github.com
Parler-TTS
An inference and training library for text-to-speech models.
https://github.com/huggingface/parler-ttsAbout This Resource
An inference and training library for text-to-speech models. It includes models that use text descriptions to guide characteristics of the generated voice and recording.
Saved Notes
Original notes saved with this link. They may describe an earlier version.
GitHub - huggingface/parler-tts: Inference and training library for high-quality TTS models.
Parler-TTS is a lightweight text-to-speech (TTS) model that generates high-quality, natural-sounding speech matching a given speaker's characteristics (gender, pitch, speaking style, etc.). It reproduces work from the paper Natural language guidance of high-fidelity text-to-speech with synthetic annotations by Dan Lyth and Simon King from Stability AI and Edinburgh University.
Unlike other TTS models, Parler-TTS is fully open-source. All datasets, pre-processing, training code, and weights are publicly available under a permissive license, allowing the community to build upon this work and develop their own powerful TTS models.