restructuring

Add torchcodec install for datasets 4.x audio decoding

Prepare training stack for RunPod: env-aware notebook + bootstrap script

Fix jiwer crash on post-normalisation empty refs; register SLR106/105 datasets

Fix SyntaxError in Cell 17: unterminated f-string literal

Fix compute_metrics crash on empty eval references in Fula training

Add Adlam/Pular Fula integration: transliterator + 3 new datasets + normalisation pipeline

Fix language mixing: per-language prompts + Mali Bambara / Guinea Pular context

Phase 3: Voice-to-Voice S2S pipeline — F5-TTS, LLM brain, CER metric

Fix Cell 16 ValueError: load model fp32 so AMP gradient scaler works

Fix Wikipedia and HF harvest buttons

Fix eval_loss nan + add generation_config to Seq2SeqTrainer

Fix GenerationConfig deprecation warning in cells 13 and 16

Auto-cap MAX_STEPS based on dataset size after Cell 12 builds train_ds

Fix Cell 15: detect eval_strategy vs evaluation_strategy at runtime

Proactive notebook audit: fix 5 issues before they cause errors

Simplify Cell 2: no restart needed since PEFT is removed

Fix Cell 16 TypeError: replace PEFT LoRA with freeze/unfreeze fine-tuning

Fix Cell 16 TypeError: target encoder-only LoRA to avoid PEFT/transformers 5.x conflict

Fix Cell 14: cast input_features to fp16 in collator

Fix Cell 16: remove tokenizer arg from Seq2SeqTrainer (renamed in transformers 5.x)

Fix Cell 14: replace evaluate.load('wer') with jiwer directly

Fix Cell 13: drop bitsandbytes, load whisper-small in fp16

Fix Cell 2: restart kernel after torchvision reinstall using sentinel file

Cell 12: never raise, let Cell 12b handle no-data case gracefully

Cell 4: remove Common Voice (moved to Mozilla Data Collective, off HF)

Fix Cell 12: add diagnostics + synthetic fallback cell (12b)

Fix Cell 11: bypass WhisperProcessor entirely to avoid torchvision crash

Fix Cell 2: reinstall torchvision to match Kaggle CUDA version at runtime

Fix Cells 2+11: unpin torch, use direct WhisperProcessor import

Fix Cell 10: correct r3 assertion to 'visit now!' (URL strips link not preceding word)

Fix Cell 10: add ! and ? to allowlist, fix smoke test assertions

Fix Cell 8: remove FLEURS fallback + strip emoji (charmap safe)

Fix Kaggle push: title slug + Windows UTF-8 encoding

Add Kaggle auto-sync: kernel-metadata.json + post-commit hook

Fix Cell 8: correct WaxalNLP subset names + drop fleurs fallback

Fix Cell 6: replace get_last_checkpoint import with inline scanner

Add Kaggle Master Trainer — Deep Sleep fine-tuning notebook

Phase 2: Waxal TTS — Bambara voice output + Fula training notebook

Initial commit: Sahel-Agri Voice AI