Instructions to use tinytrashlabs/Audio8-TTS-0.6B-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use tinytrashlabs/Audio8-TTS-0.6B-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download tinytrashlabs/Audio8-TTS-0.6B-MLX --local-dir Audio8-TTS-0.6B-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Audio8-TTS-0.6B-MLX
A repack of Edge0/Audio8-TTS-Realistic-0.6b
(source revision 1e857568bfd4f02931aca3988ee773a44d2d26d3) by Edge0, licensed under Apache 2.0. All credit for the model goes to Edge0.
This repo only rearranges the weights so the Fish DualAR loader in
TinyTrashLabs/mlx-audio-swift (PR #20) can load them:
the slow and fast transformer tensors are stored under model.* in model.safetensors, the codec is
converted from codec.pth to codec.safetensors, and config.json is written in the fish_qwen3_omni layout.
No weights are altered or quantised.
Audio8-specific config keys
max_frames_per_text_token: 12.0reference_budget_scale: 1.95
Everything else in config.json is the Fish layout with scale_codebook_embeddings: false.
Licence
Apache 2.0. See LICENSE and NOTICE (copied from the source repo).
- Downloads last month
- 53
Quantized
Model tree for tinytrashlabs/Audio8-TTS-0.6B-MLX
Base model
Edge0/Audio8-TTS-Preview-0.6b