Configuration#
Load Order#
The service loads configuration in this order:
config.yamlEnvironment variables with the
AUDIO_ANALYZER__...prefix
The same config.yaml is used for both Docker and standalone runs. In Docker, config.yaml is bind-mounted into the container, so edits on the host take effect on docker compose restart.
Config File#
config.yaml: single source of truth for both standalone and container runs.
Environment Variables#
AUDIO_ANALYZER_CONFIG_PATH: alternate base config file (advanced)AUDIO_ANALYZER_ENV_FILE: optional.envfile to preload before config parsingAUDIO_ANALYZER_SERVER_HOST: host used bypython main.pyAUDIO_ANALYZER_SERVER_PORT: port used bypython main.py
Targeted config overrides use the AUDIO_ANALYZER__... prefix.
Example:
AUDIO_ANALYZER__MODELS__ASR__DEVICE=GPU python main.py
Key Sections#
models.asr: backend provider, model name, device, export precision, decoding settingsaudio_preprocessing: chunk size, silence detection, denoise settings, chunk directoryaudio_util: max file size, allowed extensions, upload read chunk sizepipeline.delete_chunks_after_use: whether temporary chunks are removed after processingsentiment: enablement, provider, model, device, aggregation settings
Common Values#
models.asr.provider:openai|openvino|whispercppmodels.asr.device: typicallyCPU;GPUworks only for supported OpenVINO pathsmodels.asr.weight_format: OpenVINO export precision such asint8,fp16, ornull; forwhispercpp, quantization such asq5,q5_0,q5_1,q8,q8_0,int5,int8, ornullsentiment.enabled:trueorfalsesentiment.provider:openvinoorpytorchsentiment.weight_format: optional OpenVINO export precision such asint8,fp16, ornull
ASR Provider Notes#
openai: usesopenai-whisperand downloads PyTorch Whisper weights on first use.openvino: exports the configured Whisper model to OpenVINO IR undermodels/openvino/...and can targetCPUorGPU.whispercpp: downloads the matching whisper.cppggmlmodel undermodels/whispercpp/...and runs onCPUonly.
Provider-specific models.asr fields:
weight_format: used byopenvinofor IR export precision and bywhispercppfor model quantization.beam_size,best_of,threads,word_timestamps: used only bywhispercpp.