Transcription

/**
 * Whisper transcription with prompt example.
 *
 * Usage:
 *   bun examples/asr/whispercpp-prompt.ts
 *
 * This example requires a test audio file (default: examples/audio/sample-16khz.wav).
 * Sample audio files are available in the QVAC source repository, but not included in the published npm package.
 * Set audioChunk to a custom WAV, or download the default audio into examples/audio/:
 *   https://github.com/tetherto/qvac/blob/main/packages/sdk/examples/audio/sample-16khz.wav
 */
import { loadModel, unloadModel, transcribe, WHISPER_TINY } from '@qvac/sdk';
try {
    console.log('▸ Starting Whisper transcription with prompt example...');
    // Load the Whisper model
    console.log('▸ Loading Whisper model...');
    const modelId = await loadModel({
        modelSrc: WHISPER_TINY,
        modelConfig: {
            audio_format: 'f32le',
            // Sampling strategy
            strategy: 'greedy',
            n_threads: 4,
            // Transcription options
            language: 'en',
            translate: false,
            no_timestamps: false,
            single_segment: false,
            print_timestamps: true,
            token_timestamps: true,
            // Quality settings
            temperature: 0.0,
            suppress_blank: true,
            suppress_nst: true,
            // Advanced tuning
            entropy_thold: 2.4,
            logprob_thold: -1.0,
            // VAD configuration
            vad_params: {
                threshold: 0.35,
                min_speech_duration_ms: 200,
                min_silence_duration_ms: 150,
                max_speech_duration_s: 30.0,
                speech_pad_ms: 600,
                samples_overlap: 0.3
            },
            // Context parameters for GPU
            contextParams: {
                use_gpu: true,
                flash_attn: true,
                gpu_device: 0
            }
        },
        onProgress: (p) => {
            const mb = (n) => (n / 1e6).toFixed(1);
            const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
            process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
            if (p.percentage >= 100)
                process.stderr.write('\n');
        }
    });
    console.log(`▸ Whisper model loaded with ID: ${modelId}`);
    // Perform transcription
    console.log('▸ Transcribing audio...');
    const text = await transcribe({
        modelId,
        audioChunk: 'examples/audio/sample-16khz.wav',
        prompt: 'This is a test recording with clear speech and proper punctuation.'
    });
    console.log('▸ Transcription result:');
    console.log(text);
    // Unload the model when done
    console.log('▸ Unloading Whisper model...');
    await unloadModel({ modelId });
    console.log('▸ Whisper model unloaded successfully');
    process.exit(0);
}
catch (error) {
    console.error('✖', error);
    process.exit(1);
}

/**
 * Parakeet TDT transcription from a WAV file.
 *
 * Usage:
 *   bun run examples/asr/parakeet-tdt-filesystem.ts <wav-file> [parakeet-tdt-gguf]
 *
 * Loads a single GGUF checkpoint (`PARAKEET_TDT_0_6B_V3_Q8_0` by default) and
 * transcribes the file with the batch `transcribe` API. Omit the model
 * argument to use the registry constant.
 *
 * Audio should be 16 kHz mono PCM in a WAV container.
 */
import { loadModel, unloadModel, transcribe, PARAKEET_TDT_0_6B_V3_Q8_0 } from '@qvac/sdk';
const args = process.argv.slice(2);
if (!args[0]) {
    console.error('Usage: bun run examples/asr/parakeet-tdt-filesystem.ts <wav-file-path> ' +
        '[parakeet-tdt-gguf]');
    console.error('\nIf the model path is omitted, defaults to the registry model.');
    process.exit(1);
}
const audioFilePath = args[0];
const parakeetModelSrc = args[1] ?? PARAKEET_TDT_0_6B_V3_Q8_0;
try {
    console.log('▸ Starting Parakeet transcription example...');
    console.log('▸ Loading Parakeet model...');
    const modelId = await loadModel({
        modelSrc: parakeetModelSrc,
        modelType: 'parakeet-transcription',
        onProgress: (p) => {
            const mb = (n) => (n / 1e6).toFixed(1);
            const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
            process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
            if (p.percentage >= 100)
                process.stderr.write('\n');
        }
    });
    console.log(`▸ Parakeet model loaded with ID: ${modelId}`);
    console.log('▸ Transcribing audio...');
    const text = await transcribe({ modelId, audioChunk: audioFilePath });
    console.log(text);
    console.log('▸ Unloading Parakeet model...');
    await unloadModel({ modelId });
    console.log('▸ Parakeet model unloaded successfully');
}
catch (error) {
    console.error('✖', error);
    process.exit(1);
}

/**
 * Parakeet CTC transcription from a WAV file.
