Blue Model Checkpoints

This repository contains the training checkpoints and stats files for the Blue speech synthesis system.

Checkpoints Directory

If you are following the finetuning or training instructions, download these weights:

• blue_codec.safetensors: The standalone trained Audio Codec. Used for translating to/from discrete/continuous latents.
• stats_multilingual.pt: The statistical data containing the latent means and standard deviations computed from the corpus.
• vf_estimator.safetensors: The combined Text-to-Latent acoustic checkpoints (includes text encoder, reference encoder, and the Flow Matching model).
• duration_predictor.safetensors: The Duration Predictor checkpoint.

Setup Instructions

To train or finetune, download this repository to your codebase:

huggingface-cli download notmax123/blue --local-dir pt_weights

For more specifics, see the Training Guide.