@qvac/sdk 0.8.2 → 0.9.0

package/dist/examples/diffusion-flux2-klein.js

@@ -0,0 +1,46 @@
+import { loadModel, unloadModel, diffusion, FLUX_2_KLEIN_4B_Q4_0, FLUX_2_KLEIN_4B_VAE, QWEN3_4B_Q4_K_M } from "@qvac/sdk";
+import fs from "fs";
+import path from "path";
+// FLUX.2 [klein] uses a split-layout: separate diffusion model + LLM text encoder + VAE
+const diffusionModelSrc = process.argv[2] || FLUX_2_KLEIN_4B_Q4_0;
+const llmModelSrc = process.argv[3] || QWEN3_4B_Q4_K_M;
+const vaeModelSrc = process.argv[4] || FLUX_2_KLEIN_4B_VAE;
+const prompt = process.argv[5] || "a futuristic city at sunset, photorealistic";
+const outputDir = process.argv[6] || ".";
+console.log("Loading FLUX.2 [klein] split-layout model...");
+const modelId = await loadModel({
+    modelSrc: diffusionModelSrc,
+    modelType: "diffusion",
+    modelConfig: {
+        device: "gpu",
+        threads: 4,
+        llmModelSrc,
+        vaeModelSrc,
+    },
+    onProgress: (p) => console.log(`Loading: ${p.percentage.toFixed(1)}%`),
+});
+console.log(`Model loaded: ${modelId}`);
+console.log(`\nGenerating: "${prompt}"`);
+const { progressStream, outputs, stats } = diffusion({
+    modelId,
+    prompt,
+    width: 512,
+    height: 512,
+    steps: 20,
+    guidance: 3.5,
+    seed: -1,
+});
+for await (const { step, totalSteps } of progressStream) {
+    process.stdout.write(`\rStep ${step}/${totalSteps}`);
+}
+console.log();
+const buffers = await outputs;
+for (let i = 0; i < buffers.length; i++) {
+    const outputPath = path.join(outputDir, `flux2_${i}.png`);
+    fs.writeFileSync(outputPath, buffers[i]);
+    console.log(`Saved: ${outputPath}`);
+}
+console.log("\nStats:", await stats);
+await unloadModel({ modelId, clearStorage: false });
+console.log("Done.");
+process.exit(0);

package/dist/examples/diffusion-simple.d.ts

@@ -0,0 +1,2 @@
+export {};
+//# sourceMappingURL=diffusion-simple.d.ts.map

package/dist/examples/diffusion-simple.js

@@ -0,0 +1,17 @@
+import { loadModel, unloadModel, diffusion, SD_V2_1_1B_Q8_0 } from "@qvac/sdk";
+import fs from "fs";
+// Minimal diffusion example — single GGUF model, no companion files needed.
+// Works with SD 1.x / 2.x all-in-one models.
+const modelSrc = process.argv[2] || SD_V2_1_1B_Q8_0;
+const prompt = process.argv[3] || "a photo of a cat sitting on a windowsill";
+const modelId = await loadModel({
+    modelSrc,
+    modelType: "diffusion",
+    modelConfig: { prediction: "v" },
+});
+const { outputs } = diffusion({ modelId, prompt });
+const buffers = await outputs;
+fs.writeFileSync("output.png", buffers[0]);
+console.log("Saved: output.png");
+await unloadModel({ modelId, clearStorage: false });
+process.exit(0);

