[TTS]fix praatio version, test=tts (#1158)

* fix praatio version, test=tts

* fix praatio version, test=tts

examples/other/g2p/get_g2p_data.py

@@ -15,7 +15,7 @@ import argparse
 from collections import defaultdict
 from pathlib import Path
 
-from praatio import tgio
+from praatio import textgrid
 
 
 def get_baker_data(root_dir):
@@ -28,7 +28,7 @@ def get_baker_data(root_dir):
     alignment_files = [f for f in alignment_files if f.stem not in exclude]
     data_dict = defaultdict(dict)
     for alignment_fp in alignment_files:
-        alignment = tgio.openTextgrid(alignment_fp)
+        alignment = textgrid.openTextgrid(alignment_fp, includeEmptyIntervals=True)
         # only with baker's annotation
         utt_id = alignment.tierNameList[0].split(".")[0]
         intervals = alignment.tierDict[alignment.tierNameList[0]].entryList

examples/other/g2p/path.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+export MAIN_ROOT=`realpath ${PWD}/../../../`
+
+export PATH=${MAIN_ROOT}:${MAIN_ROOT}/utils:${PATH}
+export LC_ALL=C
+
+export PYTHONDONTWRITEBYTECODE=1
+# Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
+export PYTHONIOENCODING=UTF-8
+export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH}

examples/other/tn/path.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+export MAIN_ROOT=`realpath ${PWD}/../../../`
+
+export PATH=${MAIN_ROOT}:${MAIN_ROOT}/utils:${PATH}
+export LC_ALL=C
+
+export PYTHONDONTWRITEBYTECODE=1
+# Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
+export PYTHONIOENCODING=UTF-8
+export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH}

paddlespeech/t2s/exps/voice_cloning/tacotron2_ge2e/process_wav.py

@@ -19,12 +19,12 @@ from pathlib import Path
 import librosa
 import numpy as np
 import soundfile as sf
-from praatio import tgio
+from praatio import textgrid
 from tqdm import tqdm
 
 
 def get_valid_part(fpath):
-    f = tgio.openTextgrid(fpath)
+    f = textgrid.openTextgrid(fpath, includeEmptyIntervals=True)
 
     start = 0
     phone_entry_list = f.tierDict['phones'].entryList

requirements.txt

@@ -20,7 +20,7 @@ paddlespeech_feat
 pandas
 phkit
 Pillow
-praatio~=4.1
+praatio==5.0.0
 pre-commit
 pybind11
 pypi-kenlm

setup.py

@@ -45,7 +45,7 @@ requirements = {
         "pandas",
         "paddleaudio",
         "paddlespeech_feat",
-        "praatio~=4.1",
+        "praatio==5.0.0",
         "pypinyin",
         "python-dateutil",
         "pyworld",

utils/gen_duration_from_textgrid.py

@@ -18,12 +18,12 @@ from pathlib import Path
 import librosa
 import numpy as np
 import yaml
-from praatio import tgio
+from praatio import textgrid
 from yacs.config import CfgNode
 
 
 def readtg(tg_path, sample_rate=24000, n_shift=300):
-    alignment = tgio.openTextgrid(tg_path, readRaw=True)
+    alignment = textgrid.openTextgrid(tg_path, includeEmptyIntervals=True)
     phones = []
     ends = []
     for interval in alignment.tierDict["phones"].entryList: