[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-00328a14a70095c4-build-vibevoice-speech-pipelines-in-colab-summary":3,"summaries-facets-categories":215,"summary-related-00328a14a70095c4-build-vibevoice-speech-pipelines-in-colab-summary":3784},{"id":4,"title":5,"ai":6,"body":13,"categories":162,"created_at":164,"date_modified":164,"description":155,"extension":165,"faq":164,"featured":166,"kicker_label":164,"meta":167,"navigation":196,"path":197,"published_at":198,"question":164,"scraped_at":199,"seo":200,"sitemap":201,"source_id":202,"source_name":203,"source_type":204,"source_url":205,"stem":206,"tags":207,"thumbnail_url":164,"tldr":212,"tweet":164,"unknown_tags":213,"__hash__":214},"summaries\u002Fsummaries\u002F00328a14a70095c4-build-vibevoice-speech-pipelines-in-colab-summary.md","Build VibeVoice Speech Pipelines in Colab",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","x-ai\u002Fgrok-4.1-fast",9212,2845,29040,0.00324225,{"type":14,"value":15,"toc":154},"minimark",[16,21,57,91,95,111,118,122,125,132,136,151],[17,18,20],"h2",{"id":19},"setup-vibevoice-environment-for-instant-asr-and-tts","Setup VibeVoice Environment for Instant ASR and TTS",[22,23,24,25,29,30,36,37,40,41,44,45,48,49,52,53,56],"p",{},"Install via ",[26,27,28],"code",{},"!pip install git+https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Ftransformers.git"," plus torch, gradio, and clone ",[31,32,33],"a",{"href":33,"rel":34},"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FVibeVoice",[35],"nofollow",". Restart runtime after editable install ",[26,38,39],{},"-e \u002Fcontent\u002FVibeVoice",". Load 7B ASR (",[26,42,43],{},"microsoft\u002FVibeVoice-ASR-HF",", ~14GB download, float16 on auto device) and 0.5B TTS (",[26,46,47],{},"microsoft\u002FVibeVoice-Realtime-0.5B",", set DDPM steps to 20). Use ",[26,50,51],{},"AutoProcessor"," for ASR inputs and ",[26,54,55],{},"VibeVoiceTextTokenizerFast"," for TTS. This enables 50+ languages, single-pass 60min transcription, and ~300ms streaming latency from ultra-low 7.5Hz tokenizers combining LLM context with diffusion audio gen.",[22,58,59,60,63,64,67,68,71,72,75,76,79,80,82,83,86,87,90],{},"Key ",[26,61,62],{},"transcribe(audio_path, context=None)"," wraps ",[26,65,66],{},"apply_transcription_request"," then ",[26,69,70],{},"generate"," and ",[26,73,74],{},"decode"," (formats: 'parsed', 'transcription_only'). For TTS, ",[26,77,78],{},"synthesize(text, voice=\"Grace\", cfg_scale=3.0, steps=20)"," uses ",[26,81,70],{}," with ",[26,84,85],{},"return_speech=True",", ",[26,88,89],{},"speaker_name",", outputs 24kHz numpy audio—save via soundfile.",[17,92,94],{"id":93},"unlock-asr-precision-with-speakers-context-and-batches","Unlock ASR Precision with Speakers, Context, and Batches",[22,96,97,98,102,103,106,107,110],{},"Achieve speaker diarization on podcasts: parsed output yields list of dicts with 'Speaker', 'Start\u002FEnd' timestamps (s), 'Content'—e.g., ",[99,100,101],"span",{},"Speaker 1"," 0.00s-5.23s: \"Hello...\". Context prompts fix hotwords: German sample mishears without ",[26,104,105],{},"context=\"About VibeVoice\"",", correctly IDs \"VibeVoice\" with it. Batch multiple audios: ",[26,108,109],{},"apply_transcription_request(audio=[path1,path2], prompt=[ctx1,None])"," generates all at once, decode to list of texts—scales for pipelines without loops.",[22,112,113,114,117],{},"Trade-offs: Long audio risks OOM; mitigate with ",[26,115,116],{},"acoustic_tokenizer_chunk_size=64000"," in generate or bfloat16 dtype. Handles MP3\u002FWAV\u002FFLAC uploads via Colab files.",[17,119,121],{"id":120},"craft-expressive-tts-voices-cfg-and-long-form-scaling","Craft Expressive TTS: Voices, CFG, and Long-Form Scaling",[22,123,124],{},"Four presets (Carter, Grace, Emma, Davis) yield distinct styles—compare same text across voices for prosody variety. CFG scale 1-5 controls adherence (3.0 default natural), steps 5-50 trade quality\u002Fspeed (15 fast demo, 25 long-form). Generates 10min+ coherent speech: podcast script (~200 words) to 45s audio at cfg=3.5\u002Fsteps=25. Next-token diffusion ensures pauses, intonation unlike rigid TTS.",[22,126,127,128,131],{},"Real-time viable: low-param model on CUDA\u002FCPU. Gradio UI exposes text, voice dropdown, sliders for cfg\u002Fsteps—",[26,129,130],{},"gr.Interface(fn=tts_gradio)"," launches shareable demo.",[17,133,135],{"id":134},"chain-into-speech-to-speech-pipelines-with-optimizations","Chain into Speech-to-Speech Pipelines with Optimizations",[22,137,138,139,142,143,146,147,150],{},"End-to-end: Transcribe input (",[26,140,141],{},"transcribe(SAMPLE_GERMAN, context=\"About VibeVoice\")"," → \"Über VibeVoice...\"), append response text, synthesize—yields conversational audio. Optimizations: ",[26,144,145],{},"torch.cuda.empty_cache()",", gradient checkpointing, reduce steps to 10 for speed. Download outputs like ",[26,148,149],{},"\u002Fcontent\u002Flongform_output.wav",". Responsible use: Research only, disclose AI speech, avoid impersonation.",[22,152,153],{},"Outcomes: Powers voice assistants, podcasts, accessibility—batch ASR cuts processing time, TTS enables interactive apps via Gradio.",{"title":155,"searchDepth":156,"depth":156,"links":157},"",2,[158,159,160,161],{"id":19,"depth":156,"text":20},{"id":93,"depth":156,"text":94},{"id":120,"depth":156,"text":121},{"id":134,"depth":156,"text":135},[163],"AI & LLMs",null,"md",false,{"content_references":168,"triage":191},[169,173,176,179,183,186],{"type":170,"title":171,"url":33,"context":172},"tool","VibeVoice","mentioned",{"type":170,"title":174,"url":175,"context":172},"VibeVoice-ASR-HF","https:\u002F\u002Fhuggingface.co\u002Fmicrosoft\u002FVibeVoice-ASR-HF",{"type":170,"title":177,"url":178,"context":172},"VibeVoice-Realtime-0.5B","https:\u002F\u002Fhuggingface.co\u002Fmicrosoft\u002FVibeVoice-Realtime-0.5B",{"type":180,"title":181,"url":182,"context":172},"paper","VibeVoice ASR Paper","https:\u002F\u002Farxiv.org\u002Fpdf\u002F2601.18184",{"type":180,"title":184,"url":185,"context":172},"VibeVoice TTS Paper","https:\u002F\u002Fopenreview.net\u002Fpdf?id=FihSkzyxdv",{"type":187,"title":188,"url":189,"context":190},"other","Full Tutorial Codes","https:\u002F\u002Fgithub.com\u002FMarktechpost\u002FAI-Tutorial-Codes-Included\u002Fblob\u002Fmain\u002FVoice%20AI\u002Fmicrosoft_vibevoice_asr_realtime_tts_speech_to_speech_marktechpost.py","recommended",{"relevance":192,"novelty":193,"quality":193,"actionability":192,"composite":194,"reasoning":195},5,4,4.55,"Category: AI & LLMs. The article provides a detailed, hands-on tutorial for building speech pipelines using Microsoft VibeVoice, addressing practical applications for AI-powered products. It includes specific code snippets and setup instructions that developers can directly implement, making it highly actionable.",true,"\u002Fsummaries\u002F00328a14a70095c4-build-vibevoice-speech-pipelines-in-colab-summary","2026-04-13 01:22:15","2026-04-13 17:53:25",{"title":5,"description":155},{"loc":197},"00328a14a70095c4","MarkTechPost","article","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F04\u002F12\u002Fa-hands-on-coding-tutorial-for-microsoft-vibevoice-covering-speaker-aware-asr-real-time-tts-and-speech-to-speech-pipelines\u002F","summaries\u002F00328a14a70095c4-build-vibevoice-speech-pipelines-in-colab-summary",[208,209,210,211],"python","ai-tools","machine-learning","open-source","Run Microsoft VibeVoice's 7B ASR for speaker diarization and context-aware transcription plus 0.5B real-time TTS with 300ms latency using this Colab code—handles 60min audio and long-form synthesis.",[],"zmPVL5sYTbsBHWCVZHusK-U8VVYqFL1AzQHx0NUJRz8",[216,219,222,224,227,230,232,234,236,238,240,242,245,247,249,251,253,255,257,259,261,263,266,269,271,273,276,278,280,283,285,287,289,291,293,295,297,299,301,303,305,307,309,311,313,315,317,319,321,323,325,327,329,331,333,335,337,339,341,343,345,347,349,351,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,385,387,389,391,393,395,397,399,401,403,405,407,409,411,413,415,417,419,421,423,425,427,429,431,433,435,437,439,441,443,445,447,449,451,453,455,457,459,461,463,465,467,469,471,473,475,477,479,481,483,485,487,489,491,493,495,497,499,501,503,505,507,509,511,513,515,517,519,521,523,525,527,529,531,533,535,538,540,542,544,546,548,550,552,554,556,558,560,562,564,566,568,570,572,574,576,578,580,582,584,586,588,590,592,594,596,598,600,602,604,606,608,610,612,614,616,618,620,622,624,626,628,630,632,634,636,638,640,642,644,646,648,650,652,654,656,658,660,662,664,666,668,670,672,674,676,678,680,682,684,686,688,690,692,694,696,698,700,702,704,706,708,710,712,714,716,718,720,722,724,726,728,730,732,734,736,738,740,742,744,746,748,750,752,754,756,758,760,762,764,766,768,770,772,774,776,778,780,782,784,786,788,790,792,794,796,798,800,802,804,806,808,810,812,814,816,818,820,822,824,826,828,830,832,834,836,838,840,842,844,846,848,850,852,854,856,858,860,862,864,866,868,870,872,874,876,878,880,882,884,886,888,890,892,894,896,898,900,902,904,906,908,910,912,914,916,918,920,922,924,926,928,930,932,934,936,938,940,942,944,946,948,950,952,954,956,958,960,962,964,966,968,970,972,974,976,978,980,982,984,986,988,990,992,994,996,998,1000,1002,1004,1006,1008,1010,1012,1014,1016,1018,1020,1022,1024,1026,1028,1030,1032,1034,1036,1038,1040,1042,1044,1046,1048,1050,1052,1054,1056,1058,1060,1062,1064,1066,1068,1070,1072,1074,1076,1078,1080,1082,1084,1086,1088,1090,1092,1094,1096,1098,1100,1102,1104,1106,1108,1110,1112,1114,1116,1118,1120,1122,1124,1126,1128,1130,1132,1134,1136,1138,1140,1142,1144,1146,1148,1150,1152,1154,1156,1158,1160,1162,1164,1166,1168,1170,1172,1174,1176,1178,1180,1182,1184,1186,1188,1190,1192,1194,1196,1198,1200,1202,1204,1206,1208,1210,1212,1214,1216,1218,1220,1222,1224,1226,1228,1230,1232,1234,1236,1238,1240,1242,1244,1246,1248,1250,1252,1254,1256,1258,1260,1262,1264,1266,1268,1270,1272,1274,1276,1278,1280,1282,1284,1286,1288,1290,1292,1294,1296,1298,1300,1302,1304,1306,1308,1310,1312,1314,1316,1318,1320,1322,1324,1326,1328,1330,1332,1334,1336,1338,1340,1342,1344,1346,1348,1350,1352,1354,1356,1358,1360,1362,1364,1366,1368,1370,1372,1374,1376,1378,1380,1382,1384,1386,1388,1390,1392,1394,1396,1398,1400,1402,1404,1406,1408,1410,1412,1414,1416,1418,1420,1422,1424,1426,1428,1430,1432,1434,1436,1438,1440,1442,1444,1446,1448,1450,1452,1454,1456,1458,1460,1462,1464,1466,1468,1470,1472,1474,1476,1478,1480,1482,1484,1486,1488,1490,1492,1494,1496,1498,1500,1502,1504,1506,1508,1510,1512,1514,1516,1518,1520,1522,1524,1526,1528,1530,1532,1534,1536,1538,1540,1542,1544,1546,1548,1550,1552,1554,1556,1558,1560,1562,1564,1566,1568,1570,1572,1574,1576,1578,1580,1582,1584,1586,1588,1590,1592,1594,1596,1598,1600,1602,1604,1606,1608,1610,1612,1614,1616,1618,1620,1622,1624,1626,1628,1630,1632,1634,1636,1638,1640,1642,1644,1646,1648,1650,1652,1654,1656,1658,1660,1662,1664,1666,1668,1670,1672,1674,1676,1678,1680,1682,1684,1686,1688,1690,1692,1694,1696,1698,1700,1702,1704,1706,1708,1710,1712,1714,1716,1718,1720,1722,1724,1726,1728,1730,1732,1734,1736,1738,1740,1742,1744,1746,1748,1750,1752,1754,1756,1758,1760,1762,1764,1766,1768,1770,1772,1774,1776,1778,1780,1782,1784,1786,1788,1790,1792,1794,1796,1798,1800,1802,1804,1806,1808,1810,1812,1814,1816,1818,1820,1822,1824,1826,1828,1830,1832,1834,1836,1838,1840,1842,1844,1846,1848,1850,1852,1854,1856,1858,1860,1862,1864,1866,1868,1870,1872,1874,1876,1878,1880,1882,1884,1886,1888,1890,1892,1894,1896,1898,1900,1902,1904,1906,1908,1910,1912,1914,1916,1918,1920,1922,1924,1926,1928,1930,1932,1934,1936,1938,1940,1942,1944,1946,1948,1950,1952,1954,1956,1958,1960,1962,1964,1966,1968,1970,1972,1974,1976,1978,1980,1982,1984,1986,1988,1990,1992,1994,1996,1998,2000,2002,2004,2006,2008,2010,2012,2014,2016,2018,2020,2022,2024,2026,2028,2030,2032,2034,2036,2038,2040,2042,2044,2046,2048,2050,2052,2054,2056,2058,2060,2062,2064,2066,2068,2070,2072,2074,2076,2078,2080,2082,2084,2086,2088,2090,2092,2094,2096,2098,2100,2102,2104,2106,2108,2110,2112,2114,2116,2118,2120,2122,2124,2126,2128,2130,2132,2134,2136,2138,2140,2142,2144,2146,2148,2150,2152,2154,2156,2158,2160,2162,2164,2166,2168,2170,2172,2174,2176,2178,2180,2182,2184,2186,2188,2190,2192,2194,2196,2198,2200,2202,2204,2206,2208,2210,2212,2214,2216,2218,2220,2222,2224,2226,2228,2230,2232,2234,2236,2238,2240,2242,2244,2246,2248,2250,2252,2254,2256,2258,2260,2262,2264,2266,2268,2270,2272,2274,2276,2278,2280,2282,2284,2286,2288,2290,2292,2294,2296,2298,2300,2302,2304,2306,2308,2310,2312,2314,2316,2318,2320,2322,2324,2326,2328,2330,2332,2334,2336,2338,2340,2342,2344,2346,2348,2350,2352,2354,2356,2358,2360,2362,2364,2366,2368,2370,2372,2374,2376,2378,2380,2382,2384,2386,2388,2390,2392,2394,2396,2398,2400,2402,2404,2406,2408,2410,2412,2414,2416,2418,2420,2422,2424,2426,2428,2430,2432,2434,2436,2438,2440,2442,2444,2446,2448,2450,2452,2454,2456,2458,2460,2462,2464,2466,2468,2470,2472,2474,2476,2478,2480,2482,2484,2486,2488,2490,2492,2494,2496,2498,2500,2502,2504,2506,2508,2510,2512,2514,2516,2518,2520,2522,2524,2526,2528,2530,2532,2534,2536,2538,2540,2542,2544,2546,2548,2550,2552,2554,2556,2558,2560,2562,2564,2566,2568,2570,2572,2574,2576,2578,2580,2582,2584,2586,2588,2590,2592,2594,2596,2598,2600,2602,2604,2606,2608,2610,2612,2614,2616,2618,2620,2622,2624,2626,2628,2630,2632,2634,2636,2638,2640,2642,2644,2646,2648,2650,2652,2654,2656,2658,2660,2662,2664,2666,2668,2670,2672,2674,2676,2678,2680,2682,2684,2686,2688,2690,2692,2694,2696,2698,2700,2702,2704,2706,2708,2710,2712,2714,2716,2718,2720,2722,2724,2726,2728,2730,2732,2734,2736,2738,2740,2742,2744,2746,2748,2750,2752,2754,2756,2758,2760,2762,2764,2766,2768,2770,2772,2774,2776,2778,2780,2782,2784,2786,2788,2790,2792,2794,2796,2798,2800,2802,2804,2806,2808,2810,2812,2814,2816,2818,2820,2822,2824,2826,2828,2830,2832,2834,2836,2838,2840,2842,2844,2846,2848,2850,2852,2854,2856,2858,2860,2862,2864,2866,2868,2870,2872,2874,2876,2878,2880,2882,2884,2886,2888,2890,2892,2894,2896,2898,2900,2902,2904,2906,2908,2910,2912,2914,2916,2918,2920,2922,2924,2926,2928,2930,2932,2934,2936,2938,2940,2942,2944,2946,2948,2950,2952,2954,2956,2958,2960,2962,2964,2966,2968,2970,2972,2974,2976,2978,2980,2982,2984,2986,2988,2990,2992,2994,2996,2998,3000,3002,3004,3006,3008,3010,3012,3014,3016,3018,3020,3022,3024,3026,3028,3030,3032,3034,3036,3038,3040,3042,3044,3046,3048,3050,3052,3054,3056,3058,3060,3062,3064,3066,3068,3070,3072,3074,3076,3078,3080,3082,3084,3086,3088,3090,3092,3094,3096,3098,3100,3102,3104,3106,3108,3110,3112,3114,3116,3118,3120,3122,3124,3126,3128,3130,3132,3134,3136,3138,3140,3142,3144,3146,3148,3150,3152,3154,3156,3158,3160,3162,3164,3166,3168,3170,3172,3174,3176,3178,3180,3182,3184,3186,3188,3190,3192,3194,3196,3198,3200,3202,3204,3206,3208,3210,3212,3214,3216,3218,3220,3222,3224,3226,3228,3230,3232,3234,3236,3238,3240,3242,3244,3246,3248,3250,3252,3254,3256,3258,3260,3262,3264,3266,3268,3270,3272,3274,3276,3278,3280,3282,3284,3286,3288,3290,3292,3294,3296,3298,3300,3302,3304,3306,3308,3310,3312,3314,3316,3318,3320,3322,3324,3326,3328,3330,3332,3334,3336,3338,3340,3342,3344,3346,3348,3350,3352,3354,3356,3358,3360,3362,3364,3366,3368,3370,3372,3374,3376,3378,3380,3382,3384,3386,3388,3390,3392,3394,3396,3398,3400,3402,3404,3406,3408,3410,3412,3414,3416,3418,3420,3422,3424,3426,3428,3430,3432,3434,3436,3438,3440,3442,3444,3446,3448,3450,3452,3454,3456,3458,3460,3462,3464,3466,3468,3470,3472,3474,3476,3478,3480,3482,3484,3486,3488,3490,3492,3494,3496,3498,3500,3502,3504,3506,3508,3510,3512,3514,3516,3518,3520,3522,3524,3526,3528,3530,3532,3534,3536,3538,3540,3542,3544,3546,3548,3550,3552,3554,3556,3558,3560,3562,3564,3566,3568,3570,3572,3574,3576,3578,3580,3582,3584,3586,3588,3590,3592,3594,3596,3598,3600,3602,3604,3606,3608,3610,3612,3614,3616,3618,3620,3622,3624,3626,3628,3630,3632,3634,3636,3638,3640,3642,3644,3646,3648,3650,3652,3654,3656,3658,3660,3662,3664,3666,3668,3670,3672,3674,3676,3678,3680,3682,3684,3686,3688,3690,3692,3694,3696,3698,3700,3702,3704,3706,3708,3710,3712,3714,3716,3718,3720,3722,3724,3726,3728,3730,3732,3734,3736,3738,3740,3742,3744,3746,3748,3750,3752,3754,3756,3758,3760,3762,3764,3766,3768,3770,3772,3774,3776,3778,3780,3782],{"categories":217},[218],"Developer Productivity",{"categories":220},[221],"Business & SaaS",{"categories":223},[163],{"categories":225},[226],"AI Automation",{"categories":228},[229],"Product Strategy",{"categories":231},[163],{"categories":233},[218],{"categories":235},[221],{"categories":237},[],{"categories":239},[163],{"categories":241},[],{"categories":243},[244],"AI News & Trends",{"categories":246},[226],{"categories":248},[244],{"categories":250},[226],{"categories":252},[226],{"categories":254},[163],{"categories":256},[163],{"categories":258},[244],{"categories":260},[163],{"categories":262},[],{"categories":264},[265],"Design & Frontend",{"categories":267},[268],"Data Science & Visualization",{"categories":270},[244],{"categories":272},[],{"categories":274},[275],"Software Engineering",{"categories":277},[163],{"categories":279},[226],{"categories":281},[282],"Marketing & Growth",{"categories":284},[163],{"categories":286},[226],{"categories":288},[],{"categories":290},[],{"categories":292},[265],{"categories":294},[226],{"categories":296},[218],{"categories":298},[265],{"categories":300},[163],{"categories":302},[226],{"categories":304},[244],{"categories":306},[],{"categories":308},[],{"categories":310},[226],{"categories":312},[275],{"categories":314},[],{"categories":316},[221],{"categories":318},[],{"categories":320},[],{"categories":322},[226],{"categories":324},[226],{"categories":326},[163],{"categories":328},[],{"categories":330},[275],{"categories":332},[],{"categories":334},[],{"categories":336},[],{"categories":338},[163],{"categories":340},[282],{"categories":342},[265],{"categories":344},[265],{"categories":346},[163],{"categories":348},[226],{"categories":350},[163],{"categories":352},[163],{"categories":354},[226],{"categories":356},[226],{"categories":358},[268],{"categories":360},[244],{"categories":362},[226],{"categories":364},[282],{"categories":366},[226],{"categories":368},[229],{"categories":370},[],{"categories":372},[226],{"categories":374},[],{"categories":376},[226],{"categories":378},[275],{"categories":380},[265],{"categories":382},[163],{"categories":384},[],{"categories":386},[],{"categories":388},[226],{"categories":390},[],{"categories":392},[163],{"categories":394},[],{"categories":396},[218],{"categories":398},[275],{"categories":400},[221],{"categories":402},[244],{"categories":404},[163],{"categories":406},[],{"categories":408},[163],{"categories":410},[],{"categories":412},[275],{"categories":414},[268],{"categories":416},[],{"categories":418},[163],{"categories":420},[265],{"categories":422},[],{"categories":424},[265],{"categories":426},[226],{"categories":428},[],{"categories":430},[226],{"categories":432},[244],{"categories":434},[163],{"categories":436},[],{"categories":438},[226],{"categories":440},[163],{"categories":442},[229],{"categories":444},[],{"categories":446},[163],{"categories":448},[226],{"categories":450},[226],{"categories":452},[],{"categories":454},[268],{"categories":456},[163],{"categories":458},[],{"categories":460},[218],{"categories":462},[221],{"categories":464},[163],{"categories":466},[226],{"categories":468},[275],{"categories":470},[163],{"categories":472},[],{"categories":474},[],{"categories":476},[163],{"categories":478},[],{"categories":480},[265],{"categories":482},[],{"categories":484},[163],{"categories":486},[],{"categories":488},[226],{"categories":490},[163],{"categories":492},[265],{"categories":494},[],{"categories":496},[163],{"categories":498},[163],{"categories":500},[221],{"categories":502},[226],{"categories":504},[163],{"categories":506},[265],{"categories":508},[226],{"categories":510},[],{"categories":512},[],{"categories":514},[244],{"categories":516},[],{"categories":518},[163],{"categories":520},[221,282],{"categories":522},[],{"categories":524},[163],{"categories":526},[],{"categories":528},[],{"categories":530},[163],{"categories":532},[],{"categories":534},[163],{"categories":536},[537],"DevOps & Cloud",{"categories":539},[],{"categories":541},[244],{"categories":543},[265],{"categories":545},[],{"categories":547},[244],{"categories":549},[244],{"categories":551},[163],{"categories":553},[282],{"categories":555},[],{"categories":557},[221],{"categories":559},[],{"categories":561},[163,537],{"categories":563},[163],{"categories":565},[163],{"categories":567},[226],{"categories":569},[163,275],{"categories":571},[268],{"categories":573},[163],{"categories":575},[282],{"categories":577},[226],{"categories":579},[226],{"categories":581},[],{"categories":583},[226],{"categories":585},[163,221],{"categories":587},[],{"categories":589},[265],{"categories":591},[265],{"categories":593},[],{"categories":595},[],{"categories":597},[244],{"categories":599},[],{"categories":601},[218],{"categories":603},[275],{"categories":605},[163],{"categories":607},[265],{"categories":609},[226],{"categories":611},[275],{"categories":613},[244],{"categories":615},[265],{"categories":617},[],{"categories":619},[163],{"categories":621},[163],{"categories":623},[163],{"categories":625},[244],{"categories":627},[218],{"categories":629},[163],{"categories":631},[226],{"categories":633},[537],{"categories":635},[265],{"categories":637},[226],{"categories":639},[],{"categories":641},[],{"categories":643},[265],{"categories":645},[244],{"categories":647},[268],{"categories":649},[],{"categories":651},[163],{"categories":653},[163],{"categories":655},[221],{"categories":657},[163],{"categories":659},[163],{"categories":661},[244],{"categories":663},[],{"categories":665},[226],{"categories":667},[275],{"categories":669},[],{"categories":671},[163],{"categories":673},[163],{"categories":675},[226],{"categories":677},[],{"categories":679},[],{"categories":681},[163],{"categories":683},[],{"categories":685},[221],{"categories":687},[226],{"categories":689},[],{"categories":691},[218],{"categories":693},[163],{"categories":695},[221],{"categories":697},[244],{"categories":699},[],{"categories":701},[],{"categories":703},[],{"categories":705},[244],{"categories":707},[244],{"categories":709},[],{"categories":711},[],{"categories":713},[221],{"categories":715},[],{"categories":717},[],{"categories":719},[218],{"categories":721},[],{"categories":723},[282],{"categories":725},[226],{"categories":727},[221],{"categories":729},[226],{"categories":731},[],{"categories":733},[229],{"categories":735},[265],{"categories":737},[275],{"categories":739},[163],{"categories":741},[226],{"categories":743},[221],{"categories":745},[163],{"categories":747},[],{"categories":749},[],{"categories":751},[275],{"categories":753},[268],{"categories":755},[229],{"categories":757},[226],{"categories":759},[163],{"categories":761},[],{"categories":763},[537],{"categories":765},[],{"categories":767},[226],{"categories":769},[],{"categories":771},[],{"categories":773},[163],{"categories":775},[265],{"categories":777},[282],{"categories":779},[226],{"categories":781},[],{"categories":783},[218],{"categories":785},[],{"categories":787},[244],{"categories":789},[163,537],{"categories":791},[244],{"categories":793},[163],{"categories":795},[221],{"categories":797},[163],{"categories":799},[],{"categories":801},[221],{"categories":803},[],{"categories":805},[275],{"categories":807},[265],{"categories":809},[244],{"categories":811},[268],{"categories":813},[218],{"categories":815},[163],{"categories":817},[275],{"categories":819},[],{"categories":821},[],{"categories":823},[229],{"categories":825},[],{"categories":827},[163],{"categories":829},[],{"categories":831},[265],{"categories":833},[265],{"categories":835},[265],{"categories":837},[],{"categories":839},[],{"categories":841},[244],{"categories":843},[226],{"categories":845},[163],{"categories":847},[163],{"categories":849},[163],{"categories":851},[221],{"categories":853},[163],{"categories":855},[],{"categories":857},[275],{"categories":859},[275],{"categories":861},[221],{"categories":863},[],{"categories":865},[163],{"categories":867},[163],{"categories":869},[221],{"categories":871},[244],{"categories":873},[282],{"categories":875},[226],{"categories":877},[],{"categories":879},[265],{"categories":881},[],{"categories":883},[163],{"categories":885},[],{"categories":887},[221],{"categories":889},[226],{"categories":891},[],{"categories":893},[537],{"categories":895},[268],{"categories":897},[275],{"categories":899},[282],{"categories":901},[275],{"categories":903},[226],{"categories":905},[],{"categories":907},[],{"categories":909},[226],{"categories":911},[218],{"categories":913},[226],{"categories":915},[229],{"categories":917},[221],{"categories":919},[],{"categories":921},[163],{"categories":923},[229],{"categories":925},[163],{"categories":927},[163],{"categories":929},[282],{"categories":931},[265],{"categories":933},[226],{"categories":935},[],{"categories":937},[],{"categories":939},[537],{"categories":941},[275],{"categories":943},[],{"categories":945},[226],{"categories":947},[163],{"categories":949},[265,163],{"categories":951},[218],{"categories":953},[],{"categories":955},[163],{"categories":957},[218],{"categories":959},[265],{"categories":961},[226],{"categories":963},[275],{"categories":965},[],{"categories":967},[163],{"categories":969},[],{"categories":971},[218],{"categories":973},[],{"categories":975},[226],{"categories":977},[229],{"categories":979},[163],{"categories":981},[163],{"categories":983},[265],{"categories":985},[226],{"categories":987},[537],{"categories":989},[265],{"categories":991},[226],{"categories":993},[163],{"categories":995},[163],{"categories":997},[163],{"categories":999},[244],{"categories":1001},[],{"categories":1003},[229],{"categories":1005},[226],{"categories":1007},[265],{"categories":1009},[226],{"categories":1011},[275],{"categories":1013},[265],{"categories":1015},[226],{"categories":1017},[244],{"categories":1019},[],{"categories":1021},[163],{"categories":1023},[265],{"categories":1025},[163],{"categories":1027},[218],{"categories":1029},[244],{"categories":1031},[163],{"categories":1033},[282],{"categories":1035},[163],{"categories":1037},[163],{"categories":1039},[226],{"categories":1041},[226],{"categories":1043},[163],{"categories":1045},[226],{"categories":1047},[265],{"categories":1049},[163],{"categories":1051},[],{"categories":1053},[],{"categories":1055},[275],{"categories":1057},[],{"categories":1059},[218],{"categories":1061},[537],{"categories":1063},[],{"categories":1065},[218],{"categories":1067},[221],{"categories":1069},[282],{"categories":1071},[],{"categories":1073},[221],{"categories":1075},[],{"categories":1077},[],{"categories":1079},[],{"categories":1081},[],{"categories":1083},[],{"categories":1085},[163],{"categories":1087},[226],{"categories":1089},[537],{"categories":1091},[218],{"categories":1093},[163],{"categories":1095},[275],{"categories":1097},[229],{"categories":1099},[163],{"categories":1101},[282],{"categories":1103},[163],{"categories":1105},[163],{"categories":1107},[163],{"categories":1109},[163,218],{"categories":1111},[275],{"categories":1113},[275],{"categories":1115},[265],{"categories":1117},[163],{"categories":1119},[],{"categories":1121},[],{"categories":1123},[],{"categories":1125},[275],{"categories":1127},[268],{"categories":1129},[244],{"categories":1131},[265],{"categories":1133},[],{"categories":1135},[163],{"categories":1137},[163],{"categories":1139},[],{"categories":1141},[],{"categories":1143},[226],{"categories":1145},[163],{"categories":1147},[221],{"categories":1149},[],{"categories":1151},[218],{"categories":1153},[163],{"categories":1155},[218],{"categories":1157},[163],{"categories":1159},[275],{"categories":1161},[282],{"categories":1163},[163,265],{"categories":1165},[244],{"categories":1167},[265],{"categories":1169},[],{"categories":1171},[537],{"categories":1173},[265],{"categories":1175},[226],{"categories":1177},[],{"categories":1179},[],{"categories":1181},[],{"categories":1183},[],{"categories":1185},[275],{"categories":1187},[226],{"categories":1189},[226],{"categories":1191},[163],{"categories":1193},[163],{"categories":1195},[],{"categories":1197},[265],{"categories":1199},[],{"categories":1201},[],{"categories":1203},[226],{"categories":1205},[],{"categories":1207},[],{"categories":1209},[282],{"categories":1211},[282],{"categories":1213},[226],{"categories":1215},[],{"categories":1217},[163],{"categories":1219},[163],{"categories":1221},[275],{"categories":1223},[265],{"categories":1225},[265],{"categories":1227},[226],{"categories":1229},[218],{"categories":1231},[163],{"categories":1233},[265],{"categories":1235},[265],{"categories":1237},[226],{"categories":1239},[226],{"categories":1241},[163],{"categories":1243},[],{"categories":1245},[],{"categories":1247},[163],{"categories":1249},[226],{"categories":1251},[244],{"categories":1253},[275],{"categories":1255},[218],{"categories":1257},[163],{"categories":1259},[],{"categories":1261},[226],{"categories":1263},[226],{"categories":1265},[],{"categories":1267},[218],{"categories":1269},[163],{"categories":1271},[218],{"categories":1273},[218],{"categories":1275},[],{"categories":1277},[],{"categories":1279},[226],{"categories":1281},[226],{"categories":1283},[163],{"categories":1285},[163],{"categories":1287},[244],{"categories":1289},[268],{"categories":1291},[229],{"categories":1293},[244],{"categories":1295},[265],{"categories":1297},[],{"categories":1299},[244],{"categories":1301},[],{"categories":1303},[],{"categories":1305},[],{"categories":1307},[],{"categories":1309},[275],{"categories":1311},[268],{"categories":1313},[],{"categories":1315},[163],{"categories":1317},[163],{"categories":1319},[268],{"categories":1321},[275],{"categories":1323},[],{"categories":1325},[],{"categories":1327},[226],{"categories":1329},[244],{"categories":1331},[244],{"categories":1333},[226],{"categories":1335},[218],{"categories":1337},[163,537],{"categories":1339},[],{"categories":1341},[265],{"categories":1343},[218],{"categories":1345},[226],{"categories":1347},[265],{"categories":1349},[],{"categories":1351},[226],{"categories":1353},[226],{"categories":1355},[163],{"categories":1357},[282],{"categories":1359},[275],{"categories":1361},[265],{"categories":1363},[],{"categories":1365},[226],{"categories":1367},[163],{"categories":1369},[226],{"categories":1371},[226],{"categories":1373},[226],{"categories":1375},[282],{"categories":1377},[226],{"categories":1379},[163],{"categories":1381},[],{"categories":1383},[282],{"categories":1385},[244],{"categories":1387},[226],{"categories":1389},[],{"categories":1391},[],{"categories":1393},[163],{"categories":1395},[226],{"categories":1397},[244],{"categories":1399},[226],{"categories":1401},[],{"categories":1403},[],{"categories":1405},[],{"categories":1407},[226],{"categories":1409},[],{"categories":1411},[],{"categories":1413},[268],{"categories":1415},[163],{"categories":1417},[268],{"categories":1419},[244],{"categories":1421},[163],{"categories":1423},[163],{"categories":1425},[226],{"categories":1427},[163],{"categories":1429},[],{"categories":1431},[],{"categories":1433},[537],{"categories":1435},[],{"categories":1437},[],{"categories":1439},[218],{"categories":1441},[],{"categories":1443},[],{"categories":1445},[],{"categories":1447},[],{"categories":1449},[275],{"categories":1451},[244],{"categories":1453},[282],{"categories":1455},[221],{"categories":1457},[163],{"categories":1459},[163],{"categories":1461},[221],{"categories":1463},[],{"categories":1465},[265],{"categories":1467},[226],{"categories":1469},[221],{"categories":1471},[163],{"categories":1473},[163],{"categories":1475},[218],{"categories":1477},[],{"categories":1479},[218],{"categories":1481},[163],{"categories":1483},[282],{"categories":1485},[226],{"categories":1487},[244],{"categories":1489},[221],{"categories":1491},[163],{"categories":1493},[226],{"categories":1495},[],{"categories":1497},[163],{"categories":1499},[218],{"categories":1501},[163],{"categories":1503},[],{"categories":1505},[244],{"categories":1507},[163],{"categories":1509},[],{"categories":1511},[221],{"categories":1513},[163],{"categories":1515},[],{"categories":1517},[],{"categories":1519},[],{"categories":1521},[163],{"categories":1523},[],{"categories":1525},[537],{"categories":1527},[163],{"categories":1529},[],{"categories":1531},[163],{"categories":1533},[163],{"categories":1535},[163],{"categories":1537},[163,537],{"categories":1539},[163],{"categories":1541},[163],{"categories":1543},[265],{"categories":1545},[226],{"categories":1547},[],{"categories":1549},[226],{"categories":1551},[163],{"categories":1553},[163],{"categories":1555},[163],{"categories":1557},[218],{"categories":1559},[218],{"categories":1561},[275],{"categories":1563},[265],{"categories":1565},[226],{"categories":1567},[],{"categories":1569},[163],{"categories":1571},[244],{"categories":1573},[163],{"categories":1575},[221],{"categories":1577},[],{"categories":1579},[537],{"categories":1581},[265],{"categories":1583},[265],{"categories":1585},[226],{"categories":1587},[244],{"categories":1589},[226],{"categories":1591},[163],{"categories":1593},[],{"categories":1595},[163],{"categories":1597},[],{"categories":1599},[],{"categories":1601},[163],{"categories":1603},[163],{"categories":1605},[163],{"categories":1607},[226],{"categories":1609},[163],{"categories":1611},[],{"categories":1613},[268],{"categories":1615},[226],{"categories":1617},[],{"categories":1619},[163],{"categories":1621},[244],{"categories":1623},[],{"categories":1625},[265],{"categories":1627},[537],{"categories":1629},[244],{"categories":1631},[275],{"categories":1633},[275],{"categories":1635},[244],{"categories":1637},[244],{"categories":1639},[537],{"categories":1641},[],{"categories":1643},[244],{"categories":1645},[163],{"categories":1647},[218],{"categories":1649},[244],{"categories":1651},[],{"categories":1653},[268],{"categories":1655},[244],{"categories":1657},[275],{"categories":1659},[244],{"categories":1661},[537],{"categories":1663},[163],{"categories":1665},[163],{"categories":1667},[],{"categories":1669},[221],{"categories":1671},[],{"categories":1673},[],{"categories":1675},[163],{"categories":1677},[163],{"categories":1679},[163],{"categories":1681},[163],{"categories":1683},[],{"categories":1685},[268],{"categories":1687},[218],{"categories":1689},[],{"categories":1691},[163],{"categories":1693},[163],{"categories":1695},[537],{"categories":1697},[537],{"categories":1699},[],{"categories":1701},[226],{"categories":1703},[244],{"categories":1705},[244],{"categories":1707},[163],{"categories":1709},[226],{"categories":1711},[],{"categories":1713},[265],{"categories":1715},[163],{"categories":1717},[163],{"categories":1719},[],{"categories":1721},[],{"categories":1723},[537],{"categories":1725},[163],{"categories":1727},[275],{"categories":1729},[221],{"categories":1731},[163],{"categories":1733},[],{"categories":1735},[226],{"categories":1737},[218],{"categories":1739},[218],{"categories":1741},[],{"categories":1743},[163],{"categories":1745},[265],{"categories":1747},[226],{"categories":1749},[],{"categories":1751},[163],{"categories":1753},[163],{"categories":1755},[226],{"categories":1757},[],{"categories":1759},[226],{"categories":1761},[275],{"categories":1763},[],{"categories":1765},[163],{"categories":1767},[],{"categories":1769},[163],{"categories":1771},[],{"categories":1773},[163],{"categories":1775},[163],{"categories":1777},[],{"categories":1779},[163],{"categories":1781},[244],{"categories":1783},[163],{"categories":1785},[163],{"categories":1787},[218],{"categories":1789},[163],{"categories":1791},[244],{"categories":1793},[226],{"categories":1795},[],{"categories":1797},[163],{"categories":1799},[282],{"categories":1801},[],{"categories":1803},[],{"categories":1805},[],{"categories":1807},[218],{"categories":1809},[244],{"categories":1811},[226],{"categories":1813},[163],{"categories":1815},[265],{"categories":1817},[226],{"categories":1819},[],{"categories":1821},[226],{"categories":1823},[],{"categories":1825},[163],{"categories":1827},[226],{"categories":1829},[163],{"categories":1831},[],{"categories":1833},[163],{"categories":1835},[163],{"categories":1837},[244],{"categories":1839},[265],{"categories":1841},[226],{"categories":1843},[265],{"categories":1845},[221],{"categories":1847},[],{"categories":1849},[],{"categories":1851},[163],{"categories":1853},[218],{"categories":1855},[244],{"categories":1857},[],{"categories":1859},[],{"categories":1861},[275],{"categories":1863},[265],{"categories":1865},[],{"categories":1867},[163],{"categories":1869},[],{"categories":1871},[282],{"categories":1873},[163],{"categories":1875},[537],{"categories":1877},[275],{"categories":1879},[],{"categories":1881},[226],{"categories":1883},[163],{"categories":1885},[226],{"categories":1887},[226],{"categories":1889},[163],{"categories":1891},[],{"categories":1893},[218],{"categories":1895},[163],{"categories":1897},[221],{"categories":1899},[275],{"categories":1901},[265],{"categories":1903},[],{"categories":1905},[],{"categories":1907},[],{"categories":1909},[226],{"categories":1911},[265],{"categories":1913},[244],{"categories":1915},[163],{"categories":1917},[244],{"categories":1919},[265],{"categories":1921},[],{"categories":1923},[265],{"categories":1925},[244],{"categories":1927},[221],{"categories":1929},[163],{"categories":1931},[244],{"categories":1933},[282],{"categories":1935},[],{"categories":1937},[],{"categories":1939},[268],{"categories":1941},[163,275],{"categories":1943},[244],{"categories":1945},[163],{"categories":1947},[226],{"categories":1949},[226],{"categories":1951},[163],{"categories":1953},[],{"categories":1955},[275],{"categories":1957},[163],{"categories":1959},[268],{"categories":1961},[226],{"categories":1963},[282],{"categories":1965},[537],{"categories":1967},[],{"categories":1969},[218],{"categories":1971},[226],{"categories":1973},[226],{"categories":1975},[275],{"categories":1977},[163],{"categories":1979},[163],{"categories":1981},[],{"categories":1983},[],{"categories":1985},[],{"categories":1987},[537],{"categories":1989},[244],{"categories":1991},[163],{"categories":1993},[163],{"categories":1995},[163],{"categories":1997},[],{"categories":1999},[268],{"categories":2001},[221],{"categories":2003},[],{"categories":2005},[226],{"categories":2007},[537],{"categories":2009},[],{"categories":2011},[265],{"categories":2013},[265],{"categories":2015},[],{"categories":2017},[275],{"categories":2019},[265],{"categories":2021},[163],{"categories":2023},[],{"categories":2025},[244],{"categories":2027},[163],{"categories":2029},[265],{"categories":2031},[226],{"categories":2033},[244],{"categories":2035},[],{"categories":2037},[226],{"categories":2039},[265],{"categories":2041},[163],{"categories":2043},[],{"categories":2045},[163],{"categories":2047},[163],{"categories":2049},[537],{"categories":2051},[244],{"categories":2053},[268],{"categories":2055},[268],{"categories":2057},[],{"categories":2059},[],{"categories":2061},[],{"categories":2063},[226],{"categories":2065},[275],{"categories":2067},[275],{"categories":2069},[],{"categories":2071},[],{"categories":2073},[163],{"categories":2075},[],{"categories":2077},[226],{"categories":2079},[163],{"categories":2081},[],{"categories":2083},[163],{"categories":2085},[221],{"categories":2087},[163],{"categories":2089},[282],{"categories":2091},[226],{"categories":2093},[163],{"categories":2095},[275],{"categories":2097},[244],{"categories":2099},[226],{"categories":2101},[],{"categories":2103},[244],{"categories":2105},[226],{"categories":2107},[226],{"categories":2109},[],{"categories":2111},[221],{"categories":2113},[226],{"categories":2115},[],{"categories":2117},[163],{"categories":2119},[218],{"categories":2121},[244],{"categories":2123},[537],{"categories":2125},[226],{"categories":2127},[226],{"categories":2129},[218],{"categories":2131},[163],{"categories":2133},[],{"categories":2135},[],{"categories":2137},[265],{"categories":2139},[163,221],{"categories":2141},[],{"categories":2143},[218],{"categories":2145},[268],{"categories":2147},[163],{"categories":2149},[275],{"categories":2151},[163],{"categories":2153},[226],{"categories":2155},[163],{"categories":2157},[163],{"categories":2159},[244],{"categories":2161},[226],{"categories":2163},[],{"categories":2165},[],{"categories":2167},[226],{"categories":2169},[163],{"categories":2171},[537],{"categories":2173},[],{"categories":2175},[163],{"categories":2177},[226],{"categories":2179},[],{"categories":2181},[163],{"categories":2183},[282],{"categories":2185},[268],{"categories":2187},[226],{"categories":2189},[163],{"categories":2191},[537],{"categories":2193},[],{"categories":2195},[163],{"categories":2197},[282],{"categories":2199},[265],{"categories":2201},[163],{"categories":2203},[],{"categories":2205},[282],{"categories":2207},[244],{"categories":2209},[163],{"categories":2211},[163],{"categories":2213},[218],{"categories":2215},[],{"categories":2217},[],{"categories":2219},[265],{"categories":2221},[163],{"categories":2223},[268],{"categories":2225},[282],{"categories":2227},[282],{"categories":2229},[244],{"categories":2231},[],{"categories":2233},[],{"categories":2235},[163],{"categories":2237},[],{"categories":2239},[163,275],{"categories":2241},[244],{"categories":2243},[226],{"categories":2245},[275],{"categories":2247},[163],{"categories":2249},[218],{"categories":2251},[],{"categories":2253},[],{"categories":2255},[218],{"categories":2257},[282],{"categories":2259},[163],{"categories":2261},[],{"categories":2263},[265,163],{"categories":2265},[537],{"categories":2267},[218],{"categories":2269},[],{"categories":2271},[221],{"categories":2273},[221],{"categories":2275},[163],{"categories":2277},[275],{"categories":2279},[226],{"categories":2281},[244],{"categories":2283},[282],{"categories":2285},[265],{"categories":2287},[163],{"categories":2289},[163],{"categories":2291},[163],{"categories":2293},[218],{"categories":2295},[163],{"categories":2297},[226],{"categories":2299},[244],{"categories":2301},[],{"categories":2303},[],{"categories":2305},[268],{"categories":2307},[275],{"categories":2309},[163],{"categories":2311},[265],{"categories":2313},[268],{"categories":2315},[163],{"categories":2317},[163],{"categories":2319},[226],{"categories":2321},[226],{"categories":2323},[163,221],{"categories":2325},[],{"categories":2327},[265],{"categories":2329},[],{"categories":2331},[163],{"categories":2333},[244],{"categories":2335},[218],{"categories":2337},[218],{"categories":2339},[226],{"categories":2341},[163],{"categories":2343},[221],{"categories":2345},[275],{"categories":2347},[282],{"categories":2349},[],{"categories":2351},[244],{"categories":2353},[163],{"categories":2355},[163],{"categories":2357},[244],{"categories":2359},[275],{"categories":2361},[163],{"categories":2363},[226],{"categories":2365},[244],{"categories":2367},[163],{"categories":2369},[265],{"categories":2371},[163],{"categories":2373},[163],{"categories":2375},[537],{"categories":2377},[229],{"categories":2379},[226],{"categories":2381},[163],{"categories":2383},[244],{"categories":2385},[226],{"categories":2387},[282],{"categories":2389},[163],{"categories":2391},[],{"categories":2393},[163],{"categories":2395},[],{"categories":2397},[],{"categories":2399},[],{"categories":2401},[221],{"categories":2403},[163],{"categories":2405},[226],{"categories":2407},[244],{"categories":2409},[244],{"categories":2411},[244],{"categories":2413},[244],{"categories":2415},[],{"categories":2417},[218],{"categories":2419},[226],{"categories":2421},[244],{"categories":2423},[218],{"categories":2425},[226],{"categories":2427},[163],{"categories":2429},[163,226],{"categories":2431},[226],{"categories":2433},[537],{"categories":2435},[244],{"categories":2437},[244],{"categories":2439},[226],{"categories":2441},[163],{"categories":2443},[],{"categories":2445},[244],{"categories":2447},[282],{"categories":2449},[218],{"categories":2451},[163],{"categories":2453},[163],{"categories":2455},[],{"categories":2457},[275],{"categories":2459},[],{"categories":2461},[218],{"categories":2463},[226],{"categories":2465},[244],{"categories":2467},[163],{"categories":2469},[244],{"categories":2471},[218],{"categories":2473},[244],{"categories":2475},[244],{"categories":2477},[],{"categories":2479},[221],{"categories":2481},[226],{"categories":2483},[244],{"categories":2485},[244],{"categories":2487},[244],{"categories":2489},[244],{"categories":2491},[244],{"categories":2493},[244],{"categories":2495},[244],{"categories":2497},[244],{"categories":2499},[244],{"categories":2501},[244],{"categories":2503},[268],{"categories":2505},[218],{"categories":2507},[163],{"categories":2509},[163],{"categories":2511},[],{"categories":2513},[163,218],{"categories":2515},[],{"categories":2517},[226],{"categories":2519},[244],{"categories":2521},[226],{"categories":2523},[163],{"categories":2525},[163],{"categories":2527},[163],{"categories":2529},[163],{"categories":2531},[163],{"categories":2533},[226],{"categories":2535},[221],{"categories":2537},[265],{"categories":2539},[244],{"categories":2541},[163],{"categories":2543},[],{"categories":2545},[],{"categories":2547},[226],{"categories":2549},[265],{"categories":2551},[163],{"categories":2553},[],{"categories":2555},[],{"categories":2557},[282],{"categories":2559},[163],{"categories":2561},[],{"categories":2563},[],{"categories":2