Add support for DAC and Mimi

[xenova]

DAC:

import { DacModel, AutoFeatureExtractor } from '@huggingface/transformers';

const model_id = "onnx-community/dac_16khz-ONNX";
const model = await DacModel.from_pretrained(model_id);
const feature_extractor = await AutoFeatureExtractor.from_pretrained(model_id);

const audio_sample = new Float32Array(12000);

// pre-process the inputs
const inputs = await feature_extractor(audio_sample);
{
    // explicitly encode then decode the audio inputs
    const encoder_outputs = await model.encode(inputs);
    const { audio_values } = await model.decode(encoder_outputs);
    console.log(audio_values);
}

{
    // or the equivalent with a forward pass
    const { audio_values } = await model(inputs);
    console.log(audio_values);
}

Mimi:

import { MimiModel, AutoFeatureExtractor } from '@huggingface/transformers';

const model_id = "onnx-community/kyutai-mimi-ONNX";
const model = await MimiModel.from_pretrained(model_id);
const feature_extractor = await AutoFeatureExtractor.from_pretrained(model_id);

const audio_sample = new Float32Array(12000);

// pre-process the inputs
const inputs = await feature_extractor(audio_sample);
{
    // explicitly encode then decode the audio inputs
    const encoder_outputs = await model.encode(inputs);
    const { audio_values } = await model.decode(encoder_outputs);
    console.log(audio_values);
}

{
    // or the equivalent with a forward pass
    const { audio_values } = await model(inputs);
    console.log(audio_values);
}

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[xenova]

In future, it could be cool to add support for Mimi w/ past key values to speed up streamed decoding. For now, this PR is okay.