Skip to content

data argument with encoding UTF-8 #3633

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
danpovey merged 2 commits into from
Oct 3, 2019
Merged

data argument with encoding UTF-8 #3633

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cbd564c
Encoding UTF-8
sih4sing5hong5 Oct 3, 2019
80055e3
reformat
sih4sing5hong5 Oct 3, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions egs/wsj/s5/steps/data/augment_data_dir.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,7 +91,7 @@ def check_args(args):
return args

def get_noise_list(noise_wav_scp_filename):
noise_wav_scp_file = open(noise_wav_scp_filename, 'r').readlines()
noise_wav_scp_file = open(noise_wav_scp_filename, 'r', encoding='utf-8').readlines()
noise_wavs = {}
noise_utts = []
for line in noise_wav_scp_file:
Expand Down Expand Up @@ -204,7 +204,7 @@ def main():
num_bg_noises = [int(i) for i in args.num_bg_noises.split(":")]
reco2dur = parse_file_to_dict(input_dir + "/reco2dur",
value_processor = lambda x: float(x[0]))
wav_scp_file = open(input_dir + "/wav.scp", 'r').readlines()
wav_scp_file = open(input_dir + "/wav.scp", 'r', encoding='utf-8').readlines()

noise_wavs = {}
noise_reco2dur = {}
Expand Down
2 changes: 1 addition & 1 deletion egs/wsj/s5/steps/data/reverberate_data_dir.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -377,7 +377,7 @@ def add_prefix_to_fields(input_file, output_file, num_replicas, include_original
""" This function replicate the entries in files like segments, utt2spk, text
"""
list = [x.strip() for x in open(input_file, encoding='utf-8')]
f = open(output_file, "w" ,encoding='utf-8')
f = open(output_file, "w", encoding='utf-8')
if include_original:
start_index = 0
else:
Expand Down