package/dist/examples/diffusion-txt2img.d.ts

@@ -0,0 +1,2 @@
+export {};
+//# sourceMappingURL=diffusion-txt2img.d.ts.map

package/dist/examples/diffusion-txt2img.js

@@ -0,0 +1,40 @@
+import { loadModel, unloadModel, diffusion, FLUX_2_KLEIN_4B_Q4_0, FLUX_2_KLEIN_4B_VAE, QWEN3_4B_Q4_K_M } from "@qvac/sdk";
+import fs from "fs";
+import path from "path";
+const modelSrc = process.argv[2] || FLUX_2_KLEIN_4B_Q4_0;
+const prompt = process.argv[3] ||
+    "a photo of a cat sitting on a windowsill, golden hour lighting";
+const outputDir = process.argv[4] || ".";
+console.log(`Loading diffusion model...`);
+// FLUX.2 models require companion LLM + VAE models
+const modelId = await loadModel({
+    modelSrc,
+    modelType: "diffusion",
+    modelConfig: { device: "gpu", threads: 4, llmModelSrc: QWEN3_4B_Q4_K_M, vaeModelSrc: FLUX_2_KLEIN_4B_VAE },
+    onProgress: (p) => console.log(`Loading: ${p.percentage.toFixed(1)}%`),
+});
+console.log(`Model loaded: ${modelId}`);
+console.log(`\nGenerating: "${prompt}"`);
+const { progressStream, outputs, stats } = diffusion({
+    modelId,
+    prompt,
+    width: 512,
+    height: 512,
+    steps: 20,
+    cfg_scale: 7.0,
+    seed: -1,
+});
+for await (const { step, totalSteps } of progressStream) {
+    process.stdout.write(`\rStep ${step}/${totalSteps}`);
+}
+console.log();
+const buffers = await outputs;
+for (let i = 0; i < buffers.length; i++) {
+    const outputPath = path.join(outputDir, `output_${i}.png`);
+    fs.writeFileSync(outputPath, buffers[i]);
+    console.log(`Saved: ${outputPath}`);
+}
+console.log("\nStats:", await stats);
+await unloadModel({ modelId, clearStorage: false });
+console.log("Done.");
+process.exit(0);

package/dist/examples/embed-p2p.js

@@ -20,7 +20,7 @@ try {
     });
     console.log("\n📝 Example 1: Single Text Embedding");
     console.log("=".repeat(50));
-    const singleEmbedding = await embed({ modelId, text: "Hello, world!" });
+    const { embedding: singleEmbedding } = await embed({ modelId, text: "Hello, world!" });
     console.log("Input: 'Hello, world!'");
     console.log("Embedding dimensions:", singleEmbedding.length);
     console.log("First 10 values:", singleEmbedding.slice(0, 10));
@@ -31,7 +31,7 @@ try {
         "A fast auburn fox leaps over a sleepy canine",
         "Python is a programming language",
     ];
-    const batchEmbeddings = await embed({ modelId, text: texts });
+    const { embedding: batchEmbeddings } = await embed({ modelId, text: texts });
     console.log("Input: Array of", texts.length, "texts");
     console.log("Output: Array of", batchEmbeddings.length, "embeddings");
     const [emb1, emb2, emb3] = batchEmbeddings;