565},[218],{"categories":2567},[221],{"categories":2569},[163],{"categories":2571},[221],{"categories":2573},[265],{"categories":2575},[],{"categories":2577},[244],{"categories":2579},[],{"categories":2581},[265],{"categories":2583},[163],{"categories":2585},[282],{"categories":2587},[],{"categories":2589},[282],{"categories":2591},[],{"categories":2593},[],{"categories":2595},[226],{"categories":2597},[],{"categories":2599},[221],{"categories":2601},[218],{"categories":2603},[265],{"categories":2605},[275],{"categories":2607},[],{"categories":2609},[],{"categories":2611},[163],{"categories":2613},[218],{"categories":2615},[282],{"categories":2617},[],{"categories":2619},[226],{"categories":2621},[226],{"categories":2623},[244],{"categories":2625},[163],{"categories":2627},[226],{"categories":2629},[163],{"categories":2631},[226],{"categories":2633},[163],{"categories":2635},[229],{"categories":2637},[244],{"categories":2639},[],{"categories":2641},[282],{"categories":2643},[275],{"categories":2645},[226],{"categories":2647},[],{"categories":2649},[163],{"categories":2651},[226],{"categories":2653},[221],{"categories":2655},[218],{"categories":2657},[163],{"categories":2659},[265],{"categories":2661},[275],{"categories":2663},[275],{"categories":2665},[163],{"categories":2667},[268],{"categories":2669},[163],{"categories":2671},[226],{"categories":2673},[221],{"categories":2675},[226],{"categories":2677},[163],{"categories":2679},[163],{"categories":2681},[226],{"categories":2683},[244],{"categories":2685},[],{"categories":2687},[218],{"categories":2689},[163],{"categories":2691},[226],{"categories":2693},[163],{"categories":2695},[163],{"categories":2697},[],{"categories":2699},[265],{"categories":2701},[221],{"categories":2703},[244],{"categories":2705},[163],{"categories":2707},[163],{"categories":2709},[265],{"categories":2711},[282],{"categories":2713},[268],{"categories":2715},[163],{"categories":2717},[244],{"categories":2719},[163],{"categories":2721},[226],{"categories":2723},[537],{"categories":2725},[163],{"categories":2727},[226],{"categories":2729},[268],{"categories":2731},[],{"categories":2733},[226],{"categories":2735},[275],{"categories":2737},[265],{"categories":2739},[163],{"categories":2741},[218],{"categories":2743},[221],{"categories":2745},[275],{"categories":2747},[],{"categories":2749},[226],{"categories":2751},[163],{"categories":2753},[],{"categories":2755},[244],{"categories":2757},[],{"categories":2759},[244],{"categories":2761},[163],{"categories":2763},[226],{"categories":2765},[226],{"categories":2767},[226],{"categories":2769},[],{"categories":2771},[],{"categories":2773},[163],{"categories":2775},[163],{"categories":2777},[],{"categories":2779},[265],{"categories":2781},[226],{"categories":2783},[282],{"categories":2785},[218],{"categories":2787},[],{"categories":2789},[],{"categories":2791},[244],{"categories":2793},[275],{"categories":2795},[163],{"categories":2797},[163],{"categories":2799},[163],{"categories":2801},[275],{"categories":2803},[244],{"categories":2805},[265],{"categories":2807},[163],{"categories":2809},[163],{"categories":2811},[163],{"categories":2813},[244],{"categories":2815},[163],{"categories":2817},[244],{"categories":2819},[226],{"categories":2821},[226],{"categories":2823},[275],{"categories":2825},[226],{"categories":2827},[163],{"categories":2829},[275],{"categories":2831},[265],{"categories":2833},[],{"categories":2835},[226],{"categories":2837},[],{"categories":2839},[],{"categories":2841},[221],{"categories":2843},[163],{"categories":2845},[226],{"categories":2847},[218],{"categories":2849},[226],{"categories":2851},[282],{"categories":2853},[],{"categories":2855},[226],{"categories":2857},[],{"categories":2859},[218],{"categories":2861},[226],{"categories":2863},[],{"categories":2865},[226],{"categories":2867},[163],{"categories":2869},[244],{"categories":2871},[163],{"categories":2873},[226],{"categories":2875},[244],{"categories":2877},[226],{"categories":2879},[275],{"categories":2881},[265],{"categories":2883},[218],{"categories":2885},[],{"categories":2887},[226],{"categories":2889},[265],{"categories":2891},[244],{"categories":2893},[163],{"categories":2895},[265],{"categories":2897},[218],{"categories":2899},[],{"categories":2901},[226],{"categories":2903},[226],{"categories":2905},[163],{"categories":2907},[],{"categories":2909},[226],{"categories":2911},[229],{"categories":2913},[244],{"categories":2915},[226],{"categories":2917},[221],{"categories":2919},[],{"categories":2921},[163],{"categories":2923},[229],{"categories":2925},[163],{"categories":2927},[226],{"categories":2929},[244],{"categories":2931},[218],{"categories":2933},[537],{"categories":2935},[163],{"categories":2937},[163],{"categories":2939},[163],{"categories":2941},[244],{"categories":2943},[221],{"categories":2945},[163],{"categories":2947},[265],{"categories":2949},[244],{"categories":2951},[537],{"categories":2953},[163],{"categories":2955},[],{"categories":2957},[],{"categories":2959},[537],{"categories":2961},[268],{"categories":2963},[226],{"categories":2965},[226],{"categories":2967},[244],{"categories":2969},[163],{"categories":2971},[218],{"categories":2973},[265],{"categories":2975},[226],{"categories":2977},[163],{"categories":2979},[282],{"categories":2981},[163],{"categories":2983},[226],{"categories":2985},[],{"categories":2987},[163],{"categories":2989},[163],{"categories":2991},[244],{"categories":2993},[218],{"categories":2995},[],{"categories":2997},[163],{"categories":2999},[163],{"categories":3001},[275],{"categories":3003},[265],{"categories":3005},[163,226],{"categories":3007},[282,221],{"categories":3009},[163],{"categories":3011},[],{"categories":3013},[226],{"categories":3015},[],{"categories":3017},[275],{"categories":3019},[163],{"categories":3021},[244],{"categories":3023},[],{"categories":3025},[226],{"categories":3027},[],{"categories":3029},[226],{"categories":3031},[218],{"categories":3033},[226],{"categories":3035},[163],{"categories":3037},[537],{"categories":3039},[282],{"categories":3041},[221],{"categories":3043},[221],{"categories":3045},[218],{"categories":3047},[218],{"categories":3049},[163],{"categories":3051},[226],{"categories":3053},[163],{"categories":3055},[163],{"categories":3057},[218],{"categories":3059},[163],{"categories":3061},[282],{"categories":3063},[244],{"categories":3065},[163],{"categories":3067},[226],{"categories":3069},[163],{"categories":3071},[],{"categories":3073},[275],{"categories":3075},[],{"categories":3077},[226],{"categories":3079},[218],{"categories":3081},[],{"categories":3083},[537],{"categories":3085},[163],{"categories":3087},[],{"categories":3089},[244],{"categories":3091},[226],{"categories":3093},[275],{"categories":3095},[163],{"categories":3097},[226],{"categories":3099},[275],{"categories":3101},[226],{"categories":3103},[244],{"categories":3105},[218],{"categories":3107},[244],{"categories":3109},[275],{"categories":3111},[163],{"categories":3113},[265],{"categories":3115},[163],{"categories":3117},[163],{"categories":3119},[163],{"categories":3121},[163],{"categories":3123},[226],{"categories":3125},[163],{"categories":3127},[226],{"categories":3129},[163],{"categories":3131},[218],{"categories":3133},[163],{"categories":3135},[226],{"categories":3137},[265],{"categories":3139},[218],{"categories":3141},[226],{"categories":3143},[265],{"categories":3145},[],{"categories":3147},[163],{"categories":3149},[163],{"categories":3151},[275],{"categories":3153},[],{"categories":3155},[226],{"categories":3157},[282],{"categories":3159},[163],{"categories":3161},[244],{"categories":3163},[282],{"categories":3165},[226],{"categories":3167},[221],{"categories":3169},[221],{"categories":3171},[163],{"categories":3173},[218],{"categories":3175},[],{"categories":3177},[163],{"categories":3179},[],{"categories":3181},[218],{"categories":3183},[163],{"categories":3185},[226],{"categories":3187},[226],{"categories":3189},[],{"categories":3191},[275],{"categories":3193},[275],{"categories":3195},[282],{"categories":3197},[265],{"categories":3199},[],{"categories":3201},[163],{"categories":3203},[218],{"categories":3205},[163],{"categories":3207},[275],{"categories":3209},[218],{"categories":3211},[244],{"categories":3213},[244],{"categories":3215},[],{"categories":3217},[244],{"categories":3219},[226],{"categories":3221},[265],{"categories":3223},[268],{"categories":3225},[163],{"categories":3227},[],{"categories":3229},[244],{"categories":3231},[275],{"categories":3233},[221],{"categories":3235},[163],{"categories":3237},[218],{"categories":3239},[537],{"categories":3241},[218],{"categories":3243},[],{"categories":3245},[],{"categories":3247},[244],{"categories":3249},[],{"categories":3251},[226],{"categories":3253},[226],{"categories":3255},[226],{"categories":3257},[],{"categories":3259},[163],{"categories":3261},[],{"categories":3263},[244],{"categories":3265},[218],{"categories":3267},[265],{"categories":3269},[163],{"categories":3271},[244],{"categories":3273},[244],{"categories":3275},[],{"categories":3277},[244],{"categories":3279