Instructions to use 0x56696B/S1-mini-dev-dictation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0x56696B/S1-mini-dev-dictation with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="0x56696B/S1-mini-dev-dictation")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("0x56696B/S1-mini-dev-dictation")
model = AutoModelForCausalLM.from_pretrained("0x56696B/S1-mini-dev-dictation", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use 0x56696B/S1-mini-dev-dictation with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf 0x56696B/S1-mini-dev-dictation:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf 0x56696B/S1-mini-dev-dictation:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf 0x56696B/S1-mini-dev-dictation:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf 0x56696B/S1-mini-dev-dictation:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf 0x56696B/S1-mini-dev-dictation:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf 0x56696B/S1-mini-dev-dictation:Q4_K_M

Use Docker

docker model run hf.co/0x56696B/S1-mini-dev-dictation:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use 0x56696B/S1-mini-dev-dictation with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0x56696B/S1-mini-dev-dictation"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0x56696B/S1-mini-dev-dictation",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0x56696B/S1-mini-dev-dictation:Q4_K_M

SGLang

How to use 0x56696B/S1-mini-dev-dictation with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "0x56696B/S1-mini-dev-dictation" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0x56696B/S1-mini-dev-dictation",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "0x56696B/S1-mini-dev-dictation" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0x56696B/S1-mini-dev-dictation",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use 0x56696B/S1-mini-dev-dictation with Ollama:
```
ollama run hf.co/0x56696B/S1-mini-dev-dictation:Q4_K_M
```
Unsloth Desktop

How to use 0x56696B/S1-mini-dev-dictation with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0x56696B/S1-mini-dev-dictation:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "0x56696B/S1-mini-dev-dictation:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use 0x56696B/S1-mini-dev-dictation with Docker Model Runner:
```
docker model run hf.co/0x56696B/S1-mini-dev-dictation:Q4_K_M
```

Lemonade

How to use 0x56696B/S1-mini-dev-dictation with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 0x56696B/S1-mini-dev-dictation:Q4_K_M

Run and chat with the model

lemonade run user.S1-mini-dev-dictation-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use 0x56696B/S1-mini-dev-dictation with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0x56696B/S1-mini-dev-dictation:Q4_K_M

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 0x56696B/S1-mini-dev-dictation:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use 0x56696B/S1-mini-dev-dictation with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0x56696B/S1-mini-dev-dictation:Q4_K_M

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 "0x56696B/S1-mini-dev-dictation:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

S1-mini-dev-dictation

This card is the README of the Hugging Face model repo. The LICENSE and NOTICE files in that repo are S1-mini's own files.

This model is "S1-mini" by "Superwhisper", fine-tuned for dictating software engineering, DevOps and AI-tooling text. It is a modified version of superwhisper/s1-mini, itself a fine-tune of Qwen/Qwen3-0.6B. The input format, the output style and the control line are unchanged: it is a drop-in replacement for S1-mini.

Naming (licence term)

The LICENSE adds one term to Apache 2.0: any use, distribution, or integration of this model, whether unmodified or as part of a derivative work or product, must continue to identify it by its original name, "S1-mini" by "Superwhisper", using that exact capitalization, regardless of any other name under which the model or a product incorporating it is marketed or distributed. "S1-mini-dev-dictation" is only the name of this fine-tune. The model is S1-mini by Superwhisper.

What changed

Modified from S1-mini (Apache 2.0, section 4(b) notice):

LoRA fine-tune (rank 16, scale 4.0, dropout 0.05) on every linear layer of all 28 blocks, trained with mlx-lm for 4 epochs at learning rate 1e-4, batch size 8. The loss covers the cleaned text only; the system prompt, control line, transcript and the empty <think> block are masked.
The adapter is merged into the bf16 weights. Architecture, vocabulary, tokenizer, chat template and system prompt are the original S1-mini files.
GGUF builds (Q8_0, Q4_K_M) are converted from the merged weights with llama.cpp.

Target behaviour added by the fine-tune (these are training targets, not measured results):

Spoken (ASR)	Written
`so the a d o ticket needs the m c p config`	`The ADO ticket needs the MCP config.`
`queen three point five four b through sherpa on x`	`Qwen3.5-4B through sherpa-onnx.`
`tilde slash dot omp slash agent slash watchdog dot yml`	`~/.omp/agent/WATCHDOG.yml`
`whisper dot c p p with the d e r metric`	`whisper.cpp with the DER metric`

A leading filler "so" is dropped. Dictated requests are cleaned, never answered.

