Instructions to use BuilderHelm/Kanso-Koi-0.8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BuilderHelm/Kanso-Koi-0.8 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("BuilderHelm/Kanso-Koi-0.8")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use BuilderHelm/Kanso-Koi-0.8 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "BuilderHelm/Kanso-Koi-0.8"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "BuilderHelm/Kanso-Koi-0.8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use BuilderHelm/Kanso-Koi-0.8 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "BuilderHelm/Kanso-Koi-0.8"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "BuilderHelm/Kanso-Koi-0.8"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "BuilderHelm/Kanso-Koi-0.8",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use BuilderHelm/Kanso-Koi-0.8 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "BuilderHelm/Kanso-Koi-0.8"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default BuilderHelm/Kanso-Koi-0.8

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use BuilderHelm/Kanso-Koi-0.8 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "BuilderHelm/Kanso-Koi-0.8"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "BuilderHelm/Kanso-Koi-0.8" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Kanso Koi 0.8 (1.7B)

Names. ZenVoice's formatting models are called Kanso since ZenVoice 1.3.1: Kanso Koi 1.0 was ZenPolish v2.2 Lite, Koi 0.9 was ZenPolish v2.2, Koi 0.8 was ZenPolish v2, Kanso Satori 1.0 was ZenPolish v3.2 4B and Satori 0.9 was ZenPolish v3 4B. The repositories were renamed from zen-polish-…; old links and pinned revisions redirect here. Tables below use the development version numbers (v2, v2.1, v2.2, v3, v3.1, v3.2).

Retired. ZenVoice no longer offers this model; it stays here for earlier builds. Use Kanso-Koi-1.0 or Kanso-Satori-1.0.

ZenVoice's on-device dictation-enhancement model. Takes the raw, unpunctuated text produced by speech-to-text engines and restores everything dictation loses: punctuation, capitalization, filler removal, spoken numbers, dates, and times. Runs fully on-device on Apple Silicon via MLX — nothing leaves the Mac.

Base model: fine-tuned (LoRA) from Qwen3-1.7B, then merged and 4-bit quantized. Qwen3 is the starting point; the formatting behavior below is entirely the fine-tune.

Usage

ChatML prompt, thinking disabled:

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {"role": "user", "content": "um yeah so we need to fix this bug by tuesday right check the pull request"},
]
# -> "Yeah, so we need to fix this bug by Tuesday, right? Check the pull request."

The exact system prompt is in the ZenVoice repository (training/common.py).

Evaluation

Measured on ZenVoice's frozen eval sets (training/evaluate.py with the corrected word-only WER alignment and punctuation substitution accounting), greedy decoding, vs. stock Qwen3-1.7B-Instruct under the same prompt.

300-row synthetic eval — Koi 0.8 vs stock base:

Metric	Koi 0.8	Stock base
WER	5.0%	10.1%
Exact match	20.3%	11.3%
Punctuation F1	0.391	0.143
New-content (hallucination) rate	3.1%	4.3%
Capitalization accuracy	94.2%	89.9%

Clean real-input bench (120 rows): Koi 0.8 7.6% WER vs stock 11.0%, exact match 7.5% vs 5.0% — v2 stays ahead of stock on clean input. Its WER is higher on clean input than on noisy ASR-style input (7.6% vs 5.0%); identity-mix training in v3 closes that gap.

Scope

English-focused (v3 will broaden language coverage)
Formatting and cleanup only — never rewrites meaning, never adds content
Strengths: fillers, casing, punctuation, common dates/times/percent
Weak spots: email/URL rewriting, spoken money amounts, homophone repair

Training

Pipeline and recipe are in the ZenVoice repo under training/: noisifier (spoken-form degradation of clean text), synthetic + real ASR pair builders, frozen eval sets, mlx-lm LoRA training, and the gate harness. Weights: 4-bit MLX safetensors, 934 MB.

License

Apache-2.0, inherited from the Qwen3-1.7B base.

Published under BuilderHelm AI. Previously imYChaudhary22/Kanso-Koi-0.8; existing repository links and pinned revisions redirect to this organization repository. Model filenames and weights are unchanged.