Text-to-Speech
MLX
Safetensors
step1
tts
speech
voice-cloning
audio-editing
step-audio
step-audio-editx
stepfun
quantized
int8
apple-silicon
bundled-components
custom_code
Instructions to use appautomaton/step-audio-editx-8bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use appautomaton/step-audio-editx-8bit-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir step-audio-editx-8bit-mlx appautomaton/step-audio-editx-8bit-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "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, | |
| "quantization": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| } | |
| } | |