Changes: 1. Changed UI text from "Recording" to "Transcribing" for clarity 2. Implemented overlapping audio chunks to prevent word cutoff Audio Overlap Feature: - Added overlap_duration parameter (default: 0.5 seconds) - Audio chunks now overlap by 0.5s to capture words at boundaries - Prevents missed words when chunks are processed separately - Configurable via audio.overlap_duration in config.yaml How it works: - Each 3-second chunk includes 0.5s from the previous chunk - Buffer advances by (chunk_size - overlap_size) instead of full chunk - Ensures words at chunk boundaries are captured in at least one chunk - No duplicate transcription due to Whisper's context handling Example with 3s chunks and 0.5s overlap: Chunk 1: [0.0s - 3.0s] Chunk 2: [2.5s - 5.5s] <- 0.5s overlap Chunk 3: [5.0s - 8.0s] <- 0.5s overlap Files modified: - client/audio_capture.py: Implemented overlapping buffer logic - config/default_config.yaml: Added overlap_duration setting - gui/main_window_qt.py: Updated UI text, passed overlap param - main_cli.py: Passed overlap param 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
42 lines
713 B
YAML
42 lines
713 B
YAML
user:
|
|
name: "User"
|
|
id: ""
|
|
|
|
audio:
|
|
input_device: "default"
|
|
sample_rate: 16000
|
|
chunk_duration: 3.0
|
|
overlap_duration: 0.5 # Overlap between chunks to prevent word cutoff (seconds)
|
|
|
|
noise_suppression:
|
|
enabled: true
|
|
strength: 0.7
|
|
method: "noisereduce"
|
|
|
|
transcription:
|
|
model: "base"
|
|
device: "auto"
|
|
language: "en"
|
|
task: "transcribe"
|
|
|
|
processing:
|
|
use_vad: true
|
|
min_confidence: 0.5
|
|
|
|
server_sync:
|
|
enabled: false
|
|
url: "ws://localhost:8000"
|
|
api_key: ""
|
|
|
|
display:
|
|
show_timestamps: true
|
|
max_lines: 100
|
|
font_family: "Courier"
|
|
font_size: 12
|
|
theme: "dark"
|
|
fade_after_seconds: 10 # Time before transcriptions fade out (0 = never fade)
|
|
|
|
web_server:
|
|
port: 8080
|
|
host: "127.0.0.1"
|