package/dist/examples/finetune/llamacpp-finetune.d.ts

@@ -0,0 +1,2 @@
+export {};
+//# sourceMappingURL=llamacpp-finetune.d.ts.map

package/dist/examples/finetune/llamacpp-finetune.js

@@ -0,0 +1,78 @@
+import { finetune, loadModel, QWEN3_600M_INST_Q4, unloadModel, } from "@qvac/sdk";
+const pauseResumeEnabled = process.argv.includes("--pause-resume");
+let modelId;
+let exitCode = 0;
+async function readProgress(handle, onTick) {
+    for await (const tick of handle.progressStream) {
+        const phase = tick.is_train ? "train" : "val";
+        console.log(`epoch=${tick.current_epoch + 1} step=${tick.global_steps} batch=${tick.current_batch}/${tick.total_batches} ${phase} loss=${tick.loss?.toFixed(4)} acc=${tick.accuracy?.toFixed(4)} eta=${Math.round(tick.eta_ms / 1000)}s`);
+        onTick(tick.global_steps);
+    }
+}
+try {
+    modelId = await loadModel({
+        modelSrc: QWEN3_600M_INST_Q4,
+        modelType: "llm",
+        modelConfig: {
+            device: "gpu",
+            ctx_size: 512,
+        },
+    });
+    console.log(`✅ Model loaded with ID: ${modelId}`);
+    const loadedModelId = modelId;
+    const finetuneParams = {
+        modelId: loadedModelId,
+        options: {
+            trainDatasetDir: "./examples/finetune/input/small_train_HF.jsonl",
+            validation: {
+                type: "dataset",
+                path: "./examples/finetune/input/small_eval_HF.jsonl",
+            },
+            numberOfEpochs: 2,
+            learningRate: 1e-4,
+            lrMin: 1e-8,
+            loraModules: 'attn_q,attn_k,attn_v,attn_o,ffn_gate,ffn_up,ffn_down',
+            assistantLossOnly: true,
+            checkpointSaveSteps: 2,
+            checkpointSaveDir: "./examples/finetune/results/checkpoints",
+            outputParametersDir: "./examples/finetune/results",
+        },
+    };
+    const handle = finetune(finetuneParams);
+    let pauseRequested = false;
+    let pauseResultPromise;
+    const progressTask = readProgress(handle, (globalSteps) => {
+        if (pauseResumeEnabled && !pauseRequested && globalSteps >= 10) {
+            pauseRequested = true;
+            console.log("⏸️ Requesting a pause so the run can be resumed...");
+            pauseResultPromise = finetune({ modelId: loadedModelId, operation: "pause" });
+        }
+    });
+    const initialResult = await handle.result;
+    await progressTask;
+    if (pauseResultPromise) {
+        await pauseResultPromise;
+    }
+    console.log("📦 Initial finetune result:", initialResult);
+    if (pauseResumeEnabled && initialResult.status === "PAUSED") {
+        console.log("▶️ Resuming from the saved checkpoint...");
+        const resumedHandle = finetune({
+            ...finetuneParams,
+            operation: "resume",
+        });
+        const resumedProgressTask = readProgress(resumedHandle, function () { });
+        const resumedResult = await resumedHandle.result;
+        await resumedProgressTask;
+        console.log("✅ Resumed finetune result:", resumedResult);
+    }
+}
+catch (error) {
+    console.error("❌ Error:", error);
+    exitCode = 1;
+}
+finally {
+    if (modelId) {
+        await unloadModel({ modelId, clearStorage: false });
+    }
+}
+process.exit(exitCode);

package/dist/examples/logging-streaming.js

@@ -52,7 +52,7 @@ try {
         history: messages,
         stream: true,
     });
-    const embedding = await embed({
+    const { embedding } = await embed({
         modelId: embedModelId,
         text: messages[0]?.content ?? "Hello, world!",
     });

package/dist/examples/mcp-websearch.js

@@ -12,7 +12,9 @@
 import { completion, loadModel, unloadModel, QWEN3_1_7B_INST_Q4, } from "../index.js";
 // MCP SDK is a user-installed optional dependency
 // Install with: bun add @modelcontextprotocol/sdk
+// eslint-disable-next-line import/no-unresolved
 import { Client } from "@modelcontextprotocol/sdk/client/index.js";
+// eslint-disable-next-line import/no-unresolved
 import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
 function parseSearchResults(mcpResult) {
     try {

package/dist/examples/ocr-fasttext.js

@@ -1,3 +1,14 @@
+/**
+ * OCR example using the QVAC SDK.
+ *
+ * Usage:
+ *   bun examples/ocr-fasttext.ts [path-to-image]
+ *
+ * This example requires a test image (default: examples/image/basic_test.bmp).
+ * Sample images are available in the QVAC source repository, but not included in the published npm package.
+ * Pass a custom image path, or download the default image into examples/image/:
+ *   https://github.com/tetherto/qvac/blob/main/packages/sdk/examples/image/basic_test.bmp
+ */
 import { close, loadModel, ocr, OCR_LATIN_RECOGNIZER_1, unloadModel, } from "@qvac/sdk";
 import path from "path";
 import { fileURLToPath } from "url";

