Audio Transcription Review

annotation_task_name: "Audio Transcription Review"
port: 8000

# Data configuration
data_files:
  - data/transcripts.json

item_properties:
  id_key: id
  text_key: transcript

# Annotation schemes
annotation_schemes:
  # Overall quality assessment
  - annotation_type: radio
    name: overall_accuracy
    description: "How accurate is the transcript overall?"
    labels:
      - name: "Perfect (no errors)"
        key_value: "1"
      - name: "Minor errors (1-2 words)"
        key_value: "2"
      - name: "Moderate errors (3-5 words)"
        key_value: "3"
      - name: "Major errors (>5 words or meaning changed)"
        key_value: "4"
      - name: "Completely wrong"
        key_value: "5"
    sequential_key_binding: true

  # Error types observed
  - annotation_type: multiselect
    name: error_types
    description: "What types of errors are present? (Select all that apply)"
    labels:
      - Word substitution
      - Missing words
      - Extra words inserted
      - Word order errors
      - Punctuation errors
      - Speaker confusion
      - Background noise interference
      - No errors

  # Corrected transcript
  - annotation_type: text
    name: corrected_transcript
    description: "Provide the corrected transcript (if needed)"
    textarea: true
    required: false
    placeholder: "Type the corrected version here..."

  # Audio quality rating
  - annotation_type: likert
    name: audio_quality
    description: "Rate the audio quality"
    size: 5
    min_label: "Very poor"
    max_label: "Excellent"

  # Difficulty rating
  - annotation_type: likert
    name: difficulty
    description: "How difficult was this to transcribe?"
    size: 5
    min_label: "Very easy"
    max_label: "Very difficult"

  # Additional notes
  - annotation_type: text
    name: notes
    description: "Any additional notes? (Optional)"
    textarea: true
    required: false

# User settings
allow_all_users: false
authorized_users:
  - transcriber1@example.com
  - transcriber2@example.com

instances_per_annotator: 100

# Output
output_annotation_dir: "annotation_output/"
output_annotation_format: "json"