| --- |
| license: apache-2.0 |
| language: |
| - en |
| pipeline_tag: text-to-speech |
| tags: |
| - mlx |
| - text-to-speech |
| - voice-cloning |
| - apple-silicon |
| base_model: YatharthS/LuxTTS |
| --- |
| |
| # LuxTTS — MLX weights (fp32) |
|
|
| [LuxTTS](https://huggingface.co/YatharthS/LuxTTS) converted to MLX-native |
| safetensors, for Apple silicon. Same model, same precision — a key-remap and a |
| conv-layout transpose, nothing retrained and nothing quantized. |
|
|
| Upstream ships `model.pt` (torch) and ONNX graphs. Neither loads in MLX, so |
| every MLX consumer had to run the conversion itself and keep the result |
| somewhere local. This repo is that result, published once. |
|
|
| ## Files |
|
|
| | File | Size | | |
| |---|---|---| |
| | `lux_model.safetensors` | 468 MB | ZipVoiceDistill — fm_decoder + text_encoder + embeddings | |
| | `lux_vocoder.safetensors` | 61 MB | Vocos vocoder, MLX conv layout | |
| | `config.json` | — | model dimensions, 24 kHz feature config | |
| | `tokens.txt` | — | phoneme vocabulary | |
|
|
| fp32 on purpose. fp16 halves the download and is indistinguishable on a long, |
| clean reference — and audibly worse on a short one. Blind A/B on a clone made |
| from an 8-second phone recording: 4 of 8 fp16 renders had artefacts a listener |
| rejected, against 0 of 8 at fp32. If you are cloning from short user |
| recordings, use these. |
|
|
| ## Use |
|
|
| ```swift |
| // EngineKit (Gloam Voice Studio) |
| let model = try await LuxSpeechModel.load(from: weightsDirectory) |
| ``` |
|
|
| The directory needs all four files side by side. |
|
|
| ## Provenance and license |
|
|
| Converted from [YatharthS/LuxTTS](https://huggingface.co/YatharthS/LuxTTS), |
| Apache-2.0, which this repo inherits. The vocoder is |
| [Vocos](https://github.com/gemelo-ai/vocos). Conversion and publication by |
| [Tiny Trash Labs](https://tinytrashlabs.com) for |
| [Gloam Voice Studio](https://gloam.fm/studio). |
|
|
