Make WhisperX language detection configurable through FastAPI settings to handle empty audio start scenarios where automatic detection fails and incorrectly defaults to English despite 99% French usage. Quick fix acknowledging long-term solution should allow dynamic per-recording language selection configured by users through web interface rather than global server settings.
25 lines
629 B
Plaintext
25 lines
629 B
Plaintext
APP_NAME="meet-app-summary-dev"
|
|
APP_API_TOKEN="password"
|
|
|
|
AWS_STORAGE_BUCKET_NAME="meet-media-storage"
|
|
AWS_S3_ENDPOINT_URL="minio:9000"
|
|
AWS_S3_SECURE_ACCESS=false
|
|
|
|
AWS_S3_ACCESS_KEY_ID="meet"
|
|
AWS_S3_SECRET_ACCESS_KEY="password"
|
|
|
|
WHISPERX_BASE_URL="https://configure-your-url.com"
|
|
WHISPERX_ASR_MODEL="large-v2"
|
|
WHISPERX_API_KEY="your-secret-key"
|
|
WHISPERX_DEFAULT_LANGUAGE="fr"
|
|
|
|
LLM_BASE_URL="https://configure-your-url.com"
|
|
LLM_API_KEY="dev-apikey"
|
|
LLM_MODEL="Qwen/Qwen2.5-Coder-32B-Instruct-AWQ"
|
|
|
|
WEBHOOK_API_TOKEN="secret"
|
|
WEBHOOK_URL="https://configure-your-url.com"
|
|
|
|
POSTHOG_API_KEY="your-posthog-key"
|
|
POSTHOG_ENABLED="False"
|