package/dist/examples/profiling/per-call.js

@@ -9,16 +9,16 @@ try {
     });
     console.log("Model loaded:", modelId);
     console.log("\n=== Embed with per-call profiling ===");
-    const embedding1 = await embed({ modelId, text: "Profile this specific call" }, { profiling: { enabled: true, includeServerBreakdown: true } });
+    const { embedding: embedding1 } = await embed({ modelId, text: "Profile this specific call" }, { profiling: { enabled: true, includeServerBreakdown: true } });
     console.log("Embedding dimensions:", embedding1.length);
     console.log("\n=== Embed without profiling ===");
-    const embedding2 = await embed({
+    const { embedding: embedding2 } = await embed({
         modelId,
         text: "This call is not profiled",
     });
     console.log("Embedding dimensions:", embedding2.length);
     console.log("\n=== Embed with profiling explicitly disabled ===");
-    const embedding3 = await embed({ modelId, text: "Profiling explicitly disabled for this call" }, { profiling: { enabled: false } });
+    const { embedding: embedding3 } = await embed({ modelId, text: "Profiling explicitly disabled for this call" }, { profiling: { enabled: false } });
     console.log("Embedding dimensions:", embedding3.length);
     await unloadModel({ modelId });
     console.log("\n=== Profiler Summary (per-call data only) ===");

package/dist/examples/rag/rag-chromadb.js

@@ -96,7 +96,7 @@ try {
     for (const s of samples) {
         ids.push(String(s.id));
         documents.push(s.text);
-        embeddings.push(await embed({ modelId, text: s.text }));
+        embeddings.push((await embed({ modelId, text: s.text })).embedding);
     }
     await collection.add({
         ids,
@@ -104,7 +104,7 @@ try {
         embeddings,
     });
     console.log("🔎 Searching for similar documents...");
-    const queryEmbedding = await embed({ modelId, text: query });
+    const { embedding: queryEmbedding } = await embed({ modelId, text: query });
     // Query top 3 by vector similarity and include distances
     const res = await collection.query({
         queryEmbeddings: [queryEmbedding],

package/dist/examples/rag/rag-hyperdb/pipeline.js

@@ -33,7 +33,7 @@ try {
     console.log(`   Created ${chunks.length} chunks`);
     console.log("\n🧠 Step 2: Generating embeddings (batch)...");
     const texts = chunks.map((chunk) => chunk.content);
-    const embeddings = await embed({ modelId, text: texts });
+    const { embedding: embeddings } = await embed({ modelId, text: texts });
     const embeddedDocs = chunks.map((chunk, i) => ({
         id: chunk.id,
         content: chunk.content,

package/dist/examples/rag/rag-lancedb.js

@@ -63,7 +63,7 @@ try {
     console.log("📚 Embedding documents...");
     const documents = [];
     for (const sample of samples) {
-        const embedding = await embed({ modelId, text: sample.text });
+        const { embedding } = await embed({ modelId, text: sample.text });
         const record = {
             id: sample.id,
             text: sample.text,
@@ -73,7 +73,7 @@ try {
     }
     await documentsTable.add(documents);
     console.log("🔎 Searching for similar documents...");
-    const queryEmbedding = await embed({ modelId, text: query });
+    const { embedding: queryEmbedding } = await embed({ modelId, text: query });
     const results = (await documentsTable
         .vectorSearch(queryEmbedding)
         .limit(1)

package/dist/examples/rag/rag-sqlite.js

@@ -58,7 +58,7 @@ try {
 `);
     console.log("📚 Embedding documents...");
     for (const sample of samples) {
-        const embedding = await embed({ modelId, text: sample.text });
+        const { embedding } = await embed({ modelId, text: sample.text });
         db.exec({
             sql: "INSERT INTO documents VALUES (?, ?, vector_as_f32(?))",
             bind: [sample.id, sample.text, JSON.stringify(embedding)],
@@ -72,7 +72,7 @@ try {
     db.exec(`SELECT vector_quantize_preload('documents', 'embedding')`);
     // Search for similar documents
     console.log("🔎 Searching for similar documents...");
-    const queryEmbedding = await embed({ modelId, text: query });
+    const { embedding: queryEmbedding } = await embed({ modelId, text: query });
     const results = [];
     // Perform vector search
     db.exec({

