We developed and evaluated a pipeline combining Mistral Large LLM and a postprocessing phase. The pipeline's performance was assessed both at document and patient levels. For evaluation, two data sets ...

Thank you for your interest in contributing to our Repo! Pull requests are welcome. For fixing typos, please make a PR with your fixes. We are happy for every contribution. A lot can be done with this ...

Clone and fine-tune voices using Qwen3-TTS on Apple Silicon (MLX). Full pipeline: source audio → split → transcribe → prepare codec tokens → LoRA training → inference → ASR verification. Use when the ...