Add real-life reference meeting sample
- add reproducible real-world meeting sample - store meeting audio using Git LFS - include raw and cleaned Whisper transcripts - add manifest with SHA-256 checksums - document sample usage and confidentiality - intentionally exclude generated pipeline artifacts
This commit is contained in:
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"sample_id": "project_process_meeting",
|
||||
"title": "Project Process Meeting",
|
||||
"language": "de",
|
||||
"audio_file": "audio/meeting_speech.wav",
|
||||
"raw_transcript_file": "transcript/meeting_speech.json",
|
||||
"cleaned_transcript_file": "transcript/meeting_speech_cleaned.json",
|
||||
"reference_protocol_file": null,
|
||||
"audio_format": "WAV PCM 16-bit mono 16000 Hz",
|
||||
"transcript_format": "Whisper JSON",
|
||||
"created_from_existing_project_data": true,
|
||||
"notes": [
|
||||
"Deliberately versioned real-life reference sample for reproducible Meeting Lab testing.",
|
||||
"Contains real meeting data; repository must remain private.",
|
||||
"Generated chunks, normalized chunks, segmentation outputs, extraction JSON, consolidated outputs and generated protocols are intentionally excluded.",
|
||||
"No exact human-written reference protocol file was found in the repository workspace, so reference_protocol_file is null."
|
||||
],
|
||||
"checksums": {
|
||||
"audio/meeting_speech.wav": {
|
||||
"sha256": "d763b8886f089c49ed3bcc2813dfb3a78ae2fd03eee6d843bbee1c52686bf380",
|
||||
"bytes": 179592270
|
||||
},
|
||||
"transcript/meeting_speech.json": {
|
||||
"sha256": "55ea11571ce43ad299b00362bd1d9b92555aa9d1865779bf9b47ee89138e92ef",
|
||||
"bytes": 542337
|
||||
},
|
||||
"transcript/meeting_speech_cleaned.json": {
|
||||
"sha256": "22e8616a946a3f46f66ea56e8d80174b44f49a1c14dc297ea0405dee0afbdd3c",
|
||||
"bytes": 800585
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user