CobuildX-AI/cbx-healthcare-speech-to-text-0.6B

https://huggingface.co/CobuildX-AI/cbx-healthcare-speech-to-text-0.6B
Activeby CobuildX-AI604updated 4 days ago
Python

Accurately transcribes English doctor–patient conversations. It recognises medical conditions correctly 94.6% of the time (base model: 83.9%) and medicine names 66.1% (base: 61.2%) in consultations, while matching the base model's accuracy on everyday words.

Sourced from

  • HuggingFace — CobuildX-AI/cbx-healthcare-speech-to-text-0.6B

Related resources

Active145 months ago
Python

A medical question-answering LoRA trained to provide safe, cautious, general medical information, based on verified and well-structured Q&A data.

Idle161 year ago
Python
Active03 months ago
Python

This repository contains LoRA finetunes of DiffusionGemma (image-conditioned discrete-diffusion LLM) for radiology visual question answering, each paired with an autoregressive Gemma-4 finetune as a controlled baseline. It corresponds to the paper Discrete Diffusion Language Models for Interactive…

Active04 months ago
Python

Typed-decision adapter for Qwen3.5-4B, tuned on clinical question answering, financial news sentiment and structured record-level workflow decisions.

Active561 month ago
Python