Voxtral-Mini-3B-2507-ONNX

npm i @huggingface/transformers

import { VoxtralForConditionalGeneration, VoxtralProcessor, TextStreamer, read_audio } from "@huggingface/transformers";

// Load the processor and model
const model_id = "onnx-community/Voxtral-Mini-3B-2507-ONNX";
const processor = await VoxtralProcessor.from_pretrained(model_id);
const model = await VoxtralForConditionalGeneration.from_pretrained(
    model_id,
    {
        dtype: {
            embed_tokens: "fp16", // "fp32", "fp16", "q8", "q4"
            audio_encoder: "q4", // "fp32", "fp16", "q8", "q4", "q4f16"
            decoder_model_merged: "q4", // "q4", "q4f16"
        },
        device: "webgpu",
    },
);

// Prepare the conversation
const conversation = [
    {
        "role": "user",
        "content": [
            { "type": "audio" },
            { "type": "text", "text": "lang:en [TRANSCRIBE]" },
        ],
    }
];
const text = processor.apply_chat_template(conversation, { tokenize: false });
const audio = await read_audio("http://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/mlk.wav", 16000);
const inputs = await processor(text, audio);

// Generate the response
const generated_ids = await model.generate({
    ...inputs,
    max_new_tokens: 256,
    streamer: new TextStreamer(processor.tokenizer, { skip_special_tokens: true, skip_prompt: true }),
});

// Decode the generated tokens
const new_tokens = generated_ids.slice(null, [inputs.input_ids.dims.at(-1), null]);
const generated_texts = processor.batch_decode(
    new_tokens,
    { skip_special_tokens: true },
);
console.log(generated_texts[0]);
// I have a dream that one day this nation will rise up and live out the true meaning of its creed.

import { VoxtralForConditionalGeneration, VoxtralProcessor, TextStreamer, read_audio } from "@huggingface/transformers";

// Load the processor and model
const model_id = "onnx-community/Voxtral-Mini-3B-2507-ONNX";
const processor = await VoxtralProcessor.from_pretrained(model_id);
const model = await VoxtralForConditionalGeneration.from_pretrained(
    model_id,
    {
        dtype: {
            embed_tokens: "fp16", // "fp32", "fp16", "q8", "q4"
            audio_encoder: "q4", // "fp32", "fp16", "q8", "q4", "q4f16"
            decoder_model_merged: "q4", // "q4", "q4f16"
        },
        device: "webgpu",
    },
);

// Prepare the conversation
const conversation = [
    {
        "role": "user",
        "content": [
            { "type": "audio" },
            { "type": "audio" },
            { "type": "text", "text": "Describe these two audio clips in detail." },
        ],
    }
];
const text = processor.apply_chat_template(conversation, { tokenize: false });
const audio = await Promise.all([
    read_audio("https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav", 16000),
    read_audio("https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/mlk.wav", 16000),
]);
const inputs = await processor(text, audio);

// Generate the response
const generated_ids = await model.generate({
    ...inputs,
    max_new_tokens: 256,
    streamer: new TextStreamer(processor.tokenizer, { skip_special_tokens: true, skip_prompt: true }),
});

// Decode the generated tokens
const new_tokens = generated_ids.slice(null, [inputs.input_ids.dims.at(-1), null]);
const generated_texts = processor.batch_decode(
    new_tokens,
    { skip_special_tokens: true },
);
console.log(generated_texts[0]);
// The first audio clip is a speech by a leader, likely a politician or a public figure, addressing a large audience. The speaker begins by encouraging the listeners to ask not what their country can do for them, but what they can do for their country. This is a call to action and a reminder of the individual's responsibility to contribute to the nation's well-being. The second audio clip is a passionate speech by a different leader, possibly a civil rights activist or a community organizer. This speaker expresses a dream of a nation that will rise up and live out the true meaning of its creed, suggesting a vision of a more just and equitable society.