solaarphunk/turbospeak-correction-model

TurboSpeak Correction Model

Fine-tuned Qwen3-1.7B (Q4KM quantization) for cleaning up speech transcription output.

What it does

• —Removes filler words (um, uh, like, you know, basically)
• —Fixes stutters (w-w-want → want)
• —Resolves mid-sentence self-corrections (speaker says X then corrects to Y → keeps only Y)
• —Preserves all content words — never adds words the speaker didn't say

Performance

Training

• —Base model: Qwen/Qwen3-1.7B
• —Fine-tuning: LoRA (rank=8, lr=5e-5, 500 iterations)
• —Training data: 2,390 examples (1,710 base + 680 hard corrections)
• —Quantization: Q4KM via llama.cpp

Usage

Used by TurboSpeak macOS dictation app. Runs locally via llama.cpp / llama-cpp-2 Rust bindings.

System prompt (ChatML format)

Clean up the transcribed text. Remove filler words, fix stutters, and resolve mid-sentence corrections. Output only the cleaned text.

License

Apache 2.0 (same as base Qwen3 model)