Audio-Annotation

annotation_schemes:
  - annotation_type: audio_annotation
    name: audio_segments
    description: "Segment and label the audio"
    labels:
      - Speech
      - Music
      - Silence
      - Noise

annotation_schemes:
  - annotation_type: audio_annotation
    name: speaker_diarization
    mode: label
    description: "Identify speakers in the audio"
    labels:
      - Speaker A
      - Speaker B
      - Overlap

annotation_schemes:
  - annotation_type: audio_annotation
    name: speech_quality
    mode: questions
    description: "Evaluate speech segments"
    segment_schemes:
      - annotation_type: radio
        name: speaker_type
        description: "Who is speaking?"
        labels: ["host", "guest", "unknown"]
      - annotation_type: likert
        name: clarity
        description: "How clear is this segment?"
        size: 5
        min_label: "Unintelligible"
        max_label: "Perfectly clear"

annotation_schemes:
  - annotation_type: audio_annotation
    name: full_analysis
    mode: both
    description: "Label and analyze audio segments"
    labels:
      - Speech
      - Music
      - Noise
    segment_schemes:
      - annotation_type: radio
        name: foreground
        description: "Is this the foreground audio?"
        labels: ["Yes", "No"]

annotation_schemes:
  - annotation_type: audio_annotation
    name: segments
    description: "Create audio segments"
    labels:
      - Label A
      - Label B
 
    # Optional constraints
    min_segments: 1
    max_segments: 50

annotation_schemes:
  - annotation_type: audio_annotation
    name: speakers
    description: "Mark each speaker turn"
    labels:
      - Speaker A  # Press 1
      - Speaker B  # Press 2
      - Overlap    # Press 3

annotation_schemes:
  - annotation_type: audio_annotation
    name: segments
    description: "Segment the recording and label each region"
    labels:
      - name: Speech
        color: "#22C55E"
      - name: Music
        color: "#3B82F6"
      - name: Silence
        color: "#9CA3AF"

# macOS
brew install audiowaveform
 
# Ubuntu/Debian
sudo apt-get install audiowaveform
 
# Or build from source
# https://github.com/bbc/audiowaveform

audio_annotation:
  waveform_cache_dir: waveform_cache/     # Where pre-computed waveforms are stored
  waveform_look_ahead: 3                  # Pre-compute the next N instances
  waveform_cache_max_size: 50             # Maximum cached waveform files
  client_fallback_max_duration: 1800      # Longest file the browser will render, in seconds

[
  {"id": "1", "audio_path": "audio/recording_001.wav"},
  {"id": "2", "audio_path": "audio/recording_002.wav"}
]

data_files:
  - "data/audio_data.json"
 
item_properties:
  id_key: id
  text_key: audio_path   # The field holding the audio URL

[
  {
    "id": "1",
    "audio_path": "audio/call_001.wav",
    "transcript": "Hello, how can I help you today?"
  }
]

{
  "id": "audio_1",
  "annotations": {
    "segments": [
      {
        "start": 0.0,
        "end": 2.5,
        "label": "Speaker A",
        "questions": {
          "clarity": 4,
          "emotion": "Neutral"
        }
      },
      {
        "start": 2.5,
        "end": 5.2,
        "label": "Speaker B"
      }
    ]
  }
}

annotation_task_name: "Speaker Diarization"
task_dir: "."
port: 8000
 
data_files:
  - "data/recordings.json"
 
item_properties:
  id_key: id
  text_key: audio_path
 
annotation_schemes:
  - annotation_type: audio_annotation
    name: speakers
    mode: label
    description: "Identify who is speaking"
    labels:
      - Speaker 1
      - Speaker 2
      - Speaker 3
      - Overlap
      - Silence
    min_segments: 1
 
# Diarization recordings run long, so precompute a few ahead of the annotator.
audio_annotation:
  waveform_cache_dir: waveform_cache/
  waveform_look_ahead: 5
 
output_annotation_dir: "output/"
export_annotation_format: jsonl
 
user_config:
  allow_all_users: true

annotation_task_name: "Transcription Quality Review"
task_dir: "."
port: 8000
 
data_files:
  - "data/transcripts.json"
 
item_properties:
  id_key: id
  text_key: audio_path
 
annotation_schemes:
  - annotation_type: audio_annotation
    name: errors
    mode: questions
    description: "Mark transcription errors"
    # Questions mode collects answers per marked region, so the error type and
    # the correction stay attached to the stretch of audio they describe.
    segment_schemes:
      - annotation_type: radio
        name: error_type
        description: "What kind of error is this?"
        labels: ["Substitution", "Deletion", "Insertion", "Speaker mix-up"]
      - annotation_type: text
        name: correction
        description: "What should the transcript say?"
 
  - annotation_type: radio
    name: overall_accuracy
    description: "Overall transcript accuracy"
    labels:
      - Accurate
      - Minor errors
      - Major errors
      - Unusable
 
output_annotation_dir: "output/"
export_annotation_format: jsonl

annotation_task_name: "Call Center Quality Assurance"
task_dir: "."
port: 8000
 
data_files:
  - "data/calls.json"
 
item_properties:
  id_key: call_id
  text_key: recording_path
 
annotation_schemes:
  # Segment-level annotation
  - annotation_type: audio_annotation
    name: conversation
    mode: both
    description: "Segment the conversation"
    labels:
      - Agent
      - Customer
      - Hold
      - Silence
    # Who is speaking is a label; how the turn went is a question about it.
    segment_schemes:
      - annotation_type: radio
        name: tone
        description: "Tone of this turn"
        labels: ["Calm", "Neutral", "Escalated"]
 
  # Call-level assessment
  - annotation_type: likert
    name: professionalism
    description: "Agent professionalism"
    size: 5
    min_label: "Poor"
    max_label: "Excellent"
 
  - annotation_type: likert
    name: resolution
    description: "Issue resolution"
    size: 5
    min_label: "Unresolved"
    max_label: "Fully resolved"
 
  - annotation_type: multiselect
    name: issues
    description: "Select any issues observed"
    labels:
      - Long hold time
      - Agent interrupted
      - Incorrect information
      - Missing greeting
      - Unprofessional language
 
  - annotation_type: text
    name: notes
    description: "Additional observations"
    rows: 4
 
output_annotation_dir: "output/"
export_annotation_format: jsonl