Course Pass 12: Multimodal

Pass 12 extends the text platform to images and audio. This path is staged from the B14 design; module chapters and checkable module stages arrive when Step C merges and builds B14.

Part of: the course. Needs: Pass 11.

Gate: MS-P12, composed from the multimodal component milestones in B14.

Stages

Generated from path.tsv. Track progress locally with practice/bin/ol learn.

Stage	Read	Done when
1	Multimodal pass plan course/design/B14-multimodal.md	You can explain the image, speech, engine, gateway, and operations work planned for Pass 12.
2	Convolution as a linear map Convolution as a linear map	Your implementation of M12.1 passes its course checks.
3	Image tensors and layouts Image tensors and layouts	Your implementation of M12.2 passes its course checks.
4	Resampling and interpolation Resampling and interpolation	Your implementation of M12.3 passes its course checks.
5	DFT and FFT DFT and FFT	Your implementation of M12.4 passes its course checks.
6	Sampling, Nyquist, windows, and the STFT Sampling, Nyquist, windows, and the STFT	Your implementation of M12.5 passes its course checks.
7	Mel scale and filterbanks Mel scale and filterbanks	Your implementation of M12.6 passes its course checks.
8	Signals and images problem set Signals and images problem set: convolution, sampling, Fourier, mel, contrastive losses, and WER	You complete the S-M12 solve set and its check passes.