wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-09 11:16:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Check num of columns in coqui format (#2066)

Browse Source 
* Check 4 colums in coqui format

* Fix encoding

* Fixup
This commit is contained in:
Eren Gölge
2022-10-10 12:13:32 +02:00
committed by GitHub
parent f3b947e706
commit 843fa6f3fa
1 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
TTS/tts/datasets/formatters.py
+9
View File
@@ -15,6 +15,15 @@ from tqdm import tqdm
def coqui(root_path, meta_file, ignored_speakers=None):
"""Interal dataset formatter."""
filepath = os.path.join(root_path, meta_file)
# ensure there are 4 columns for every line
with open(filepath, "r", encoding="utf8") as f:
lines = f.readlines()
num_cols = len(lines[0].split("|")) # take the first row as reference
for idx, line in enumerate(lines[1:]):
if len(line.split("|")) != num_cols:
print(f" > Missing column in line {idx + 1} -> {line.strip()}")
# load metadata
metadata = pd.read_csv(os.path.join(root_path, meta_file), sep="|")
assert all(x in metadata.columns for x in ["audio_file", "text"])
speaker_name = None if "speaker_name" in metadata.columns else "coqui"