Foundation audio intelligence
Foundation Models & Olympiad Practice
Foundation audio intelligence
| Topic | Subtopic | Category | Lab link |
|---|---|---|---|
| Audio Processing | Pre-trained Audio Encoders (HuBERT) | Practice | MFCC / features · Embedding lab |
| Audio Models | Qwen-Audio, Whisper, Voxtral | Practice | ASR tasks |
| NLP (cross-track) | Text Classification, BERT encoders | Both | NLP (soon) |
| NLP | Language Modeling & Encoder-Decoder | Both | NLP (soon) |
| Computer Vision | Detection, Segmentation, CLIP, Diffusion | Practice | CV (soon) |
| Neural Networks | Attention, Transformers, Finetuning | Both | NN & DL (soon) |