FluidInference/FluidAudio v0.12.3

on GitHub

What's New

• CoreML G2P Model for TTS (#350): Replace eSpeak with a CoreML grapheme-to-phoneme model, rename product to FluidAudioTTS
• Speaker Pre-Enrollment APIs (#355): Add extractSpeakerEmbedding(from:) and primeWithAudio(_:) for priming diarizers with known speaker audio
• Download Progress Callbacks (#354): Byte-level progress reporting for model downloads

Fixes

• Fix CustomVocabularyContext.minSimilarity not being respected in rescoring (#349)
• Fix iOS build and CI benchmark failures (#353)
• Fix release build data race and currency number spelling (#352)

Other

• Remove ESpeakNG framework and update docs (#351)
• Update README with current versions and product names (#348)

Full Changelog: v0.12.2...v0.12.3