 *
 * Usage:
 *   bun run examples/asr/parakeet-ctc-filesystem.ts <wav-file> [parakeet-ctc-gguf]
 *
 * Loads a single GGUF checkpoint (`PARAKEET_CTC_0_6B_Q8_0` by default) and
 * transcribes the file with the batch `transcribe` API. Omit the model
 * argument to use the registry constant.
 *
 * Audio should be 16 kHz mono PCM in a WAV container.
 */
import { loadModel, unloadModel, transcribe, PARAKEET_CTC_0_6B_Q8_0 } from '@qvac/sdk';
const args = process.argv.slice(2);
if (!args[0]) {
    console.error('Usage: bun run examples/asr/parakeet-ctc-filesystem.ts <wav-file> ' + '[parakeet-ctc-gguf]');
    console.error('\nIf the model path is omitted, defaults to the registry model.');
    process.exit(1);
}
const audioFilePath = args[0];
const parakeetModelSrc = args[1] ?? PARAKEET_CTC_0_6B_Q8_0;
try {
    console.log('▸ Loading Parakeet CTC model...');
    const modelId = await loadModel({
        modelSrc: parakeetModelSrc,
        modelType: 'parakeet-transcription',
        onProgress: (p) => {
            const mb = (n) => (n / 1e6).toFixed(1);
            const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
            process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
            if (p.percentage >= 100)
                process.stderr.write('\n');
        }
    });
    console.log(`▸ Parakeet CTC model loaded with ID: ${modelId}`);
    console.log('▸ Transcribing audio...');
    const text = await transcribe({ modelId, audioChunk: audioFilePath });
    console.log(text);
    console.log('▸ Unloading model...');
    await unloadModel({ modelId });
    console.log('▸ Done');
}
catch (error) {
    console.error('✖', error);
    process.exit(1);
}

/**
 * Parakeet Unified transcription from a WAV file.
 *
 * Usage:
 *   bun run examples/asr/parakeet-unified-filesystem.ts <wav-file> [parakeet-unified-gguf]
 *
 * Loads a single GGUF checkpoint (`PARAKEET_UNIFIED_0_6B_Q8_0` by default) and
 * transcribes the file with the batch `transcribe` API. The Unified RNN-T
 * checkpoint is English-only and serves both batch and low-latency streaming
 * from the same GGUF; the engine auto-detects the model type from the GGUF
 * metadata. Omit the model argument to use the registry constant.
 *
 * Audio should be 16 kHz mono PCM in a WAV container.
 */
import { loadModel, unloadModel, transcribe, PARAKEET_UNIFIED_0_6B_Q8_0 } from '@qvac/sdk';
const args = process.argv.slice(2);
if (!args[0]) {
    console.error('Usage: bun run examples/asr/parakeet-unified-filesystem.ts <wav-file-path> ' +
        '[parakeet-unified-gguf]');
    console.error('\nIf the model path is omitted, defaults to the registry model.');
    process.exit(1);
}
const audioFilePath = args[0];
const parakeetModelSrc = args[1] ?? PARAKEET_UNIFIED_0_6B_Q8_0;
try {
    console.log('▸ Starting Parakeet Unified transcription example...');
    console.log('▸ Loading Parakeet Unified model...');
    const modelId = await loadModel({
        modelSrc: parakeetModelSrc,
        modelType: 'parakeet-transcription',
        onProgress: (p) => {
            const mb = (n) => (n / 1e6).toFixed(1);
            const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
            process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
            if (p.percentage >= 100)
                process.stderr.write('\n');
        }
    });
    console.log(`▸ Parakeet Unified model loaded with ID: ${modelId}`);
    console.log('▸ Transcribing audio...');
    const text = await transcribe({ modelId, audioChunk: audioFilePath });
    console.log(text);
    console.log('▸ Unloading Parakeet Unified model...');
    await unloadModel({ modelId });
    console.log('▸ Parakeet Unified model unloaded successfully');
}
catch (error) {
    console.error('✖', error);
    process.exit(1);
}

/**
 * Indic Conformer CTC transcription from a WAV file.
