Larynx2 Versions Save

A fast, local neural text to speech system

2023.11.14-2

6 months ago

v1.2.0

9 months ago
  • Add --phoneme_silence option to CLI
  • Read inference.phoneme_silence from voice config
  • Upgrade to piper-phonemize 1.2.0 (phonemes for Luxembourgish)

v1.1.0

10 months ago
  • Add --json-input and --version

v1.0.0

11 months ago
  • Use fork of espeak-ng for punctuation preservation and sentence boundary detection
  • Support raw text phonemes with piper-phonemize
  • Support Arabic diacritization with libtashkeel (model included)
  • Extend default phoneme set to 256 for future expansion (use these pretrained checkpoints)
  • New command-line options (--silence_seconds, --espeak_data, --tashkeel_model, --debug)
  • Merge code into piper.hpp and piper.cpp for use as a library
  • Update to onnxruntime 1.14.1 (from piper-phonemize)
  • Adding logging with spdlog

v0.0.1

1 year ago

v0.0.2

1 year ago