#!/bin/bash
# Usage: transcribe.sh <audio_file> [model_size] [min_speakers] [max_speakers]

set -euo pipefail

source "$HOME/dev/whisperx/venv/bin/activate"

AUDIO_FILE="${1:?Usage: transcribe.sh <audio_file> [model] [min_spk] [max_spk]}"
MODEL="${2:-large-v3}"
MIN_SPK="${3:-2}"
MAX_SPK="${4:-3}"

if [[ -z "${HF_TOKEN:-}" ]]; then
  echo "ERROR: HF_TOKEN is not set. Export it first:" >&2
  echo "  export HF_TOKEN=hf_your_token_here" >&2
  exit 1
fi

whisperx "$AUDIO_FILE" \
  --model "$MODEL" \
  --language en \
  --diarize \
  --diarize_model pyannote/speaker-diarization-3.1 \
  --hf_token "$HF_TOKEN" \
  --min_speakers "$MIN_SPK" \
  --max_speakers "$MAX_SPK" \
  --compute_type int8 \
  --output_dir ./transcripts