Add BibleTTS recipe

[wyh2000]

What?

BibleTTS training recipe and corresponding pre-trained models

Why?

The goal is to build a TTS character based system using high-quality BibleTTS dataset. BibleTTS is a large high-quality open Text-to-Speech dataset with up to 80 hours of single speaker. It releases aligned speech and text for six languages spoken in Sub-Saharan Africa. There are two options:

1. Train VITS models from scratch for each language.

2. Finetune from a pretrained TTS model to accelarate training stage.

See also

BibleTTS : https://masakhane-io.github.io/bibleTTS/

[codecov]

Codecov Report

Merging #5436 (2e9c519) into master (92207e2) will decrease coverage by 0.01%.
Report is 61 commits behind head on master.
The diff coverage is n/a.

@@            Coverage Diff             @@
##           master    #5436      +/-   ##
==========================================
- Coverage   77.17%   77.17%   -0.01%     
==========================================
  Files         684      684              
  Lines       62643    62643              
==========================================
- Hits        48345    48344       -1     
- Misses      14298    14299       +1     

Flag	Coverage Δ
test_configuration_espnet2	∅ <ø> (∅)
test_integration_espnet1	65.73% <ø> (-0.03%)	⬇️
test_integration_espnet2	49.10% <ø> (-0.01%)	⬇️
test_python_espnet1	19.96% <ø> (ø)
test_python_espnet2	52.29% <ø> (ø)
test_utils	23.10% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

see 1 file with indirect coverage changes

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more