Lucas Newman

f5-tts-mlx. Implementation of F5-TTS in MLX

nanospeech. A simple, hackable text-to-speech system in PyTorch and MLX

best-rq-pytorch. Implementation of BEST-RQ - a model for self-supervised learning of speech signals using a random projection quantizer, in Pytorch.

f5-tts-swift. Implementation of F5-TTS in Swift using MLX

vocos-mlx. Implementation of 'Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis', in MLX

e2-tts-mlx. Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in MLX

vocos-swift. Implementation of 'Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis', in Swift using MLX

descript-mlx. Implementation of the Descript Audio Codec in MLX

e2-tts-pytorch. Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch

mlx2coreai. Convert MLX models to CoreAI

voicebox-pytorch. Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch

vector-quantize-pytorch. Vector (and Scalar) Quantization, in Pytorch

spear-tts-pytorch. Implementation of Spear-TTS - multi-speaker text-to-speech attention network, in Pytorch

mlx2coreml. Experimental MLX -> Core ML translation pipeline