Skip to content

Replace sf.read with librosa.load to load correct sr based on config … #24

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

Open
mrbraden56 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Replace sf.read with librosa.load to load correct sr based on config … #24

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 5 additions & 4 deletions audiolib.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,14 +7,15 @@
import soundfile as sf
import os
import numpy as np
import librosa

# Function to read audio
def audioread(path, norm = True, start=0, stop=None):
def audioread(path, norm = True, sr=16000):
path = os.path.abspath(path)
if not os.path.exists(path):
raise ValueError("[{}] does not exist!".format(path))
try:
x, sr = sf.read(path, start=start, stop=stop)
x, sr = librosa.load(path, sr=sr)
except RuntimeError: # fix for sph pcm-embedded shortened v2
print('WARNING: Audio type not supported')

Expand Down Expand Up @@ -47,8 +48,8 @@ def audiowrite(data, fs, destpath, norm=False):

if not os.path.exists(destdir):
os.makedirs(destdir)
sf.write(destpath, data, fs)

sf.write(destpath, data, int(fs))
return

# Function to mix clean speech and noise at various SNR levels
Expand Down
10 changes: 5 additions & 5 deletions noisyspeech_synthesizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ def main(cfg):
clean_dir = cfg["speech_dir"]
if not os.path.exists(clean_dir):
assert False, ("Clean speech data is required")

noise_dir = os.path.join(os.path.dirname(__file__), 'noise_train')
if cfg["noise_dir"]!='None':
noise_dir = cfg["noise_dir"]
Expand Down Expand Up @@ -59,7 +59,7 @@ def main(cfg):

while num_samples < total_samples:
idx_s = np.random.randint(0, np.size(cleanfilenames))
clean, fs = audioread(cleanfilenames[idx_s])
clean, fs = audioread(cleanfilenames[idx_s], sr=fs)

if len(clean)>audio_length:
clean = clean
Expand All @@ -70,12 +70,12 @@ def main(cfg):
idx_s = idx_s + 1
if idx_s >= np.size(cleanfilenames)-1:
idx_s = np.random.randint(0, np.size(cleanfilenames))
newclean, fs = audioread(cleanfilenames[idx_s])
newclean, fs = audioread(cleanfilenames[idx_s], sr=fs)
cleanconcat = np.append(clean, np.zeros(int(fs*silence_length)))
clean = np.append(cleanconcat, newclean)

idx_n = np.random.randint(0, np.size(noisefilenames))
noise, fs = audioread(noisefilenames[idx_n])
noise, fs = audioread(noisefilenames[idx_n], sr=fs)

if len(noise)>=len(clean):
noise = noise[0:len(clean)]
Expand All @@ -86,7 +86,7 @@ def main(cfg):
idx_n = idx_n + 1
if idx_n >= np.size(noisefilenames)-1:
idx_n = np.random.randint(0, np.size(noisefilenames))
newnoise, fs = audioread(noisefilenames[idx_n])
newnoise, fs = audioread(noisefilenames[idx_n], sr=fs)
noiseconcat = np.append(noise, np.zeros(int(fs*silence_length)))
noise = np.append(noiseconcat, newnoise)
noise = noise[0:len(clean)]
Expand Down