package/dist/examples/suspend-resume.d.ts

@@ -0,0 +1,2 @@
+export {};
+//# sourceMappingURL=suspend-resume.d.ts.map

package/dist/examples/suspend-resume.js

@@ -0,0 +1,52 @@
+import { loadModel, LLAMA_3_2_1B_INST_Q4_0, completion, unloadModel, suspend, resume, } from "@qvac/sdk";
+try {
+    // Load a model
+    const modelId = await loadModel({
+        modelSrc: LLAMA_3_2_1B_INST_Q4_0,
+        modelType: "llm",
+        onProgress: (progress) => {
+            console.log(progress);
+        },
+    });
+    console.log("✅ Model loaded\n");
+    // Run a completion before suspending
+    console.log("--- Completion before suspend ---");
+    const result1 = completion({
+        modelId,
+        history: [{ role: "user", content: "Say hello in one word" }],
+        stream: true,
+    });
+    for await (const token of result1.tokenStream) {
+        process.stdout.write(token);
+    }
+    console.log("\n");
+    // Suspend all networking and storage (e.g. app going to background)
+    console.log("⏸️  Suspending...");
+    await suspend();
+    console.log("✅ Suspended — Hyperswarm and Corestore resources are paused\n");
+    // Simulate time in background
+    console.log("💤 Simulating 3 seconds in background...");
+    await new Promise((resolve) => setTimeout(resolve, 3000));
+    // Resume when returning to foreground
+    console.log("▶️  Resuming...");
+    await resume();
+    console.log("✅ Resumed — networking and storage restored\n");
+    // Run another completion after resuming
+    console.log("--- Completion after resume ---");
+    const result2 = completion({
+        modelId,
+        history: [{ role: "user", content: "Say goodbye in one word" }],
+        stream: true,
+    });
+    for await (const token of result2.tokenStream) {
+        process.stdout.write(token);
+    }
+    console.log("\n");
+    await unloadModel({ modelId });
+    console.log("✅ Model unloaded");
+    process.exit(0);
+}
+catch (error) {
+    console.error("❌ Error:", error);
+    process.exit(1);
+}

package/dist/examples/transcription/parakeet-ctc-filesystem.js

@@ -1,15 +1,14 @@
-import { loadModel, unloadModel, transcribe, PARAKEET_CTC_FP32, PARAKEET_CTC_DATA_FP32, PARAKEET_CTC_TOKENIZER, } from "@qvac/sdk";
+import { loadModel, unloadModel, transcribe, PARAKEET_CTC_FP32, PARAKEET_CTC_TOKENIZER, } from "@qvac/sdk";
 const args = process.argv.slice(2);
 if (!args[0]) {
     console.error("Usage: bun run examples/transcription/parakeet-ctc-filesystem.ts <wav-file> " +
-        "[model.onnx] [model.onnx_data] [tokenizer.json]");
+        "[model.onnx] [tokenizer.json]");
     console.error("\nIf model paths are omitted, defaults to registry models.");
     process.exit(1);
 }
 const audioFilePath = args[0];
 const parakeetCtcModelSrc = args[1] ?? PARAKEET_CTC_FP32;
-const parakeetCtcModelDataSrc = args[2] ?? PARAKEET_CTC_DATA_FP32;
-const parakeetTokenizerSrc = args[3] ?? PARAKEET_CTC_TOKENIZER;
+const parakeetTokenizerSrc = args[2] ?? PARAKEET_CTC_TOKENIZER;
 try {
     console.log("Loading Parakeet CTC model...");
     const modelId = await loadModel({
@@ -18,7 +17,6 @@ try {
         modelConfig: {
             modelType: "ctc",
             parakeetCtcModelSrc,
-            parakeetCtcModelDataSrc,
             parakeetTokenizerSrc,
         },
         onProgress: (progress) => {

