Views
No views yet
| If you need… | Use |
|---|---|
| End-to-end ONNX TTS | notmax123/blue-onnx + BlueTTS |
| Full PyTorch stack + stats (training / voice export) | notmax123/blue — includes blue_codec.safetensors alongside TTL/DP weights |
| Training the codec from scratch | maxmelichov/blue-codec (standalone repo & training doc) |
| Piece | Details |
|---|---|
| Input | 1253-channel spectrogram (1025 log-linear + 228 log-mel; FFT 2048, hop 512) |
| Encoder (~25.6M params) | Conv1d stem (1253→512) + 10 ConvNeXt blocks + projection (512→24) |
| Decoder (~25.3M params) | CausalConv1d stem (24→512) + 10 causal dilated ConvNeXt blocks + vocoder head |
| Latent | 24-D @ ~86 Hz |
| File | Role |
|---|---|
model.safetensors | Encoder + decoder weights (Safetensors). State dict keys are typically prefixed with encoder.* and decoder.*. |
ae_latest.safetensors; the file served from this Hub repo is model.safetensors.)hf download notmax123/blue-codec --repo-type model --local-dir ./blue_codec_onlyhuggingface-cli download notmax123/blue-codec --repo-type model --local-dir ./blue_codec_onlynotmax123/blue-codec.