_csv_file, fieldnames=FIELDNAMES)
train_writer.writeheader()
dev_writer = csv.DictWriter(dev_csv_file, fieldnames=FIELDNAMES)

6
bin/import_m-ailabs.py
View File

@ -137,9 +137,9 @@ def _maybe_convert_sets(target_dir, extracted_data):
pool.close()
pool.join()
with open(target_csv_template.format("train"), "w") as train_csv_file: # 80%
with open(target_csv_template.format("dev"), "w") as dev_csv_file: # 10%
with open(target_csv_template.format("test"), "w") as test_csv_file: # 10%
with open(target_csv_template.format("train"), "w", encoding="utf-8", newline="") as train_csv_file: # 80%
with open(target_csv_template.format("dev"), "w", encoding="utf-8", newline="") as dev_csv_file: # 10%
with open(target_csv_template.format("test"), "w", encoding="utf-8", newline="") as test_csv_file: # 10%
train_writer = csv.DictWriter(train_csv_file, fieldnames=FIELDNAMES)
train_writer.writeheader()
dev_writer = csv.DictWriter(dev_csv_file, fieldnames=FIELDNAMES)

6
bin/import_slr57.py
View File

@ -159,9 +159,9 @@ def _maybe_convert_sets(target_dir, extracted_data):
pool.close()
pool.join()
with open(target_csv_template.format("train"), "w") as train_csv_file: # 80%
with open(target_csv_template.format("dev"), "w") as dev_csv_file: # 10%
with open(target_csv_template.format("test"), "w") as test_csv_file: # 10%
with open(target_csv_template.format("train"), "w", encoding="utf-8", newline="") as train_csv_file: # 80%
with open(target_csv_template.format("dev"), "w", encoding="utf-8", newline="") as dev_csv_file: # 10%
with open(target_csv_template.format("test"), "w", encoding="utf-8", newline="") as test_csv_file: # 10%
train_writer = csv.DictWriter(train_csv_file, fieldnames=FIELDNAMES)
train_writer.writeheader()
dev_writer = csv.DictWriter(dev_csv_file, fieldnames=FIELDNAMES)

2
bin/import_swc.py
View File

@ -461,7 +461,7 @@ def write_csvs(samples, language):
base_dir = os.path.abspath(CLI_ARGS.base_dir)
csv_path = os.path.join(base_dir, language + "-" + sub_set + ".csv")
print('Writing "{}"...'.format(csv_path))
with open(csv_path, "w") as csv_file:
with open(csv_path, "w", encoding="utf-8", newline="") as csv_file:
writer = csv.DictWriter(
csv_file, fieldnames=FIELDNAMES_EXT if CLI_ARGS.add_meta else FIELDNAMES
)

6
bin/import_ts.py
View File

@ -131,9 +131,9 @@ def _maybe_convert_sets(target_dir, extracted_data, english_compatible=False):
pool.close()
pool.join()
with open(target_csv_template.format("train"), "w") as train_csv_file: # 80%
with open(target_csv_template.format("dev"), "w") as dev_csv_file: # 10%
with open(target_csv_template.format("test"), "w") as test_csv_file: # 10%
with open(target_csv_template.format("train"), "w", encoding="utf-8", newline="") as train_csv_file: # 80%
with open(target_csv_template.format("dev"), "w", encoding="utf-8", newline="") as dev_csv_file: # 10%
with open(target_csv_template.format("test"), "w", encoding="utf-8", newline="") as test_csv_file: # 10%
train_writer = csv.DictWriter(train_csv_file, fieldnames=FIELDNAMES)
train_writer.writeheader()
dev_writer = csv.DictWriter(dev_csv_file, fieldnames=FIELDNAMES)

2
bin/import_tuda.py
View File

@ -111,7 +111,7 @@ def write_csvs(extracted):
CLI_ARGS.base_dir, "tuda-{}-{}.csv".format(TUDA_VERSION, sub_set)
)
print('Writing "{}"...'.format(csv_path))
with open(csv_path, "w") as csv_file:
with open(csv_path, "w", encoding="utf-8", newline="") as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=FIELDNAMES)
writer.writeheader()
set_dir = os.path.join(extracted, sub_set)