{
	"$id": "/inference/schemas/automatic-speech-recognition/input.json",
	"$schema": "http://json-schema.org/draft-06/schema#",
	"description": "Inputs for Automatic Speech Recognition inference",
	"title": "AutomaticSpeechRecognitionInput",
	"type": "object",
	"properties": {
		"inputs": {
			"description": "The input audio data as a base64-encoded string. If no `parameters` are provided, you can also provide the audio data as a raw bytes payload.",
			"type": "string",
			"comment": "type=binary"
		},
		"parameters": {
			"description": "Additional inference parameters for Automatic Speech Recognition",
			"$ref": "#/$defs/AutomaticSpeechRecognitionParameters"
		}
	},
	"$defs": {
		"AutomaticSpeechRecognitionParameters": {
			"title": "AutomaticSpeechRecognitionParameters",
			"type": "object",
			"properties": {
				"return_timestamps": {
					"type": "boolean",
					"description": "Whether to output corresponding timestamps with the generated text"
				},
				"generation_parameters": {
					"description": "Parametrization of the text generation process",
					"$ref": "/inference/schemas/common-definitions.json#/definitions/GenerationParameters"
				}
			}
		}
	},
	"required": ["inputs"]
}