From 2edab4b3f9b5ad4352126ba6d52878b71d8e2cb3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eren=20G=C3=B6lge?= Date: Mon, 1 Feb 2021 17:05:03 +0000 Subject: [PATCH] disable pw in audio that causes numpy issue --- TTS/utils/audio.py | 20 ++++++++++---------- setup.py | 2 +- 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/TTS/utils/audio.py b/TTS/utils/audio.py index 93a5880f..93093d1a 100644 --- a/TTS/utils/audio.py +++ b/TTS/utils/audio.py @@ -3,7 +3,7 @@ import soundfile as sf import numpy as np import scipy.io.wavfile import scipy.signal -import pyworld as pw +# import pyworld as pw from TTS.tts.utils.data import StandardScaler @@ -292,15 +292,15 @@ class AudioProcessor(object): return pad // 2, pad // 2 + pad % 2 ### Compute F0 ### - def compute_f0(self, x): - f0, t = pw.dio( - x.astype(np.double), - fs=self.sample_rate, - f0_ceil=self.mel_fmax, - frame_period=1000 * self.hop_length / self.sample_rate, - ) - f0 = pw.stonemask(x.astype(np.double), f0, t, self.sample_rate) - return f0 + # def compute_f0(self, x): + # f0, t = pw.dio( + # x.astype(np.double), + # fs=self.sample_rate, + # f0_ceil=self.mel_fmax, + # frame_period=1000 * self.hop_length / self.sample_rate, + # ) + # f0 = pw.stonemask(x.astype(np.double), f0, t, self.sample_rate) + # return f0 ### Audio Processing ### def find_endpoint(self, wav, threshold_db=-40, min_silence_sec=0.8): diff --git a/setup.py b/setup.py index a4fbe1d1..1f3be4b4 100644 --- a/setup.py +++ b/setup.py @@ -27,7 +27,7 @@ args, unknown_args = parser.parse_known_args() # Remove our arguments from argv so that setuptools doesn't see them sys.argv = [sys.argv[0]] + unknown_args -version = '0.0.9.1' +version = '0.0.9.2' cwd = os.path.dirname(os.path.abspath(__file__)) # Handle Cython code