 *
 * Usage:
 *   bun run examples/asr/parakeet-indic-conformer-filesystem.ts <wav-file> <language> [gguf]
 *
 * Loads a single GGUF checkpoint (`PARAKEET_INDIC_CONFORMER_CTC_Q8_0` by
 * default) and transcribes with the batch `transcribe` API. `language` is
 * required (e.g. `hi`, `ta`) because Indic Conformer CTC masks the vocab
 * with `parakeet.ctc.lang_*` ranges. English Parakeet CTC ignores this field.
 *
 * Audio should be 16 kHz mono PCM in a WAV container.
 */
import { loadModel, unloadModel, transcribe, PARAKEET_INDIC_CONFORMER_CTC_Q8_0 } from '@qvac/sdk';
const args = process.argv.slice(2);
if (!args[0] || !args[1]) {
    console.error('Usage: bun run examples/asr/parakeet-indic-conformer-filesystem.ts ' +
        '<wav-file> <language> [indic-conformer-gguf]');
    console.error('\nExample: ... filesystem.ts speech.wav hi');
    console.error('If the model path is omitted, defaults to the registry model.');
    process.exit(1);
}
const audioFilePath = args[0];
const language = args[1];
const parakeetModelSrc = args[2] ?? PARAKEET_INDIC_CONFORMER_CTC_Q8_0;
try {
    console.log('▸ Loading Indic Conformer CTC model...');
    const modelId = await loadModel({
        modelSrc: parakeetModelSrc,
        modelType: 'parakeet-transcription',
        modelConfig: { language },
        onProgress: (p) => {
            const mb = (n) => (n / 1e6).toFixed(1);
            const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
            process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
            if (p.percentage >= 100)
                process.stderr.write('\n');
        }
    });
    console.log(`▸ Indic Conformer CTC model loaded with ID: ${modelId}`);
    console.log(`▸ Language: ${language}`);
    console.log('▸ Transcribing audio...');
    const text = await transcribe({ modelId, audioChunk: audioFilePath });
    console.log(text);
    console.log('▸ Unloading model...');
    await unloadModel({ modelId });
    console.log('▸ Done');
}
catch (error) {
    console.error('✖', error);
    process.exit(1);
}

/**
 * Parakeet Sortformer diarization + TDT transcription pipeline.
 *
 * Usage:
 *   bun run examples/asr/parakeet-sortformer.ts [sortformer-gguf] [wav-file]
 *
 * Two-step flow: Sortformer v2.1 diarizes the audio, then TDT transcribes each
 * speaker segment. Defaults to registry GGUFs and
 * `examples/audio/diarization-sample-16k.wav`. For live streaming + AOSC, see
 * `parakeet-sortformer-streaming.ts`.
 *
 * Sample audio is in the QVAC source repo but not the published npm package.
