Improve model card: scope, links, correct filename model.safetensors

README.md

@@ -1,31 +1,66 @@
 ---
 license: mit
+language:
+  - multilingual
 tags:
   - text-to-speech
   - speech-synthesis
   - autoencoder
   - audio
+  - onnx
+pipeline_tag: text-to-speech
 ---
 
-# BlueCodec — Speech Autoencoder
+# BlueCodec — speech autoencoder (codec only)
 
-A neural speech autoencoder that compresses 44.1 kHz audio into a compact continuous latent representation, used as the first stage of the Light-BlueTTS text-to-speech system.
+This repository publishes **only the neural audio codec** used by **[BlueTTS](https://github.com/maxmelichov/BlueTTS)**: a 44.1 kHz speech **autoencoder** that maps waveforms to a low-rate continuous latent sequence and back. It is **not** a full TTS model (no text encoder, duration model, or flow stack).
 
-The encoder turns raw audio into a 24-dim latent sequence at ~86 Hz. Downstream TTS modules (flow-matching, duration prediction) operate entirely in this latent space, making synthesis fast and lightweight. The decoder reconstructs full-quality waveforms from those latents at inference time.
+| If you need… | Use |
+|--------------|-----|
+| **End-to-end ONNX TTS** | [`notmax123/blue-onnx`](https://huggingface.co/notmax123/blue-onnx) + [BlueTTS](https://github.com/maxmelichov/BlueTTS) |
+| **Full PyTorch stack + stats** (training / voice export) | [`notmax123/blue`](https://huggingface.co/notmax123/blue) — includes `blue_codec.safetensors` alongside TTL/DP weights |
+| **Training the codec from scratch** | [maxmelichov/blue-codec](https://github.com/maxmelichov/blue-codec) (standalone repo & [training doc](https://github.com/maxmelichov/blue-codec/blob/main/docs/training.md)) |
 
----
+**Project home:** [https://github.com/maxmelichov/BlueTTS](https://github.com/maxmelichov/BlueTTS) · **Live demo:** [Hugging Face Space — notmax123/Blue](https://huggingface.co/spaces/notmax123/Blue)
 
-## Architecture
+## What it does
 
-| Component | Details |
-|---|---|
-| Input | 1253-channel spectrogram (1025 log-linear + 228 log-mel, FFT 2048, hop 512) |
-| Encoder (~25.6M) | Conv1d stem (1253→512) + 10 ConvNeXt blocks + proj (512→24) |
-| Decoder (~25.3M) | CausalConv1d stem (24→512) + 10 causal dilated ConvNeXt blocks + VocoderHead |
-| Latent | 24-dim @ ~86 Hz |
+- **Encoder:** waveform → spectrogram features → **24-dimensional latents** at **~86 Hz** (compact trajectory for downstream TTS).
+- **Decoder:** latents → high-quality **44.1 kHz** audio (causal stack + vocoder head).
 
----
+Downstream BlueTTS modules (flow matching, duration, text-to-latent) run in this latent space; keeping synthesis lightweight and fast.
+
+## Architecture (summary)
+
+| 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 |
+
+## Checkpoint in this repo
+
+| File | Role |
+|------|------|
+| **`model.safetensors`** | Encoder + decoder weights (Safetensors). State dict keys are typically prefixed with `encoder.*` and `decoder.*`. |
+
+*(An older naming convention in some local scripts is `ae_latest.safetensors`; the file served from **this** Hub repo is **`model.safetensors`**.)*
+
+## Download
+
+```bash
+hf download notmax123/blue-codec --repo-type model --local-dir ./blue_codec_only
+```
+
+Equivalent:
+
+```bash
+huggingface-cli download notmax123/blue-codec --repo-type model --local-dir ./blue_codec_only
+```
+
+Repo id is **case-sensitive**: `notmax123/blue-codec`.
 
-## Checkpoint
+## License
 
-`ae_latest.safetensors` — encoder + decoder weights (~204 MB). Keys are prefixed with `encoder.*` and `decoder.*`.
+MIT — align usage with [BlueTTS](https://github.com/maxmelichov/BlueTTS) and the [blue-codec](https://github.com/maxmelichov/blue-codec) repository for any training or redistribution terms that apply to your use case.