Audio-to-Audio
MLX
Safetensors
English
Chinese
step1
speech-editing
step-audio
stepfun
quantized
8bit
custom_code
Instructions to use mlx-community/Step-Audio-EditX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Step-Audio-EditX-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/Step-Audio-EditX-8bit --local-dir Step-Audio-EditX-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download flow-model-config.json from mlx-community/Step-Audio-EditX-8bit: direct link, hf CLI and curl.
- Browser
- Download file 536 Bytes
-
https://huggingface.co/mlx-community/Step-Audio-EditX-8bit/resolve/main/flow-model-config.json
- Command line
-
hf download hf://mlx-community/Step-Audio-EditX-8bit/flow-model-config.json
-
curl -L -o flow-model-config.json https://huggingface.co/mlx-community/Step-Audio-EditX-8bit/resolve/main/flow-model-config.json
536 Bytes
| { | |
| "input_size": 512, | |
| "output_size": 80, | |
| "spk_embed_dim": 192, | |
| "vocab_size": 5121, | |
| "encoder_output_size": 512, | |
| "pre_lookahead_len": 3, | |
| "num_blocks": 6, | |
| "num_up_blocks": 4, | |
| "up_stride": 2, | |
| "up_scale_factor": 2.0, | |
| "attention_heads": 8, | |
| "linear_units": 2048, | |
| "key_bias": true, | |
| "estimator_in_channels": 320, | |
| "estimator_out_channels": 80, | |
| "estimator_hidden_size": 512, | |
| "estimator_depth": 16, | |
| "estimator_num_heads": 8, | |
| "estimator_head_dim": 64, | |
| "estimator_mlp_ratio": 4.0, | |
| "inference_cfg_rate": 0.7 | |
| } | |