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

refactor(bin.find_unique_chars): use existing function

This commit is contained in:
Enno Hermann 2023-11-18 14:11:01 +01:00
parent 571f065994
commit 7630abb43f
2 changed files with 3 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
TTS/bin/find_unique_chars.py
View File

@ -4,7 +4,7 @@ import argparse
from argparse import RawTextHelpFormatter from argparse import RawTextHelpFormatter
from TTS.config import load_config from TTS.config import load_config
from TTS.tts.datasets import load_tts_samples from TTS.tts.datasets import find_unique_chars, load_tts_samples
def main(): def main():
@ -29,17 +29,7 @@ def main():
) )
items = train_items + eval_items items = train_items + eval_items
find_unique_chars(items)
texts = "".join(item["text"] for item in items)
chars = set(texts)
lower_chars = filter(lambda c: c.islower(), chars)
chars_force_lower = [c.lower() for c in chars]
chars_force_lower = set(chars_force_lower)
print(f" > Number of unique characters: {len(chars)}")
print(f" > Unique characters: {''.join(sorted(chars))}")
print(f" > Unique lower characters: {''.join(sorted(lower_chars))}")
print(f" > Unique all forced to lower characters: {''.join(sorted(chars_force_lower))}")
if __name__ == "__main__": if __name__ == "__main__":

2
TTS/tts/datasets/__init__.py
View File

@ -167,7 +167,7 @@ def _get_formatter_by_name(name):
def find_unique_chars(data_samples, verbose=True): def find_unique_chars(data_samples, verbose=True):
texts = "".join(item[0] for item in data_samples) texts = "".join(item["text"] for item in data_samples)
chars = set(texts) chars = set(texts)
lower_chars = filter(lambda c: c.islower(), chars) lower_chars = filter(lambda c: c.islower(), chars)
chars_force_lower = [c.lower() for c in chars] chars_force_lower = [c.lower() for c in chars]