Lmaana 2.2 is a Moroccan Darija automatic speech recognition model built by fully fine-tuning OmniASR CTC 3B v2 with a CTC objective. It was trained on Dataset13 clean v4 with two-node FSDP and evaluated with greedy CTC decoding. The released checkpoint is step8000. Training continued to step 8,500, where validation improved further, but that state was not checkpointed before the 24-hour HPC allocation ended. All release results below therefore refer to the reproducible, saved step8000 checkpoint. The validation and test sets are disjoint Dataset13 clean v4 splits. UER is the tokenizer-unit error rate reported by fairseq2; it should not be presented as CER unless the tokenizer units are…