 * Download the default file into `examples/audio/`:
 *   https://github.com/tetherto/qvac/blob/main/packages/sdk/examples/audio/diarization-sample-16k.wav
 */
import { loadModel, unloadModel, transcribe, PARAKEET_TDT_0_6B_V3_Q8_0, PARAKEET_SORTFORMER_4SPK_V2_1_Q8_0 } from '@qvac/sdk';
import { dirname, join } from 'path';
import { fileURLToPath } from 'url';
import { readFileSync, writeFileSync, mkdirSync } from 'fs';
import { tmpdir } from 'os';
const __dirname = dirname(fileURLToPath(import.meta.url));
const args = process.argv.slice(2);
const sortformerSrc = args[0] ?? PARAKEET_SORTFORMER_4SPK_V2_1_Q8_0;
const defaultAudioPath = join(__dirname, '..', 'audio', 'diarization-sample-16k.wav');
const audioFilePath = args[1] ?? defaultAudioPath;
try {
    // ── Step 1: Diarize with Sortformer ──
    const sfModelId = await loadModel({
        modelSrc: sortformerSrc,
        modelType: 'parakeet-transcription'
    });
    const diarization = await transcribe({
        modelId: sfModelId,
        audioChunk: audioFilePath
    });
    await unloadModel({ modelId: sfModelId });
    const segments = parseDiarization(diarization);
    // ── Step 2: Transcribe each segment with TDT ──
    const tdtModelId = await loadModel({
        modelSrc: PARAKEET_TDT_0_6B_V3_Q8_0
    });
    const pcm = readPcm(audioFilePath);
    const sliceDir = join(tmpdir(), `qvac-diarize-${Date.now()}`);
    mkdirSync(sliceDir, { recursive: true });
    const results = [];
    for (let i = 0; i < segments.length; i++) {
        const seg = segments[i];
        const slicePath = join(sliceDir, `seg-${i}.wav`);
        if (!writeWavSlice(pcm, seg.start, seg.end, slicePath)) {
            results.push({ ...seg, text: '[No speech detected]' });
            continue;
        }
        const text = await transcribe({
            modelId: tdtModelId,
            audioChunk: slicePath
        });
        results.push({ ...seg, text: text.trim() || '[No speech detected]' });
    }
    await unloadModel({ modelId: tdtModelId });
    // ── Step 3: Merge consecutive same-speaker segments and print ──
    const merged = mergeSpeakers(results);
    console.log('\n▸ Diarized transcription');
    for (const entry of merged) {
        console.log(`Speaker ${entry.speaker} (${entry.start.toFixed(2)}s - ${entry.end.toFixed(2)}s):`);
        console.log(`  ${entry.text}\n`);
    }
    console.log('▸ Done');
}
catch (error) {
    console.error('✖', error);
    process.exit(1);
}
// ── Helpers ──
function parseDiarization(text) {
    const segs = [];
    for (const line of text.split('\n')) {
        const m = line.match(/Speaker (\d+): ([\d.]+)s - ([\d.]+)s/);
        if (m)
            segs.push({ speaker: +m[1], start: +m[2], end: +m[3] });
    }
    return segs.sort((a, b) => a.start - b.start);
}
function readPcm(wavPath) {
    const buf = readFileSync(wavPath);
    const dataOffset = buf.indexOf('data') + 4;
    return buf.subarray(dataOffset + 4, dataOffset + 4 + buf.readUInt32LE(dataOffset));
}
function writeWavSlice(pcm, startSec, endSec, outPath) {
    const SR = 16000;
    const BPS = 2;
    const startByte = Math.floor(startSec * SR) * BPS;
    const endByte = Math.min(Math.ceil(endSec * SR) * BPS, pcm.length);
    if (startByte >= endByte)
        return false;
    const slice = pcm.subarray(startByte, endByte);
    const hdr = Buffer.alloc(44);
    hdr.write('RIFF', 0);
    hdr.writeUInt32LE(36 + slice.length, 4);
    hdr.write('WAVEfmt ', 8);
    hdr.writeUInt32LE(16, 16);
    hdr.writeUInt16LE(1, 20);
    hdr.writeUInt16LE(1, 22);
    hdr.writeUInt32LE(SR, 24);
    hdr.writeUInt32LE(SR * BPS, 28);
    hdr.writeUInt16LE(BPS, 32);
    hdr.writeUInt16LE(16, 34);
    hdr.write('data', 36);
    hdr.writeUInt32LE(slice.length, 40);
    writeFileSync(outPath, Buffer.concat([hdr, slice]));
    return true;
}
function mergeSpeakers(entries) {
    const out = [];
    for (const e of entries) {
        const last = out[out.length - 1];
        if (last && last.speaker === e.speaker) {
            last.text += ' ' + e.text;
            last.end = e.end;
        }
        else {
            out.push({ ...e });
        }
    }
    return out;
}