package/dist/examples/transcription/parakeet-microphone-record.js

@@ -1,56 +1,64 @@
-import { loadModel, unloadModel, transcribeStream, PARAKEET_TDT_ENCODER_FP32, PARAKEET_TDT_ENCODER_DATA_FP32, PARAKEET_TDT_DECODER_FP32, PARAKEET_TDT_VOCAB, PARAKEET_TDT_PREPROCESSOR_FP32, } from "@qvac/sdk";
+/**
+ * Microphone → Parakeet transcription using chunked `transcribe` calls.
+ *
+ * Usage: bun run examples/transcription/parakeet-microphone-record.ts
+ *
+ * Captures 3-second audio chunks from the microphone and sends each to the
+ * batch `transcribe` API. Press Ctrl+C to quit.
+ *
+ * Requirements: FFmpeg installed, microphone access.
+ */
+import { loadModel, unloadModel, transcribe, PARAKEET_TDT_ENCODER_FP32, PARAKEET_TDT_DECODER_FP32, PARAKEET_TDT_VOCAB, PARAKEET_TDT_PREPROCESSOR_FP32, } from "@qvac/sdk";
 import { spawn, spawnSync } from "child_process";
 import { platform } from "os";
-function checkFFmpeg() {
-    const result = spawnSync("ffmpeg", ["-version"], { stdio: "ignore" });
-    if (result.error || result.status !== 0) {
-        throw new Error("FFmpeg is required but not found in PATH.");
-    }
-}
-function getAudioDevice() {
-    switch (platform()) {
-        case "darwin":
-            return ":0";
-        case "linux":
-            return "default";
-        case "win32":
-            // Change as per your system
-            return "audio=@device_cm_{33D9A762-90C8-11D0-BD43-00A0C911CE86}\\wave_{58C07110-A4FD-4FF8-BA10-5A3C14389F71}";
-        default:
-            throw new Error(`Unsupported platform: ${platform()}`);
-    }
-}
+const SAMPLE_RATE = 16000;
+const BYTES_PER_SAMPLE = 2; // s16le
+const CHUNK_DURATION_S = 3;
+const CHUNK_SIZE = SAMPLE_RATE * BYTES_PER_SAMPLE * CHUNK_DURATION_S;
 function getAudioInputArgs() {
     switch (platform()) {
         case "darwin":
-            return ["-f", "avfoundation", "-i", getAudioDevice()];
-        case "linux":
-            return ["-f", "pulse", "-i", getAudioDevice()];
+            return ["-f", "avfoundation", "-i", ":0"];
         case "win32":
-            return ["-f", "dshow", "-i", getAudioDevice()];
+            return [
+                "-f",
+                "dshow",
+                "-i",
+                "audio=@device_cm_{33D9A762-90C8-11D0-BD43-00A0C911CE86}\\wave_{58C07110-A4FD-4FF8-BA10-5A3C14389F71}",
+            ];
+        case "linux":
+            return ["-f", "pulse", "-i", "default"];
         default:
             throw new Error(`Unsupported platform: ${platform()}`);
     }
 }
-checkFFmpeg();
+// ── Main ──
+try {
+    const r = spawnSync("ffmpeg", ["-version"], { stdio: "ignore" });
+    if (r.error || r.status !== 0)
+        throw new Error("FFmpeg not found");
+}
+catch {
+    console.error("FFmpeg is required. Install it and try again.");
+    process.exit(1);
+}
 console.log("Loading Parakeet model...");
 const modelId = await loadModel({
     modelSrc: PARAKEET_TDT_ENCODER_FP32,
     modelType: "parakeet",
     modelConfig: {
         parakeetEncoderSrc: PARAKEET_TDT_ENCODER_FP32,
-        parakeetEncoderDataSrc: PARAKEET_TDT_ENCODER_DATA_FP32,
         parakeetDecoderSrc: PARAKEET_TDT_DECODER_FP32,
         parakeetVocabSrc: PARAKEET_TDT_VOCAB,
         parakeetPreprocessorSrc: PARAKEET_TDT_PREPROCESSOR_FP32,
     },
     onProgress: (p) => console.log(`Download: ${p.percentage.toFixed(1)}%`),
 });
-console.log("Model loaded. Speak into your microphone (Ctrl+C to stop):\n");
+console.log("Model loaded.\n");
 const ffmpeg = spawn("ffmpeg", [
     ...getAudioInputArgs(),
     "-ar",
-    "16000",
+    String(SAMPLE_RATE),
     "-ac",
     "1",
     "-sample_fmt",
@@ -59,9 +67,11 @@ const ffmpeg = spawn("ffmpeg", [
     "s16le",
     "pipe:1",
 ], { stdio: ["ignore", "pipe", "ignore"] });
-const CHUNK_SIZE = 96000; // ~3s of 16kHz 16-bit mono
+if (!ffmpeg.stdout)
+    throw new Error("Failed to open microphone");
 let buffer = Buffer.alloc(0);
 let processing = false;
+console.log("Listening... speak and pause to see transcriptions.\n");
 ffmpeg.stdout.on("data", (chunk) => {
     buffer = Buffer.concat([buffer, chunk]);
     if (buffer.length >= CHUNK_SIZE && !processing) {
@@ -70,10 +80,9 @@ ffmpeg.stdout.on("data", (chunk) => {
         processing = true;
         void (async () => {
             try {
-                for await (const text of transcribeStream({ modelId, audioChunk })) {
-                    if (text.trim() && !text.includes("[No speech detected]")) {
-                        process.stdout.write(text);
-                    }
+                const text = await transcribe({ modelId, audioChunk });
+                if (text.trim() && !text.includes("[No speech detected]")) {
+                    console.log(`> ${text.trim()}`);
                 }
             }
             catch (err) {

