Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

use soundfile for faster read

This commit is contained in:
Eren Golge 2019-05-23 01:52:37 +02:00
parent c6f970b65b
commit d4b900f6c9
3 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
dataset_analysis/AnalyzeDataset.ipynb
View File

@ -753,7 +753,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.5" "version": "3.7.2"
} }
}, },
"nbformat": 4, "nbformat": 4,

1
setup.py
View File

@ -83,6 +83,7 @@ setup(
# "lws", # "lws",
"tqdm", "tqdm",
"phonemizer", "phonemizer",
"soundfile",
], ],
dependency_links=[ dependency_links=[
'http://github.com/bootphon/phonemizer/tarball/master#egg=phonemizer' 'http://github.com/bootphon/phonemizer/tarball/master#egg=phonemizer'

3
utils/audio.py
View File

@ -1,5 +1,6 @@
import os import os
import librosa import librosa
import soundfile as sf
import pickle import pickle
import copy import copy
import numpy as np import numpy as np
@ -230,7 +231,7 @@ class AudioProcessor(object):
# return np.sign(signal) * magnitude # return np.sign(signal) * magnitude
def load_wav(self, filename, encode=False): def load_wav(self, filename, encode=False):
x, sr = librosa.load(filename, sr=self.sample_rate) x, sr = sf.read(filename)
if self.do_trim_silence: if self.do_trim_silence:
x = self.trim_silence(x) x = self.trim_silence(x)
# sr, x = io.wavfile.read(filename) # sr, x = io.wavfile.read(filename)