Space Talkers

A diarization viewer for Whisper transcription output

Features

• Speaker visualization: Speakers displayed as animated orbs in a starfield
• Real-time transcription: Live transcript panel following audio playback
• Waveform navigation: Click/drag on the waveform to seek through the audio
• Keyboard controls: Space to play/pause, Arrow keys to seek

Keyboard Shortcuts

Key	Action
Space	Play/Pause
← / A	Seek back 10 seconds
→ / D	Seek forward 10 seconds
Shift + ←/→	Seek 60 seconds

Quick Start

1. Place your audio file in input/
2. Place your Whisper transcript JSON in outputs/float32/
3. Generate the waveform data (see below)
4. Start a local server and open in browser:

   npx serve -p 5000
   

   Then navigate to http://localhost:5000

Waveform Generation

For optimal performance with long audio files (1-3 hours), waveform data is pre-generated as JSON rather than decoded in the browser.

Prerequisites

• Node.js (v14+)
• FFmpeg installed and available in PATH

Generate Waveform Data

node scripts/generate-waveform.js <input-audio> [output-json] [columns]

Arguments:

• input-audio - Path to the audio file (opus, mp3, wav, etc.)
• output-json - Output path for waveform JSON (default: <input>.waveform.json)
• columns - Number of waveform columns/peaks (default: 1000)

Example:

# Generate waveform for a single file
node scripts/generate-waveform.js input/amuta_2026-01-12_1.opus outputs/float32/amuta_2026-01-12_1.waveform.json

# Or let it auto-generate the output path
node scripts/generate-waveform.js input/meeting.opus

Configuration

Edit the paths at the top of app.js:

const transcriptPath = "outputs/float32/amuta_2026-01-12_1.json";
const waveformPath = "outputs/float32/amuta_2026-01-12_1.waveform.json";

Speaker Labels

Map speaker IDs to display names in app.js: supports merging names

const SPEAKER_LABELS = {
  "SPEAKER_01": "Maya",
  "SPEAKER_02": "SPEAKER_23","SPEAKER_4",
};

File Structure

amuta-meetings/
├── index.html              # Main HTML page
├── app.js                  # Application logic
├── styles.css              # Styles
├── scripts/
│   └── generate-waveform.js  # Waveform generator script
├── input/                  # Audio files (gitignored)
├── outputs/
│   └── float32/            # Transcript and waveform JSON

Transcription with WhisperX (GPU or CPU)

For transcribing audio with speaker diarization, we used WhisperX on a rented GPU service (verda) or book one of tami's P40s, or do cpp.

WhisperX CLI Command

the code to save as json and convert to srt for quick anima runs from https://notes.nicolasdeville.com/python/library-whisperx/

we adapted to add diarization (see below for huginface hug)

Key Arguments

Argument	Description
--model	Whisper model: large-v3 (best quality), turbo (fastest), large-v2
--language	Source language code (e.g., en for English, country ISO codes)
--diarize	Enable speaker diarization (requires HuggingFace token)
--compute_type	float16 (GPU), int8 (CPU/low memory), float32 (highest accuracy)
--batch_size	Higher = faster but uses more VRAM (16-32 for 24GB GPUs)
--hf_token	HuggingFace token for PyAnnote diarization models

Performance Benchmarks (from Nic's notes)

Configuration	Speed Ratio
turbo, int8, batch_size=16	~2.3x realtime
large-v3, int8, batch_size=16	~1.2x realtime
large-v2, float16, batch_size=32	~1.5x realtime (GPU)

Tip

: For Hebrew transcription, large-v3 typically provides better accuracy than turbo.

Getting a HuggingFace Token

1. Create account at huggingface.co
2. Accept model terms at:
   • pyannote/speaker-diarization-3.1
   • pyannote/segmentation-3.0
3. Generate token at Settings → Access Tokens

Output Format

WhisperX outputs JSON with word-level timestamps and speaker labels:

{
  "segments": [
    {
      "start": 0.0,
      "end": 2.5,
      "text": "שלום לכולם",
      "speaker": "SPEAKER_01",
      "words": [
        { "word": "שלום", "start": 0.0, "end": 0.8 },
        { "word": "לכולם", "start": 0.9, "end": 2.5 }
      ]
    }
  ]
}