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

Minor changes in documentation

Browse Source
This commit is contained in:
Heiko J Schick
2022-09-07 16:20:48 +02:00
parent 3890beec4d
commit aa0b2d6cb7
1 changed files with 8 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tts.py
+8 -1
View File
@@ -1,9 +1,16 @@
""" """
Text-to-speech synthesis (TTS) 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
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
following sources. ↓
Sources: Sources:
— https://arxiv.org/abs/2109.06912
— https://github.com/facebookresearch/fairseq/tree/main/examples/speech_synthesis
— https://huggingface.co/facebook/fastspeech2-en-ljspeech — https://huggingface.co/facebook/fastspeech2-en-ljspeech
— https://github.com/AI-Guru/arxiv-reader — https://github.com/AI-Guru/arxiv-reader
— https://www.linkedin.com/in/dr-tristan-behrens-734967a2/
""" """
import argparse import argparse
from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf_hub from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf_hub