package/dist/examples/transcription/parakeet-sortformer.js

@@ -1,4 +1,15 @@
-import { loadModel, unloadModel, transcribe, PARAKEET_TDT_ENCODER_FP32, PARAKEET_TDT_ENCODER_DATA_FP32, PARAKEET_TDT_DECODER_FP32, PARAKEET_TDT_VOCAB, PARAKEET_TDT_PREPROCESSOR_FP32, PARAKEET_SORTFORMER_FP32, } from "@qvac/sdk";
+/**
+ * Parakeet Sortformer diarization + TDT transcription example.
+ *
+ * Usage:
+ *   bun examples/transcription/parakeet-sortformer.ts [sortformer-src] [path-to-audio]
+ *
+ * This example requires a test audio file (default: examples/audio/diarization-sample-16k.wav).
+ * Sample audio files are available in the QVAC source repository, but not included in the published npm package.
+ * Pass a custom audio path as the second argument, or download the default audio into examples/audio/:
+ *   https://github.com/tetherto/qvac/blob/main/packages/sdk/examples/audio/diarization-sample-16k.wav
+ */
+import { loadModel, unloadModel, transcribe, PARAKEET_TDT_ENCODER_FP32, PARAKEET_TDT_DECODER_FP32, PARAKEET_TDT_VOCAB, PARAKEET_TDT_PREPROCESSOR_FP32, PARAKEET_SORTFORMER_FP32, } from "@qvac/sdk";
 import { dirname, join } from "path";
 import { fileURLToPath } from "url";
 import { readFileSync, writeFileSync, mkdirSync } from "fs";
@@ -6,7 +17,7 @@ import { tmpdir } from "os";
 const __dirname = dirname(fileURLToPath(import.meta.url));
 const args = process.argv.slice(2);
 const sortformerSrc = args[0] ?? PARAKEET_SORTFORMER_FP32;
-const defaultAudioPath = join(__dirname, "..", "..", "..", "examples", "transcription", "audio", "diarization-sample-16k.wav");
+const defaultAudioPath = join(__dirname, "..", "audio", "diarization-sample-16k.wav");
 const audioFilePath = args[1] ?? defaultAudioPath;
 // ── Step 1: Diarize with Sortformer ──
 const sfModelId = await loadModel({
@@ -29,7 +40,6 @@ const tdtModelId = await loadModel({
     modelType: "parakeet",
     modelConfig: {
         parakeetEncoderSrc: PARAKEET_TDT_ENCODER_FP32,
-        parakeetEncoderDataSrc: PARAKEET_TDT_ENCODER_DATA_FP32,
         parakeetDecoderSrc: PARAKEET_TDT_DECODER_FP32,
         parakeetVocabSrc: PARAKEET_TDT_VOCAB,
         parakeetPreprocessorSrc: PARAKEET_TDT_PREPROCESSOR_FP32,

