SparkAudio_Spark-TTS-0.5B.json

{
    "bomFormat": "CycloneDX",
    "specVersion": "1.6",
    "serialNumber": "urn:uuid:dd938abe-dbb2-4838-8459-edc51f28df1b",
    "version": 1,
    "metadata": {
        "timestamp": "2025-07-14T14:13:20.770453+00:00",
        "component": {
            "type": "machine-learning-model",
            "bom-ref": "SparkAudio/Spark-TTS-0.5B-bf10ddd8-615d-53b3-b697-f3e446f4c11b",
            "name": "SparkAudio/Spark-TTS-0.5B",
            "externalReferences": [
                {
                    "url": "https://huggingface.co/SparkAudio/Spark-TTS-0.5B",
                    "type": "documentation"
                }
            ],
            "modelCard": {
                "modelParameters": {
                    "task": "text-to-speech"
                }
            },
            "authors": [
                {
                    "name": "SparkAudio"
                }
            ],
            "licenses": [
                {
                    "license": {
                        "id": "CC-BY-NC-SA-4.0",
                        "url": "https://spdx.org/licenses/CC-BY-NC-SA-4.0.html"
                    }
                }
            ],
            "description": "Spark-TTS is an advanced text-to-speech system that uses the power of large language models (LLM) for highly accurate and natural-sounding voice synthesis. It is designed to be efficient, flexible, and powerful for both research and production use.",
            "tags": [
                "safetensors",
                "text-to-speech",
                "en",
                "zh",
                "arxiv:2503.01710",
                "doi:10.57967/hf/4650",
                "license:cc-by-nc-sa-4.0",
                "region:us"
            ]
        }
    }
}