Align Whisper default to turbo-v3 + add document upload to Knowledge Base tab

Fix WhisperProcessor import in reload + upgrade base to large-v3-turbo

Fix mel-bin mismatch: load per-language processor from fine-tuned checkpoint

Fix Self-Teaching language detection: parse code from dropdown label

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

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

Fix model loading stuck forever + unhandled TTS crash in conversation mode

Fix 'Model loading' stuck state: block in _do_asr until Whisper is ready

Fix conversation mode timeout: two-stage pipeline + faster LLM

Add real conversational memory + live learning to Conversation Mode

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

Fix Self-Teaching tab: float sliders, deduplication, Kaggle API fallback

Fix Kaggle trigger 401: pass credentials as env vars instead of KAGGLE_CONFIG_DIR

Fix kaggle trigger: use kaggle binary not python -m kaggle

Fix Kaggle trigger: use kaggle CLI push instead of fake /run endpoint

Fix Wikipedia and HF harvest buttons

Add mass training + internet self-teaching features

Align Space app with Kaggle notebook training pipeline

Fix: replace YouTube download with audio upload (HF Spaces blocks outbound HTTP)

Add phrase library + fuzzy matcher for general Bambara/Fula conversation

Improve Bambara/Fula quality + add full correction UI

Fix: disable SSR mode and use port 7860 to unblock HF Spaces startup

Fix: use direct WhisperProcessor/WhisperForConditionalGeneration imports

Fix: robust Whisper import + upgrade Gradio to fix API schema crash

Fix: use AutoModelForSpeechSeq2Seq for transformers 5.x; disable buggy API schema endpoint

Fix: upgrade to Gradio 5 (HfFolder removed from huggingface-hub 1.x)

Initial commit: Sahel-Agri Voice AI