# Real-time processing

This is an open-source model using the Apache-2.0 license; specific details need to be supplemented

A language detection model fine-tuned based on openai/whisper-small, achieving 96.47% accuracy on the evaluation set

A lightweight lane line detection model based on the SegFormer architecture, fine-tuned for 10,000 steps on the lane_master dataset

This model is an open-source model based on the MIT license, with a CER (Character Error Rate) of 0.0019, indicating high accuracy in specific tasks.

Speaker diarization model based on pyannote.audio 2.1.1, used for automatic detection of speaker changes and overlap speech in audio

This is a well-performing model with a test accuracy of 91.17% and a test loss of 0.241.