feat: transcribe long recordings in overlapping chunks
Sending entire recordings in one request can exceed provider limits. Decode audio once to a shared PCM sample clock and split uploads at a configurable maximum of 1 to 30 minutes, defaulting to 30 minutes. Prefer nearby pauses and include six seconds of overlap to protect words at audio cuts while keeping each encoded MP3 within the duration cap. Request word timestamps for chunked text and SRT output. Match overlapping words and times to retain each passage once, warn when a join falls back to timestamps, and generate SRT cues on the original recording timeline. Reuse subtitle timestamp validation without reordering regressing words. Only emit output after every request and conversion succeeds. Document the Python dependency, temporary storage, boundary limitations, and lack of automatic retry or resume. Keep single-request text formatting. Test Plan: - python3 -B -m unittest -v: all 29 tests passed, including mocked provider failures, native MP3 payload checks, boundary stitching, and SRT timing. - bash -n transcribe and shellcheck transcribe: passed. - git diff --cached --check: passed. - Locally decoded and encoded the supplied 74-minute WebM into three MP3 chunks; ffprobe confirmed each duration was below 30 minutes. - Live transcription was not verified: the configured 1Password credential was unavailable.
This commit is contained in:
ddidderr committed
1 parent
300203d33f
commit
a5c535cfb9
7 files changed
+635
-57
No files matched your search
+76
-35
@@ -3,18 +3,32 @@
|
||||
set -euo pipefail
|
||||
|
||||
srt=false
|
||||
if [[ ${1:-} == --srt ]]; then
|
||||
srt=true
|
||||
shift
|
||||
fi
|
||||
if [[ $# == 1 && ($1 == -h || $1 == --help) ]]; then
|
||||
echo "Usage: ${0##*/} [--srt] AUDIO_FILE"
|
||||
chunk_minutes=30
|
||||
usage() {
|
||||
echo "Usage: ${0##*/} [--srt] [--chunk-minutes 1..30] AUDIO_FILE"
|
||||
echo 'Transcribe audio using OPENROUTER_API_KEY; print the text to stdout.'
|
||||
echo ' --srt Print SRT subtitles in short cues using word timestamps instead.'
|
||||
exit 0
|
||||
fi
|
||||
echo ' --chunk-minutes N Maximum upload duration in minutes (default: 30).'
|
||||
}
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case $1 in
|
||||
--srt) srt=true; shift ;;
|
||||
--chunk-minutes)
|
||||
if [[ ! ${2:-} =~ ^([1-9]|[12][0-9]|30)$ ]]; then
|
||||
echo '--chunk-minutes must be an integer between 1 and 30' >&2
|
||||
exit 1
|
||||
fi
|
||||
chunk_minutes=$2
|
||||
shift 2
|
||||
;;
|
||||
-h|--help) usage; exit 0 ;;
|
||||
--) shift; break ;;
|
||||
-*) usage >&2; exit 1 ;;
|
||||
*) break ;;
|
||||
esac
|
||||
done
|
||||
if [[ $# != 1 ]]; then
|
||||
echo "Usage: ${0##*/} [--srt] AUDIO_FILE" >&2
|
||||
usage >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ ! -f $1 || ! -r $1 ]]; then
|
||||
@@ -24,10 +38,7 @@ fi
|
||||
export OPENROUTER_API_KEY
|
||||
OPENROUTER_API_KEY="$(op read "op://API Keys/openrouter-mai-transcribe-2/credential")"
|
||||
: "${OPENROUTER_API_KEY:?Set OPENROUTER_API_KEY first}"
|
||||
dependencies=(ffmpeg curl jq base64 mktemp)
|
||||
if "$srt"; then
|
||||
dependencies+=(python3)
|
||||
fi
|
||||
dependencies=(ffmpeg curl jq base64 mktemp python3)
|
||||
for tool in "${dependencies[@]}"; do
|
||||
command -v "$tool" >/dev/null || {
|
||||
echo "Missing dependency: $tool" >&2
|
||||
@@ -39,31 +50,61 @@ tmp=$(mktemp -d)
|
||||
trap 'rm -rf -- "$tmp"' EXIT
|
||||
trap 'exit 130' INT
|
||||
trap 'exit 143' TERM
|
||||
script_dir=$(dirname -- "$(realpath -- "$0")")
