fmt

transcribe

@@ -24,8 +24,14 @@ usage() {
 }
 while [[ $# -gt 0 ]]; do
     case $1 in
-        --srt) srt=true; shift ;;
-        --no-diarization) diarization=false; shift ;;
+        --srt)
+            srt=true
+            shift
+            ;;
+        --no-diarization)
+            diarization=false
+            shift
+            ;;
         --speakers)
             if [[ ! ${2:-} =~ ^([1-9]|[1-5][0-9]|6[0-4])$ ]]; then
                 echo '--speakers must be an integer between 1 and 64' >&2
@@ -66,9 +72,18 @@ while [[ $# -gt 0 ]]; do
             chunk_minutes=$2
             shift 2
             ;;
-        -h|--help) usage; exit 0 ;;
-        --) shift; break ;;
-        -*) usage >&2; exit 1 ;;
+        -h | --help)
+            usage
+            exit 0
+            ;;
+        --)
+            shift
+            break
+            ;;
+        -*)
+            usage >&2
+            exit 1
+            ;;
         *) break ;;
     esac
 done
@@ -91,7 +106,7 @@ if [[ ! -f $1 || ! -r $1 ]]; then
     echo "Cannot read audio file: $1" >&2
     exit 1
 fi
-if (( BASH_VERSINFO[0] < 5 || (BASH_VERSINFO[0] == 5 && BASH_VERSINFO[1] < 1) )); then
+if ((BASH_VERSINFO[0] < 5 || (BASH_VERSINFO[0] == 5 && BASH_VERSINFO[1] < 1))); then
     echo 'Bash 5.1 or newer is required for parallel chunk processing.' >&2
     exit 1
 fi
@@ -103,6 +118,8 @@ for tool in "${dependencies[@]}"; do
     }
 done
 
+PYANNOTE_API_KEY_REF="op://API Keys/pyannote-api/credential"
+
 # Explicit environment keys also work in headless sessions without 1Password.
 # Resolve both credentials before starting any paid requests.
 if "$diarization" && [[ -z ${PYANNOTE_API_KEY:-} ]]; then
@@ -177,7 +194,7 @@ save_diagnostic "$tmp/chunks.json" chunks.json
 count=$(jq 'length' "$tmp/chunks.json")
 timestamps=$srt
 if "$diarization"; then timestamps=true; fi
-if (( count > 1 )); then
+if ((count > 1)); then
     timestamps=true
     echo "Splitting audio into $count overlapping chunks (maximum $chunk_minutes minutes each)." >&2
     echo "Processing up to $jobs chunks in parallel." >&2
@@ -190,7 +207,7 @@ transcribe_chunk() {
     mkdir -- "$work"
     read -r start duration < <(jq -r --argjson i "$i" \
         '.[$i] | "\(.start) \(.end - .start)"' "$tmp/chunks.json")
-    if (( count > 1 )); then
+    if ((count > 1)); then
         echo "Transcribing chunk $((i + 1))/$count (start ${start}s, duration ${duration}s)..." >&2
     fi
     ffmpeg -nostdin -hide_banner -loglevel error -y -ss "$start" -i "$tmp/audio.wav" \
@@ -255,8 +272,8 @@ wait_for_worker() {
 # response filenames retain recording order regardless of completion order.
 set -m
 next=0
-while (( next < count || ${#workers[@]} > 0 )); do
-    while (( next < count && ${#workers[@]} < jobs )); do
+while ((next < count || ${#workers[@]} > 0)); do
+    while ((next < count && ${#workers[@]} < jobs)); do
         transcribe_chunk "$next" &
         workers[$!]=$next
         next=$((next + 1))
@@ -270,7 +287,7 @@ while (( next < count || ${#workers[@]} > 0 )); do
     fi
 done
 # Only emit a transcript after every chunk succeeds, including SRT conversion.
-if "$diarization" || "$srt" || (( count > 1 )); then
+if "$diarization" || "$srt" || ((count > 1)); then
     python3 -B "$script_dir/chunks.py" merge "$tmp/chunks.json" --json >"$tmp/transcript.json"
 else
     cp -- "$tmp/response-0.json" "$tmp/transcript.json"