core/stt.py

# core/stt.py
"""Whisper audio → text (EN/BN).

Uses get_config().stt_model (EN) or stt_bn_model (BN, if set), transcribed on
Modal. Returns '' on failure so the caller can fall back to typed input — the
primary, reliable path for Bengali especially (CLAUDE.md §2, §14). Never raises.
"""

from core.model_config import UI_MOCK, get_config
from core.modal_infra import transcribe_remote


def transcribe(audio_path: str, language: str) -> str:
    """language is 'en' or 'bn'. Returns '' on failure. Never raises."""
    if UI_MOCK:  # local UI dev — no Modal/GPU
        return "tell me a story about my dragon"
    if not audio_path:
        return ""
    cfg = get_config()
    if language == "bn" and cfg.stt_bn_model:
        model = cfg.stt_bn_model
    else:
        model = cfg.stt_model
    try:
        with open(audio_path, "rb") as f:
            audio_bytes = f.read()
        return transcribe_remote(audio_bytes, language, model) or ""
    except Exception as e:  # noqa: BLE001 — never raise; caller uses typed input
        print(f"[stt.py] transcription failed: {e}")
        return ""