CoolFace
Modelpublic

Enriqueag26/keysay-transcription-cleaner-0.8B-8bit

sourceHugging Faceupdated 7mo agoView on Hugging Face
0likes12downloads
Model Card

keysay-transcription-cleaner-0.8B-8bit

A fine-tuned Qwen3.5-0.8B VLM that cleans speech transcriptions into ready-to-send chat messages. Removes self-corrections and filler words while preserving the speaker's intended meaning.

What it does

Input (messy speech)Output (clean message)
es a las 5, no perdón, a las 6es a las 6
I think we should, um, you know, go with the first option, no wait, the second one is betterI think we should go with the second one is better
Bueno, pues, o sea, la reunión es el martes a las tres.La reunión es el martes a las tres.
el precio es 100, no 200, no perdón, 150 eurosel precio es 150 euros
habla con María, no perdón, con Carlos sobre el proyectohabla con Carlos sobre el proyecto

Training

  • —Method: LoRA fine-tuning + fusion
  • —Base model: mlx-community/Qwen3.5-0.8B-8bit
  • —Teacher: Google Gemini Flash (knowledge distillation)
  • —Dataset: 360 examples (70% Spanish, 30% English) covering self-corrections, filler removal, nested corrections, and passthrough
  • —Eval score: 12/12 on hand-verified test suite (base model: 0/12)

Usage

python
from mlx_lm import load, generate

model, tokenizer = load("Enriqueag26/keysay-transcription-cleaner-0.8B-8bit")

system = """You clean speech-to-text transcriptions into ready-to-send chat messages.

Remove self-corrections (keep only the final version). Remove filler words.
Never rephrase. Never add words. Keep the original language."""

messages = [
    {"role": "system", "content": system},
    {"role": "user", "content": "es a las 5, no perdón, a las 6"},
]
prompt = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True,
    enable_thinking=False,
)
result = generate(model, tokenizer, prompt=prompt, max_tokens=500)
print(result)  # "es a las 6"

Part of keysay

A macOS press-to-dictate app that uses Qwen3-ASR for speech recognition, a VLM for screen context extraction, and this model for transcription cleaning.