},[218],{"categories":3281},[163],{"categories":3283},[],{"categories":3285},[226],{"categories":3287},[226],{"categories":3289},[218],{"categories":3291},[],{"categories":3293},[],{"categories":3295},[],{"categories":3297},[265],{"categories":3299},[226],{"categories":3301},[163],{"categories":3303},[],{"categories":3305},[],{"categories":3307},[],{"categories":3309},[265],{"categories":3311},[],{"categories":3313},[218],{"categories":3315},[],{"categories":3317},[],{"categories":3319},[265],{"categories":3321},[163],{"categories":3323},[244],{"categories":3325},[],{"categories":3327},[282],{"categories":3329},[244],{"categories":3331},[282],{"categories":3333},[163],{"categories":3335},[],{"categories":3337},[],{"categories":3339},[226],{"categories":3341},[],{"categories":3343},[],{"categories":3345},[226],{"categories":3347},[163],{"categories":3349},[],{"categories":3351},[226],{"categories":3353},[244],{"categories":3355},[282],{"categories":3357},[268],{"categories":3359},[226],{"categories":3361},[226],{"categories":3363},[],{"categories":3365},[],{"categories":3367},[],{"categories":3369},[244],{"categories":3371},[],{"categories":3373},[],{"categories":3375},[265],{"categories":3377},[218],{"categories":3379},[],{"categories":3381},[221],{"categories":3383},[282],{"categories":3385},[163],{"categories":3387},[275],{"categories":3389},[218],{"categories":3391},[268],{"categories":3393},[221],{"categories":3395},[275],{"categories":3397},[],{"categories":3399},[],{"categories":3401},[226],{"categories":3403},[218],{"categories":3405},[265],{"categories":3407},[218],{"categories":3409},[226],{"categories":3411},[537],{"categories":3413},[226],{"categories":3415},[],{"categories":3417},[163],{"categories":3419},[244],{"categories":3421},[275],{"categories":3423},[],{"categories":3425},[265],{"categories":3427},[244],{"categories":3429},[218],{"categories":3431},[226],{"categories":3433},[163],{"categories":3435},[221],{"categories":3437},[226,537],{"categories":3439},[226],{"categories":3441},[275],{"categories":3443},[163],{"categories":3445},[268],{"categories":3447},[282],{"categories":3449},[226],{"categories":3451},[],{"categories":3453},[226],{"categories":3455},[163],{"categories":3457},[221],{"categories":3459},[],{"categories":3461},[],{"categories":3463},[163],{"categories":3465},[268],{"categories":3467},[163],{"categories":3469},[],{"categories":3471},[244],{"categories":3473},[],{"categories":3475},[244],{"categories":3477},[275],{"categories":3479},[226],{"categories":3481},[163],{"categories":3483},[282],{"categories":3485},[275],{"categories":3487},[],{"categories":3489},[244],{"categories":3491},[163],{"categories":3493},[],{"categories":3495},[163],{"categories":3497},[226],{"categories":3499},[163],{"categories":3501},[226],{"categories":3503},[163],{"categories":3505},[163],{"categories":3507},[163],{"categories":3509},[163],{"categories":3511},[221],{"categories":3513},[],{"categories":3515},[229],{"categories":3517},[244],{"categories":3519},[163],{"categories":3521},[],{"categories":3523},[275],{"categories":3525},[163],{"categories":3527},[163],{"categories":3529},[226],{"categories":3531},[244],{"categories":3533},[163],{"categories":3535},[163],{"categories":3537},[221],{"categories":3539},[226],{"categories":3541},[265],{"categories":3543},[],{"categories":3545},[268],{"categories":3547},[163],{"categories":3549},[],{"categories":3551},[244],{"categories":3553},[282],{"categories":3555},[],{"categories":3557},[],{"categories":3559},[244],{"categories":3561},[244],{"categories":3563},[282],{"categories":3565},[218],{"categories":3567},[226],{"categories":3569},[226],{"categories":3571},[163],{"categories":3573},[221],{"categories":3575},[],{"categories":3577},[],{"categories":3579},[244],{"categories":3581},[268],{"categories":3583},[275],{"categories":3585},[226],{"categories":3587},[265],{"categories":3589},[268],{"categories":3591},[268],{"categories":3593},[],{"categories":3595},[244],{"categories":3597},[163],{"categories":3599},[163],{"categories":3601},[275],{"categories":3603},[],{"categories":3605},[244],{"categories":3607},[244],{"categories":3609},[244],{"categories":3611},[],{"categories":3613},[226],{"categories":3615},[163],{"categories":3617},[],{"categories":3619},[218],{"categories":3621},[221],{"categories":3623},[],{"categories":3625},[163],{"categories":3627},[163],{"categories":3629},[],{"categories":3631},[275],{"categories":3633},[],{"categories":3635},[],{"categories":3637},[],{"categories":3639},[],{"categories":3641},[163],{"categories":3643},[244],{"categories":3645},[],{"categories":3647},[],{"categories":3649},[163],{"categories":3651},[163],{"categories":3653},[163],{"categories":3655},[268],{"categories":3657},[163],{"categories":3659},[268],{"categories":3661},[],{"categories":3663},[268],{"categories":3665},[268],{"categories":3667},[537],{"categories":3669},[226],{"categories":3671},[275],{"categories":3673},[],{"categories":3675},[],{"categories":3677},[268],{"categories":3679},[275],{"categories":3681},[275],{"categories":3683},[275],{"categories":3685},[],{"categories":3687},[218],{"categories":3689},[275],{"categories":3691},[275],{"categories":3693},[218],{"categories":3695},[275],{"categories":3697},[221],{"categories":3699},[275],{"categories":3701},[275],{"categories":3703},[275],{"categories":3705},[268],{"categories":3707},[244],{"categories":3709},[244],{"categories":3711},[163],{"categories":3713},[275],{"categories":3715},[268],{"categories":3717},[537],{"categories":3719},[268],{"categories":3721},[268],{"categories":3723},[268],{"categories":3725},[],{"categories":3727},[221],{"categories":3729},[],{"categories":3731},[537],{"categories":3733},[275],{"categories":3735},[275],{"categories":3737},[275],{"categories":3739},[226],{"categories":3741},[244,221],{"categories":3743},[268],{"categories":3745},[],{"categories":3747},[],{"categories":3749},[268],{"categories":3751},[],{"categories":3753},[268],{"categories":3755},[244],{"categories":3757},[226],{"categories":3759},[],{"categories":3761},[275],{"categories":3763},[163],{"categories":3765},[265],{"categories":3767},[],{"categories":3769},[163],{"categories":3771},[],{"categories":3773},[244],{"categories":3775},[218],{"categories":3777},[268],{"categories":3779},[],{"categories":3781},[275],{"categories":3783},[244],[3785,3835,3946,4131],{"id":3786,"title":3787,"ai":3788,"body":3793,"categories":3821,"created_at":164,"date_modified":164,"description":155,"extension":165,"faq":164,"featured":166,"kicker_label":164,"meta":3822,"navigation":196,"path":3823,"published_at":3824,"question":164,"scraped_at":164,"seo":3825,"sitemap":3826,"source_id":3827,"source_name":3828,"source_type":204,"source_url":3829,"stem":3830,"tags":3831,"thumbnail_url":164,"tldr":3832,"tweet":164,"unknown_tags":3833,"__hash__":3834},"summaries\u002Fsummaries\u002Fgenerate-videos-by-slerp-walking-stable-diffusion--summary.md","Generate Videos by Slerp-Walking Stable Diffusion Latents",{"provider":7,"model":8,"input_tokens":3789,"output_tokens":3790,"processing_time_ms":3791,"cost_usd":3792},10775,1430,16123,0.00284735,{"type":14,"value":3794,"toc":3816},[3795,3799,3802,3806,3809,3813],[17,3796,3798],{"id":3797},"latent-space-walking-creates-hypnotic-videos","Latent Space Walking Creates Hypnotic Videos",[22,3800,3801],{},"Sample two random latents (shape 1x4x64x64 for 512x512 images), then use spherical linear interpolation (slerp) across 200 steps from init1 to init2. For each interpolated latent, run diffusion conditioned on a fixed text prompt (e.g., \"blueberry spaghetti\") with classifier-free guidance: concatenate unconditional and conditional embeddings, predict noise with UNet, apply guidance_scale=7.5, and denoise over num_inference_steps=50 using LMSDiscreteScheduler. Decode final latents via VAE to produce one frame per step. Repeat pairs up to max_frames=10000, saving JPEGs at 90% quality. Stitch with ffmpeg -r 10 -f image2 -s 512x512 -i frame%06d.jpg -vcodec libx264 -crf 10 -pix_fmt yuv420p output.mp4. This random walk yields surreal, morphing visuals without prompt changes.",[17,3803,3805],{"id":3804},"custom-diffuse-handles-guidance-and-schedulers","Custom Diffuse Handles Guidance and Schedulers",[22,3807,3808],{},"Bypass pipeline for fine control: compute unconditional embeddings from empty prompt, cat with conditional (1x77x768). Set timesteps with offset=1 if supported, eta=0.0 for DDIM compatibility. For each timestep, double latents for CFG, predict noise_pred, scale as uncond + guidance_scale*(text - uncond), step scheduler to prev_sample. Scale latents by 1\u002F0.18215 before VAE decode, clamp\u002Fpost-process to uint8 numpy. Supports LMSDiscreteScheduler (multiplies latents by sigmas initially, divides model input by sqrt(sigma^2 +1)). Slerp avoids straight-line artifacts in high-D latent space using arccos(dot) for theta, blending with sin terms if dot \u003C 0.9995.",[17,3810,3812],{"id":3811},"setup-params-and-optimizations","Setup, Params, and Optimizations",[22,3814,3815],{},"Requires Hugging Face access token