README.md

metadata

license: apache-2.0
base_model: stepfun-ai/Step-Audio-EditX
library_name: mlx
pipeline_tag: audio-to-audio
language:
  - en
  - zh
tags:
  - mlx
  - speech-editing
  - step-audio
  - stepfun
  - quantized
  - 8bit

Step-Audio-EditX — int8 MLX bundle

Step-Audio-EditX (StepFun, Apache-2.0): a 3 B audio LLM that re-delivers an existing take — emotion, speaking style, inserted paralinguistics (laughter, sighs, breaths), denoise, silence trim — in the same voice, plus zero-shot cloning. This is the bf16 bundle with the step1 LM quantised to 8 bits (affine, group 64, every Linear and the embeddings — model.safetensors 3.75 GB instead of 7.06 GB); the tokenizers, flow, HiFT and CAM++ are the bf16 files unchanged. config.json carries "quantization": {"bits": 8, "group_size": 64, "mode": "affine"}.

The quantised weights were written by the Swift consumer itself from the bf16 bundle (editx-gates --write-int8-bundle, quantised on MLX's CPU stream), so loading this bundle reproduces quantise-at-load exactly.

file	component	source
model.safetensors (3.75 GB, int8) + config.json	step1 LM — 32 × 3072, 48 heads / 4 KV groups, sqrt-ALiBi	stepfun-ai/Step-Audio-EditX
vq02.safetensors, vq06.safetensors, step-audio-tokenizer-assets.safetensors + configs	the dual tokenizer (bf16)	FunASR Paraformer (FunASR model licence) / stepfun-ai/Step-Audio-Tokenizer
flow-model.safetensors, flow-conditioner.safetensors, hift.safetensors, campplus.safetensors + configs	flow, vocoder, speaker (bf16)	StepFun-trained / Alibaba CAM++ (Apache-2.0)
tokenizer.json, tokenizer_config.json, frontend-config.json	text tokenizer, mel front end	derived from tokenizer.model

Consumers

• Swift: xocialize/mlx-step-audio-editx-swift ≥ 0.1.1 — EditXPipeline.load(bundle:) reads the quantisation from config.json.
• Python: mlx-speech loads int8 LM bundles of this layout (its --bits 8 converter writes the same keys).

Measured (M5 Max, the Swift consumer, the E19 evaluation cues)

• Resident 6.2 GB phys_footprint after load (MLX active 5.7 GB); MLX peak 7.3–7.7 GB per edit; real-time factor 0.51–0.53 (bf16: 0.72–0.75); loads in 0.5 s.
• Content survives every edit (ASR error 0.000 on the four test edits), speaker similarity 0.83–0.97 to the source, DNSMOS 3.45–3.49 — the same bars as bf16 and the torch reference. Sampled tokens differ from bf16's at near-ties, as any quantised tier's do.

Licence

Apache-2.0 (StepFun) for the LM, flow, HiFT and the S3 tokenizer; the Paraformer encoder under the FunASR model licence; CAM++ Apache-2.0 (Alibaba / 3D-Speaker). Quantised and re-hosted by xocialize for mlx-community.