schihei/tts
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Minor changes

Browse Source
This commit is contained in:
Heiko J Schick
2022-09-07 17:11:32 +02:00
parent aa0b2d6cb7
commit b10b9feec0
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tts.py
+2 -1
View File
@@ -1,6 +1,6 @@
""" """
Text-to-speech synthesis (TTS) by using the FastSpeech2 model from fairseq S^2. Text-to-speech synthesis (TTS) by using the FastSpeech2 model from fairseq S^2.
This Python script convers an input text file in output wav file. The project This Python script converts an input text file in output wav file. The project
was inspired by Dr. Tristan Behrens's arxiv-reader, which converts arXiv papers was inspired by Dr. Tristan Behrens's arxiv-reader, which converts arXiv papers
to audio. More details about the models and further examples are in the to audio. More details about the models and further examples are in the
following sources. ↓ following sources. ↓
@@ -58,6 +58,7 @@ def main():
line = line.replace("5G", "5 G") line = line.replace("5G", "5 G")
line = line.replace("CO2", "C O 2") line = line.replace("CO2", "C O 2")
line = line.replace("EUR", "Euro") line = line.replace("EUR", "Euro")
line = line.replace("USD", "U S Dollars")
line = line.replace("II", "2") line = line.replace("II", "2")
line = line.replace("IBM", "I B M") line = line.replace("IBM", "I B M")
line = line.replace("IMF", "I M F") line = line.replace("IMF", "I M F")