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

import the spacy language class dynamically with a English fallback when import error

This commit is contained in:
David Martin Rius 2024-02-28 19:58:25 +01:00
parent dbf1a08a0d
commit 8aeced16fc
1 changed files with 8 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
TTS/tts/layers/xtts/tokenizer.py
View File

@ -8,29 +8,21 @@ import torch
from hangul_romanize import Transliter from hangul_romanize import Transliter
from hangul_romanize.rule import academic from hangul_romanize.rule import academic
from num2words import num2words from num2words import num2words
from spacy.lang.ar import Arabic
from spacy.lang.en import English from spacy.lang.en import English
from spacy.lang.es import Spanish from spacy.util import get_lang_class
from spacy.lang.ja import Japanese
from spacy.lang.zh import Chinese
from tokenizers import Tokenizer from tokenizers import Tokenizer
from TTS.tts.layers.xtts.zh_num2words import TextNorm as zh_num2words from TTS.tts.layers.xtts.zh_num2words import TextNorm as zh_num2words
def get_spacy_lang(lang): def get_spacy_lang(lang):
if lang == "zh": try:
return Chinese() lang_model = get_lang_class(lang)()
elif lang == "ja": except ImportError:
return Japanese() # Fallback to English if the language model is not available
elif lang == "ar": lang_model = English()
return Arabic() return lang_model
elif lang == "es":
return Spanish()
else:
# For most languages, Enlish does the job
return English()
def split_sentence(text, lang, text_split_length=250): def split_sentence(text, lang, text_split_length=250):
"""Preprocess the input text""" """Preprocess the input text"""