Pyannote Diarizer
@mgreten/pyannote-diarizerv2026.07.16.1
01README
Apply pyannote/speaker-diarization-3.1 to a Whisper transcript JSON and tag each segment with a speaker label. Requires Python + pyannote.audio and a Hugging Face token (gated model). Falls back gracefully — a failed diarization never blocks the pipeline; the original transcript is returned unchanged.
02Release Notes
Rebuild against swamp CLI 20260716
03Models
@mgreten/pyannote-diarizerv2026.07.16.1pyannote_diarizer.ts
fn diarize(transcriptJson: string, audioPath: string, instanceName?: string)
Apply pyannote speaker diarization to a Whisper transcript. Falls back gracefully on error.
| Argument | Type | Description |
|---|---|---|
| transcriptJson | string | Whisper JSON transcript content |
| audioPath | string | Absolute path to the source audio file |
| instanceName? | string | Resource instance name |
Resources
diarizedTranscript(infinite)— Whisper transcript with speaker labels (or original on fallback)
04Previous Versions
2026.06.27.1
Added 1, removed 1 models
2026.05.28.5
2026.05.28.4
2026.05.28.3
2026.05.28.2
2026.05.28.1
05Stats
A
100 / 100
Downloads
10
Archive size
7.2 KB
- Has README or module doc2/2earned
- README has a code example1/1earned
- README is substantive1/1earned
- Most symbols documented1/1earned
- No slow types (deprecated)1/1earned
- Dependencies pass trust audit2/2earned
- Has description1/1earned
- Platform support declared (or universal)2/2earned
- License declared1/1earned
- Verified public repository2/2earned
06Platforms
07Labels