Adding the possibility of get durations out of pretrained model

This commit is contained in:
Shivam Mehta
2024-05-24 11:34:51 +02:00
parent fb7b954de5
commit 4b39f6cad0
13 changed files with 274 additions and 24 deletions

View File

@@ -15,7 +15,6 @@ import logging
import re
import phonemizer
import piper_phonemize
from unidecode import unidecode
# To avoid excessive logging we set the log level of the phonemizer package to Critical
@@ -106,11 +105,17 @@ def english_cleaners2(text):
return phonemes
def english_cleaners_piper(text):
"""Pipeline for English text, including abbreviation expansion. + punctuation + stress"""
text = convert_to_ascii(text)
text = lowercase(text)
text = expand_abbreviations(text)
phonemes = "".join(piper_phonemize.phonemize_espeak(text=text, voice="en-US")[0])
phonemes = collapse_whitespace(phonemes)
return phonemes
# I am removing this due to incompatibility with several version of python
# However, if you want to use it, you can uncomment it
# and install piper-phonemize with the following command:
# pip install piper-phonemize
# import piper_phonemize
# def english_cleaners_piper(text):
# """Pipeline for English text, including abbreviation expansion. + punctuation + stress"""
# text = convert_to_ascii(text)
# text = lowercase(text)
# text = expand_abbreviations(text)
# phonemes = "".join(piper_phonemize.phonemize_espeak(text=text, voice="en-US")[0])
# phonemes = collapse_whitespace(phonemes)
# return phonemes