Modelpublic

beingpax/VoiceInk-Refine-V1

sourceHugging Faceotherupdated 2mo agoView on Hugging Face

0likes1.7kdownloads

Model Card

VoiceInk Refine V1

A compact cleanup model for VoiceInk. It turns raw speech-to-text output into clear, ready-to-use writing while keeping the speaker's meaning and tone.

It handles punctuation, capitalization, filler words, repetitions, spoken formatting cues, lists, and email-style paragraphs.

Model

VoiceInk Refine V1 is a task-specific fine-tune of Qwen3.5-2B for ASR transcript refinement. This release uses 4-bit post-training weight quantization.

Example

Input

text

hi maya comma quick update period new paragraph can we meet on friday question mark thanks comma daniel

Output

text

Hi Maya,

Quick update.

Can we meet on Friday?

Thanks,
Daniel

License

This model is provided for use with VoiceInk. See `LICENSE.md` for details.