|
||||
|
||||
# Normalize any FFmpeg-readable audio (or the first audio track in a video).
|
||||
# Decode once so duration, pause detection, and all cuts share a sample clock.
|
||||
# This also works for inputs whose container omits or misreports the duration.
|
||||
ffmpeg -nostdin -hide_banner -loglevel error -i "$(realpath -- "$1")" \
|
||||
-map 0:a:0 -ac 1 -ar 16000 -c:a libmp3lame -b:a 64k "$tmp/audio.mp3"
|
||||
-map 0:a:0 -ac 1 -ar 16000 -c:a pcm_s16le "$tmp/audio.wav"
|
||||
python3 "$script_dir/chunks.py" plan "$tmp/audio.wav" "$chunk_minutes" >"$tmp/chunks.json"
|
||||
count=$(jq 'length' "$tmp/chunks.json")
|
||||
timestamps=$srt
|
||||
if (( count > 1 )); then
|
||||
timestamps=true
|
||||
echo "Splitting audio into $count overlapping chunks (maximum $chunk_minutes minutes each)." >&2
|
||||
fi
|
||||
|
||||
# Keep large audio payloads out of shell arguments (which have a size limit).
|
||||
base64 <"$tmp/audio.mp3" | tr -d '\n\r' >"$tmp/audio.b64"
|
||||
jq -n --rawfile data "$tmp/audio.b64" --argjson srt "$srt" \
|
||||
'{model: "microsoft/mai-transcribe-2", input_audio: {data: $data, format: "mp3"}}
|
||||
+ (if $srt then {response_format: "verbose_json", timestamp_granularities: ["segment", "word"]}
|
||||
else {} end)' \
|
||||
>"$tmp/request.json"
|
||||
for ((i = 0; i < count; i++)); do
|
||||
read -r start duration < <(jq -r --argjson i "$i" \
|
||||
'.[$i] | "\(.start) \(.end - .start)"' "$tmp/chunks.json")
|
||||
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 "$tmp/audio.wav" \
|
||||
-t "$duration" -map 0:a:0 -ac 1 -ar 16000 -c:a libmp3lame -b:a 64k "$tmp/audio.mp3"
|
||||
|
||||
curl --silent --show-error --fail-with-body \
|
||||
https://openrouter.ai/api/v1/audio/transcriptions \
|
||||
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
|
||||
-H 'Content-Type: application/json' \
|
||||
--data-binary @"$tmp/request.json" -o "$tmp/response.json" || {
|
||||
cat "$tmp/response.json" >&2
|
||||
exit 1
|
||||
}
|
||||
if "$srt"; then
|
||||
python3 "$(dirname -- "$(realpath -- "$0")")/subtitles.py" "$tmp/response.json"
|
||||
# Keep large audio payloads out of shell arguments (which have a size limit).
|
||||
base64 <"$tmp/audio.mp3" | tr -d '\n\r' >"$tmp/audio.b64"
|
||||
jq -n --rawfile data "$tmp/audio.b64" --argjson timestamps "$timestamps" \
|
||||
'{model: "microsoft/mai-transcribe-2", input_audio: {data: $data, format: "mp3"}}
|
||||
+ (if $timestamps then {response_format: "verbose_json", timestamp_granularities: ["segment", "word"]}
|
||||
else {} end)' \
|
||||
>"$tmp/request.json"
|
||||
|
||||
curl --silent --show-error --fail-with-body \
|
||||
https://openrouter.ai/api/v1/audio/transcriptions \
|
||||
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
|
||||
-H 'Content-Type: application/json' \
|
||||
--data-binary @"$tmp/request.json" -o "$tmp/response-$i.json" || {
|
||||
echo "Transcription failed for chunk $((i + 1))/$count." >&2
|
||||
if [[ -f $tmp/response-$i.json ]]; then
|
||||
cat "$tmp/response-$i.json" >&2
|
||||
fi
|
||||
exit 1
|
||||
}
|
||||
jq -e 'if .error then error("Transcription failed: " + (.error | tostring))
|
||||
elif (.text | type) == "string" then true
|
||||
else error("Transcription failed: missing text in response") end' \
|
||||
"$tmp/response-$i.json" >/dev/null
|
||||
done
|
||||
|
||||
# Only emit a transcript after every chunk succeeds, including SRT conversion.
|
||||
if (( count > 1 )); then
|
||||
format=()
|
||||
if "$srt"; then format+=(--srt); fi
|
||||
python3 "$script_dir/chunks.py" merge "$tmp/chunks.json" "${format[@]}"
|
||||
elif "$srt"; then
|
||||
python3 "$script_dir/subtitles.py" "$tmp/response-0.json"
|
||||
else
|
||||
jq -r 'if (.text | type) == "string" then .text
|
||||
else error("Transcription failed: " + (.error.message // tojson)) end' \
|
||||
"$tmp/response.json"
|
||||
jq -r .text "$tmp/response-0.json"
|
||||
fi
|
||||
Reference in new issue
Block a user