Emoji Space Adventure

{"name":"Teachable Machine - Sound Model Demo","description":"Base project for a teachable machine audio model.","photo":"https://res.cloudinary.com/dzv7hjwfn/image/upload/useojsudad4dwru7bgqb","view_count":19,"fork_count":5,"expires_at":null,"created_at":"2025-05-20T18:23:02.231474Z","updated_at":"2025-05-20T18:23:02.231474Z","user_id":166,"status":"PUBLIC","parent_id":null,"id":8010,"user":{"username":"m_ivlev","id":166,"password_hash":"$2b$12$lM.SwMhsrEJrs7ZjNyj9e.FOyWqAZgNBSeOEkB8gCGEsXkmGPZLu6","updated_at":"2024-08-05T03:36:08.774314Z","reset_token_expiry":null,"subscription_status":null,"photo":null,"email":"markivlev@gmail.com","recess_id":"38a987b1-569d-47cc-ae61-0c84198aa65c","created_at":"2024-08-05T03:36:08.774307Z","reset_token":null,"stripe_customer_id":null,"seats":null},"code":{"script.js":"const URL = \"https://teachablemachine.withgoogle.com/models/AWOPAP5HI/\";\n\nlet currentPrediction = \"\";\n\nlet currentConfidence = 0;\n\nfunction setup() {\n createCanvas(windowWidth, windowHeight);\n background(135, 206, 235); // Sky blue background\n}\n\nfunction draw() {\n // Change background color based on the current prediction\n if (currentPrediction === \"Background Noise\") {\n background(255); // White\n } else if (currentPrediction === \"G\") {\n background(34, 139, 34); // Jungle green\n } else if (currentPrediction === \"A\") {\n background(0, 255, 255); // Aqua\n } else if (currentPrediction === \"B\") {\n background(128, 0, 32); // Burgundy\n } else {\n background(135, 206, 235); // Default Sky blue background\n }\n\n textSize(32);\n textAlign(CENTER, CENTER);\n fill(0); // Text color\n text(currentPrediction, width / 2, height / 2);\n textSize(24);\n text(`Confidence: ${(currentConfidence * 100).toFixed(2)}%`, width / 2, height / 2 + 40);\n}\n\nasync function createModel() {\n const checkpointURL = URL + \"model.json\"; // model topology\n const metadataURL = URL + \"metadata.json\"; // model metadata\n\n const recognizer = speechCommands.create(\n \"BROWSER_FFT\", // Fourier transform type, not useful to change\n undefined, // Speech commands vocabulary feature, not useful for your models\n checkpointURL,\n metadataURL);\n\n // Check that model and metadata are loaded via HTTPS requests.\n await recognizer.ensureModelLoaded();\n\n return recognizer;\n}\n\ninit();\n\nasync function init() {\n const recognizer = await createModel();\n const classLabels = recognizer.wordLabels(); // Get class labels\n\n recognizer.listen(result => {\n const scores = result.scores; // Probability of prediction for each class\n const maxScoreIndex = scores.indexOf(Math.max(...scores));\n currentPrediction = classLabels[maxScoreIndex];\n currentConfidence = scores[maxScoreIndex];\n }, {\n includeSpectrogram: true,\n probabilityThreshold: 0.75,\n invokeCallbackOnNoiseAndUnknown: true,\n overlapFactor: 0.75 // Increased to make predictions more frequently\n });\n}\n\n","style.css":"body { margin: 0; } canvas { display: block; }","index.html":"\n\n\n\n \n \n Emoji Space Adventure\n \n \n \n \n \n\n\n\n

\n \n\n\n"},"chat_history":[{"code_id":244368,"deleted":0,"input_tokens":null,"id":143429,"project_id":8010,"sender":"server_script","message":"

Add your new assets to the code

\n\n```javascript\nfunction preload() {\n\n\tcover = loadImage(\"@asset('cover')\");\n}\n```","created_at":"2025-05-20T18:22:20.007228Z","output_tokens":null},{"code_id":244368,"deleted":0,"input_tokens":null,"id":143451,"project_id":8010,"sender":"human","message":"Can you update the prediction more frequently? It is a little slow to react","created_at":"2025-05-20T18:58:44.679966Z","output_tokens":null},{"code_id":244368,"deleted":0,"input_tokens":3087,"id":143452,"project_id":8010,"sender":"ai","message":"

\n# Reasoning\nThe user wants to increase the frequency of predictions to make the system more responsive. This can be achieved by adjusting the `overlapFactor` parameter in the recognizer's `listen` method. Increasing this factor allows the recognizer to make predictions more frequently by overlapping more audio slices.\n

\n\n

\n# Answer: \n

\n\nWe can update the prediction more frequently by adjusting the `overlapFactor` in the `init` function.\n\n```javascript\n// script.js\nasync function init() {\n const recognizer = await createModel();\n const classLabels = recognizer.wordLabels(); // Get class labels\n\n recognizer.listen(result => {\n const scores = result.scores; // Probability of prediction for each class\n const maxScoreIndex = scores.indexOf(Math.max(...scores));\n currentPrediction = classLabels[maxScoreIndex];\n currentConfidence = scores[maxScoreIndex];\n }, {\n includeSpectrogram: true,\n probabilityThreshold: 0.75,\n invokeCallbackOnNoiseAndUnknown: true,\n overlapFactor: 0.75 // Increased to make predictions more frequently\n });\n}\n```\n\n- The `overlapFactor` is increased from `0.50` to `0.75`, which will make predictions more frequently by overlapping more audio segments.\n- This change should make your application more responsive to changes in audio input.","created_at":"2025-05-20T18:58:44.843925Z","output_tokens":351}],"assets":[{"project_id":8010,"created_at":"2025-05-20T18:22:19.673355Z","resource_type":"image","id":74565,"cloudinary_id":"useojsudad4dwru7bgqb","name":"cover","deleted":false}],"messages_sent":11,"comments":[],"steps":[]}