@huggingface/tasks/dist/esm/tasks/text-to-speech/data.js

List of ML tasks for huggingface.co/tasks

const taskData = {
    canonicalId: "text-to-audio",
    datasets: [
        {
            description: "10K hours of multi-speaker English dataset.",
            id: "parler-tts/mls_eng_10k",
        },
        {
            description: "Multi-speaker English dataset.",
            id: "mythicinfinity/libritts_r",
        },
        {
            description: "Multi-lingual dataset.",
            id: "facebook/multilingual_librispeech",
        },
    ],
    demo: {
        inputs: [
            {
                label: "Input",
                content: "I love audio models on the Hub!",
                type: "text",
            },
        ],
        outputs: [
            {
                filename: "audio.wav",
                type: "audio",
            },
        ],
    },
    metrics: [
        {
            description: "The Mel Cepstral Distortion (MCD) metric is used to calculate the quality of generated speech.",
            id: "mel cepstral distortion",
        },
    ],
    models: [
        {
            description: "A prompt based, powerful TTS model.",
            id: "parler-tts/parler-tts-large-v1",
        },
        {
            description: "A powerful TTS model that supports English and Chinese.",
            id: "SWivid/F5-TTS",
        },
        {
            description: "A massively multi-lingual TTS model.",
            id: "fishaudio/fish-speech-1.5",
        },
        {
            description: "A powerful TTS model.",
            id: "OuteAI/OuteTTS-0.1-350M",
        },
        {
            description: "Small yet powerful TTS model.",
            id: "hexgrad/Kokoro-82M",
        },
    ],
    spaces: [
        {
            description: "An application for generate high quality speech in different languages.",
            id: "hexgrad/Kokoro-TTS",
        },
        {
            description: "A multilingual text-to-speech application.",
            id: "fishaudio/fish-speech-1",
        },
        {
            description: "An application that generates speech in different styles in English and Chinese.",
            id: "mrfakename/E2-F5-TTS",
        },
        {
            description: "An application that synthesizes emotional speech for diverse speaker prompts.",
            id: "parler-tts/parler-tts-expresso",
        },
        {
            description: "An application that generates podcast episodes.",
            id: "ngxson/kokoro-podcast-generator",
        },
    ],
    summary: "Text-to-Speech (TTS) is the task of generating natural sounding speech given text input. TTS models can be extended to have a single model that generates speech for multiple speakers and multiple languages.",
    widgetModels: ["suno/bark"],
    youtubeId: "NW62DpzJ274",
};
export default taskData;