Training data

Pairs of raw ASR-style transcripts and cleaned text, 1,248 rows in all (1,123 for training, 125 for validation):

249 pairs for the failure cases above, drafted with an AI assistant from the author's dictation style;
564 rows from sentence templates filled from a vocabulary list (written form, spoken forms, category), with injected fillers and self-corrections; the template outputs were drafted the same way;
36 transcripts cleaned by a larger model (Qwen3.5-9B) with a fixed instruction prompt, then read row by row (32 labels corrected);
399 synthetic general non-technical transcripts cleaned by stock S1-mini and then read row by row (59 labels corrected, 1 row dropped), to keep its general behaviour (anti-forgetting).

The rows cover all four styles (1,013 semi-formal, 81 formal, 78 casual, 76 semi-casual) and include 175 Context: email rows. 69 rows show a bullet list. Every row passes four checks: no number that the transcript does not say, no um, uh or er, no bullets under Structure: prose, and no kept leading "so" in the semi-formal and formal styles.

No private, customer or credential data is included. A held-out set was never trained on.

Usage

Identical to S1-mini. Send the system prompt and the control line exactly, decode greedily, and turn thinking off:

from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL = "0x56696B/S1-mini-dev-dictation"
tok = AutoTokenizer.from_pretrained(MODEL)
model = AutoModelForCausalLM.from_pretrained(MODEL, torch_dtype="auto")

SYSTEM = (
    "You are a text normalizer for speech-to-text transcripts. The input begins "
    "with a control line specifying the styling, structure, and context settings; "
    "clean the transcript to match those settings and output only the cleaned text."
)
control = "[Styling: semi-formal] [Structure: prose] [Context: general]"
messages = [
    {"role": "system", "content": SYSTEM},
    {"role": "user", "content": f"{control}\nso the a d o ticket needs the m c p config"},
]
text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False)
inputs = tok(text, return_tensors="pt")
out = model.generate(**inputs, max_new_tokens=256, do_sample=False)
print(tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

llama.cpp: llama-server -hf 0x56696B/S1-mini-dev-dictation:Q4_K_M --jinja --chat-template-kwargs '{"enable_thinking":false}' --temp 0.

Ollama: create a Modelfile that starts the assistant turn with the empty think block, set PARAMETER repeat_penalty 1 and PARAMETER temperature 0, and send "think": false with every request.

Evaluation

Held-out set: 59 cases never used in training, scored on the Q4_K_M GGUF through Ollama (greedy).

model	cases	exact match	word accuracy	char accuracy
S1-mini (base)	59	32.2%	78.2%	91.0%
S1-mini-dev-dictation (this model)	59	84.7%	93.8%	97.3%

On the ten examples in the S1-mini card (semi-formal, formal and casual, plus a list and an email) this model matches the card output in 9 and the base Q4_K_M build in 7.

Limitations

English only, tuned to one speaker's dictation vocabulary. Terms outside the training vocabulary get no special handling: tsconfig.json and parakeet-unified-en-0.6b are not built from the spoken parts.
Structure: lists and Context: email are not a focus of the fine-tune. It reproduces the list example in the S1-mini card but drops that example's leading "So", and one three-item lists case in the held-out set stayed prose.
Known held-out failures (9 of 59): the WATCHDOG.yml file name comes out lowercase, pyannote and WezTerm get a wrong capital, a sentence after a spoken "period" can start lowercase, spoken "colon" and "new line" can stay words, and one email case gets an extra comma.
Long run-on dictations: in a spot check of 15 long real dictations kept out of the training data, 4 outputs lost or changed words (a dropped clause, a dropped opening phrase, a rarely seen name replaced by a trained term). The base model kept more of the text there. Compare long outputs with the input.
Inherits the limits of S1-mini and Qwen3-0.6B. Check the output before you rely on it.

License

Apache License 2.0 plus the S1-mini naming term, the same terms as S1-mini. LICENSE and NOTICE are included unchanged. S1-mini is Copyright 2026 Superwhisper and a derivative of Qwen3-0.6B, Copyright 2024 Alibaba Cloud.

Citation

@misc{s1mini2026,
  title  = {S1-mini: a small text normalizer for speech-to-text output},
  author = {Superwhisper},
  year   = {2026},
  url    = {https://huggingface.co/superwhisper/s1-mini}
}

@misc{qwen3technicalreport,
  title         = {Qwen3 Technical Report},
  author        = {Qwen Team},
  year          = {2025},
  eprint        = {2505.09388},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2505.09388}
}