From fd009bb088d664bfc100cad48a0290b8c96783c4 Mon Sep 17 00:00:00 2001
From: chenfeiyu <chenfeiyu@baidu.com>
Date: Fri, 6 Mar 2020 06:53:50 +0000
Subject: [PATCH] use os.path instead of pathlib.
---
parakeet/datasets/ljspeech.py | 10 ++++------
parakeet/models/waveflow/data.py | 3 ++-
2 files changed, 6 insertions(+), 7 deletions(-)
diff --git a/parakeet/datasets/ljspeech.py b/parakeet/datasets/ljspeech.py
index 62209e9..3ab8ac9 100644
--- a/parakeet/datasets/ljspeech.py
+++ b/parakeet/datasets/ljspeech.py
@@ -12,7 +12,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-from pathlib import Path
+import os
import numpy as np
import pandas as pd
import librosa
@@ -27,13 +27,11 @@ from ..data.batch import TextIDBatcher, SpecBatcher
class LJSpeech(DatasetMixin):
def __init__(self, root):
super(LJSpeech, self).__init__()
- assert isinstance(root, (
- str, Path)), "root should be a string or Path object"
- self.root = root if isinstance(root, Path) else Path(root)
+ self.root = root
self.metadata = self._prepare_metadata()
def _prepare_metadata(self):
- csv_path = self.root.joinpath("metadata.csv")
+ csv_path = os.path.join(self.root, "metadata.csv")
metadata = pd.read_csv(
csv_path,
sep="|",
@@ -51,7 +49,7 @@ class LJSpeech(DatasetMixin):
"""
fname, raw_text, normalized_text = metadatum
- wav_path = self.root.joinpath("wavs", fname + ".wav")
+ wav_path = os.path.join(self.root, "wavs", fname + ".wav")
# load -> trim -> preemphasis -> stft -> magnitude -> mel_scale -> logscale -> normalize
wav, sample_rate = librosa.load(
diff --git a/parakeet/models/waveflow/data.py b/parakeet/models/waveflow/data.py
index 0c1e914..83438f7 100644
--- a/parakeet/models/waveflow/data.py
+++ b/parakeet/models/waveflow/data.py
@@ -12,6 +12,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.
+import os
import random
import librosa
@@ -32,7 +33,7 @@ class Dataset(ljspeech.LJSpeech):
def _get_example(self, metadatum):
fname, _, _ = metadatum
- wav_path = self.root.joinpath("wavs", fname + ".wav")
+ wav_path = os.path.join(self.root, "wavs", fname + ".wav")
loaded_sr, audio = read(wav_path)
assert loaded_sr == self.config.sample_rate