package/dist/examples/transcription/parakeet-tdt-filesystem.js

@@ -1,17 +1,16 @@
-import { loadModel, unloadModel, transcribe, PARAKEET_TDT_ENCODER_FP32, PARAKEET_TDT_ENCODER_DATA_FP32, PARAKEET_TDT_DECODER_FP32, PARAKEET_TDT_VOCAB, PARAKEET_TDT_PREPROCESSOR_FP32, } from "@qvac/sdk";
+import { loadModel, unloadModel, transcribe, PARAKEET_TDT_ENCODER_FP32, PARAKEET_TDT_DECODER_FP32, PARAKEET_TDT_VOCAB, PARAKEET_TDT_PREPROCESSOR_FP32, } from "@qvac/sdk";
 const args = process.argv.slice(2);
 if (!args[0]) {
     console.error("Usage: bun run examples/transcription/parakeet-tdt-filesystem.ts <wav-file-path> " +
-        "[encoder-onnx] [encoder-data] [decoder-onnx] [vocab-txt] [preprocessor-onnx]");
+        "[encoder-onnx] [decoder-onnx] [vocab-txt] [preprocessor-onnx]");
     console.error("\nIf model paths are omitted, defaults to registry models.");
     process.exit(1);
 }
 const audioFilePath = args[0];
 const parakeetEncoderSrc = args[1] ?? PARAKEET_TDT_ENCODER_FP32;
-const parakeetEncoderDataSrc = args[2] ?? PARAKEET_TDT_ENCODER_DATA_FP32;
-const parakeetDecoderSrc = args[3] ?? PARAKEET_TDT_DECODER_FP32;
-const parakeetVocabSrc = args[4] ?? PARAKEET_TDT_VOCAB;
-const parakeetPreprocessorSrc = args[5] ?? PARAKEET_TDT_PREPROCESSOR_FP32;
+const parakeetDecoderSrc = args[2] ?? PARAKEET_TDT_DECODER_FP32;
+const parakeetVocabSrc = args[3] ?? PARAKEET_TDT_VOCAB;
+const parakeetPreprocessorSrc = args[4] ?? PARAKEET_TDT_PREPROCESSOR_FP32;
 try {
     console.log("Starting Parakeet transcription example...");
     console.log("Loading Parakeet model...");
@@ -20,7 +19,6 @@ try {
         modelType: "parakeet",
         modelConfig: {
             parakeetEncoderSrc,
-            parakeetEncoderDataSrc,
             parakeetDecoderSrc,
             parakeetVocabSrc,
             parakeetPreprocessorSrc,

package/dist/examples/transcription/whispercpp-filesystem-streaming.d.ts

@@ -0,0 +1,2 @@
+export {};
+//# sourceMappingURL=whispercpp-filesystem-streaming.d.ts.map