{ "models": [ // Configuration for the built-in models. You can remove any of these // if you don't want to use the default models. { "name": "tiny", "url": "tiny" }, { "name": "base", "url": "base" }, { "name": "small", "url": "small" }, { "name": "medium", "url": "medium" }, { "name": "large", "url": "large" }, { "name": "large-v2", "url": "large-v2" }, // Uncomment to add custom Japanese models //{ // "name": "whisper-large-v2-mix-jp", // "url": "vumichien/whisper-large-v2-mix-jp", // // The type of the model. Can be "huggingface" or "whisper" - "whisper" is the default. // // HuggingFace models are loaded using the HuggingFace transformers library and then converted to Whisper models. // "type": "huggingface", //} ], // Configuration options that will be used if they are not specified in the command line arguments. // Maximum audio file length in seconds, or -1 for no limit. "input_audio_max_duration": 600, // True to share the app on HuggingFace. "share": false, // The host or IP to bind to. If None, bind to localhost. "server_name": null, // The port to bind to. "server_port": 7860, // The default model name. "default_model_name": "medium", // The default VAD. "default_vad": "silero-vad", // A commma delimited list of CUDA devices to use for parallel processing. If None, disable parallel processing. "vad_parallel_devices": "", // The number of CPU cores to use for VAD pre-processing. "vad_cpu_cores": 1, // The number of seconds before inactivate processes are terminated. Use 0 to close processes immediately, or None for no timeout. "vad_process_timeout": 1800, // True to use all available GPUs and CPU cores for processing. Use vad_cpu_cores/vad_parallel_devices to specify the number of CPU cores/GPUs to use. "auto_parallel": false, // Directory to save the outputs "output_dir": null }