for CompVis\u002Fstable-diffusion-v1-3-diffusers (or v1-4), diffusers library, torch, einops, PIL, fire (pip install fire), ~10GB VRAM for 512x512. Run: python stablediffusionwalk.py --prompt \"blueberry spaghetti\" --name outdir --num_steps 200 --num_inference_steps 50 --guidance_scale 7.5 --seed 1337 --max_frames 10000. Wrap diffuse in torch.autocast('cuda') for half-precision speedup. Higher inference steps (100-200) improve quality; guidance 3-10 tunes adherence. Users extended to prompt interpolation, fp16 models (fix dtype mismatches by upgrading diffusers\u002Ftransformers\u002Fscipy), or pipeline simplifications (pipe(prompt, latents=init, ...)).",{"title":155,"searchDepth":156,"depth":156,"links":3817},[3818,3819,3820],{"id":3797,"depth":156,"text":3798},{"id":3804,"depth":156,"text":3805},{"id":3811,"depth":156,"text":3812},[275],{},"\u002Fsummaries\u002Fgenerate-videos-by-slerp-walking-stable-diffusion-summary","2026-04-08 21:21:20",{"title":3787,"description":155},{"loc":3823},"9fd1fce56d7f77a1","Andrej Karpathy Gists","https:\u002F\u002Funknown","summaries\u002Fgenerate-videos-by-slerp-walking-stable-diffusion--summary",[208,209,210],"Interpolate random latents with slerp under a fixed prompt to create smooth, hypnotic videos from Stable Diffusion frames (50 inference steps, 7.5 guidance, 200 steps per pair).",[],"VddoAG9zJ0Akb8dH2o3dDgU_wO7ggV90n9VzfWlSvPE",{"id":3836,"title":3837,"ai":3838,"body":3843,"categories":3918,"created_at":164,"date_modified":164,"description":155,"extension":165,"faq":164,"featured":166,"kicker_label":164,"meta":3919,"navigation":196,"path":3935,"published_at":164,"question":164,"scraped_at":3936,"seo":3937,"sitemap":3938,"source_id":3939,"source_name":3940,"source_type":204,"source_url":175,"stem":3941,"tags":3942,"thumbnail_url":164,"tldr":3943,"tweet":164,"unknown_tags":3944,"__hash__":3945},"summaries\u002Fsummaries\u002Ff783931b642bec27-vibevoice-asr-60-min-asr-with-speakers-timestamps--summary.md","VibeVoice-ASR: 60-Min ASR with Speakers, Timestamps, Hotwords",{"provider":7,"model":8,"input_tokens":3839,"output_tokens":3840,"processing_time_ms":3841,"cost_usd":3842},8981,1739,13836,0.00215885,{"type":14,"value":3844,"toc":3913},[3845,3849,3873,3880,3884,3906,3910],[17,3846,3848],{"id":3847},"unified-long-form-transcription-in-single-pass","Unified Long-Form Transcription in Single Pass",[22,3850,3851,3852,71,3854,3857,3858,3861,3862,71,3865,3868,3869,3872],{},"VibeVoice-ASR handles 60-minute audio within 64K tokens without chunking losses, maintaining speaker consistency and semantics. It jointly performs ASR, diarization, and timestamping, outputting JSON-like structures with Start\u002FEnd times, Speaker IDs, and Content. Load via Transformers >=5.3.0: ",[26,3853,51],{},[26,3855,3856],{},"VibeVoiceAsrForConditionalGeneration.from_pretrained(\"microsoft\u002FVibeVoice-ASR-HF\")",". Use ",[26,3859,3860],{},"processor.apply_transcription_request(audio)"," for inputs, then ",[26,3863,3864],{},"model.generate(**inputs)",[26,3866,3867],{},"processor.decode(generated_ids, return_format=\"parsed\")"," for list of dicts or ",[26,3870,3871],{},"\"transcription_only\""," for plain text. Example on podcast audio yields segments like {\"Start\":0,\"End\":15.43,\"Speaker\":0,\"Content\":\"Hello everyone...\"}, preserving multi-speaker flow.",[22,3874,3875,3876,3879],{},"Custom hotwords via ",[26,3877,3878],{},"prompt"," parameter fix misrecognitions: on German-accented \"VibeVoice\" audio, without prompt it transcribes \"Revevoices\", but \"About VibeVoice\" prompt corrects to exact match, ideal for names or terms.",[17,3881,3883],{"id":3882},"flexible-inference-and-optimization-techniques","Flexible Inference and Optimization Techniques",[22,3885,3886,3887,3890,3891,3894,3895,3898,3899,82,3902,3905],{},"Batch process lists of audio\u002Fprompts for efficiency. Adjust ",[26,3888,3889],{},"tokenizer_chunk_size"," (default 1440000 samples\u002F60s at 24kHz, multiples of 3200 hop length) to fit memory, e.g., 64000 for shorter segments with cached states. Chat templates enable role-based inputs: ",[26,3892,3893],{},"[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"prompt\"},{\"type\":\"audio\",\"path\":\"url\"}]}]",", processed via ",[26,3896,3897],{},"apply_chat_template",". Torch.compile speeds up by 2x+ on benchmarks (e.g., batch-4 German audio: ~0.2s uncompiled to ~0.1s compiled). Pipeline mode works but requires custom parsing of raw JSON strings. For training, use ",[26,3900,3901],{},"model.train()",[26,3903,3904],{},"output_labels=True"," in chat templates, computing loss on JSON-like targets.",[17,3907,3909],{"id":3908},"proven-performance-across-benchmarks","Proven Performance Across Benchmarks",[22,3911,3912],{},"Achieves average 7.77% WER on Open ASR Leaderboard (e.g., 2.20% LibriSpeech clean, 13.17% earnings22, RTF 51.80x real-time). Technical report shows low DER, cpWER, tcpWER on long-form datasets. Supports 50+ languages without ID specification, handling code-switching; distribution chart emphasizes English-heavy training with broad coverage. MIT-licensed, deployable on Foundry or Gradio playground.",{"title":155,"searchDepth":156,"depth":156,"links":3914},[3915,3916,3917],{"id":3847,"depth":156,"text":3848},{"id":3882,"depth":156,"text":3883},{"id":3908,"depth":156,"text":3909},[],{"content_references":3920,"triage":3932},[3921,3924,3926,3929],{"type":180,"title":3922,"url":182,"context":3923},"VibeVoice-ASR Technical Report","cited",{"type":187,"title":3925,"url":33,"context":172},"GitHub Repo",{"type":170,"title":3927,"url":3928,"context":172},"Live Playground","https:\u002F\u002Faka.ms\u002Fvibevoice-asr",{"type":187,"title":3930,"url":3931,"context":3923},"Open ASR Leaderboard","https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fhf-audio\u002Fopen_asr_leaderboard",{"relevance":192,"novelty":193,"quality":193,"actionability":193,"composite":3933,"reasoning":3934},4.35,"Category: AI & LLMs. The article provides a detailed overview of the VibeVoice-ASR tool, which is highly relevant for developers looking to integrate advanced ASR capabilities into their AI products. It includes practical examples of how to implement the tool, making it actionable for the target audience.","\u002Fsummaries\u002Ff783931b642bec27-vibevoice-asr-60-min-asr-with-speakers-timestamps-summary","2026-04-14 14:33:41",{"title":3837,"description":155},{"loc":3935},"f783931b642bec27","__oneoff__","summaries\u002Ff783931b642bec27-vibevoice-asr-60-min-asr-with-speakers-timestamps--summary",[209,210,208],"Process up to 60 minutes of audio in one pass for structured transcripts (speaker IDs, timestamps, content) across 50+ languages, with custom hotwords boosting accuracy on proper nouns.",[],"CleYyRRaj1ZGtSxuM2ol1nsnQLLYzXcBZdiNsBG4ShM",{"id":3947,"title":3948,"ai":3949,"body":3954,"categories":4098,"created_at":164,"date_modified":164,"description":155,"extension":165,"faq":164,"featured":166,"kicker_label":164,"meta":4099,"navigation":196,"path":4118,"published_at":4119,"question":164,"scraped_at":4120,"seo":4121,"sitemap":4122,"source_id":4123,"source_name":4112,"source_type":204,"source_url":4124,"stem":4125,"tags":4126,"thumbnail_url":164,"tldr":4128,"tweet":164,"unknown_tags":4129,"__hash__":4130},"summaries\u002Fsummaries\u002Fc09281106c1de2ef-ibm-granite-speech-4-1-3-asr-models-for-accuracy-f-summary.md","IBM Granite Speech 4.1: 3 ASR Models for Accuracy, Features, Speed",{"provider":7,"model":8,"input_tokens":3950,"output_tokens":3951,"processing_time_ms":3952,"cost_usd":3953},6601,1943,19579,0.00178485,{"type":14,"value":3955,"toc":4093},[3956,3960,3963,3966,3969,4061,4065,4068,4072,4090],[17,3957,3959],{"id":3958},"select-granite-41-variant-by-your-asr-bottleneck","Select Granite 4.1 Variant by Your ASR Bottleneck",[22,3961,3962],{},"IBM's Granite Speech 4.1 releases three ~2B parameter models optimized for edge deployment, each targeting a specific constraint: accuracy, structured output, or throughput. Use the base model (ibm\u002Fgranite-speech-4.1-2b) for top accuracy—it leads the Hugging Face Open ASR Leaderboard with 5.33% word error rate (WER) across diverse datasets, translating to ~95% word accuracy in real-world scenarios. Its real-time factor (RTF) reaches 231, processing 4 minutes of audio per second of compute (e.g., 1-hour audio in 16 seconds). Supports 7 languages (English, French, German, Spanish, Portuguese, Japanese) for transcription, bidirectional speech-to-text translation, punctuation, truecasing, and keyword biasing—pass domain-specific terms like names or acronyms in the prompt to boost recognition.",[22,3964,3965],{},"Switch to the Plus variant (ibm\u002Fgranite-speech-4.1-2b-plus) for speaker-attributed ASR (diarization) and word-level timestamps. It labels speakers (e.g., Speaker 1, Speaker 2) for podcasts or meetings, with timestamp accuracy outperforming Whisper-X and customized Whisper models. Incremental decoding lets you prefix prior transcripts for seamless long-audio chunking with overlap, maintaining consistent speaker IDs. Trade-offs: WER rises slightly, drops to 5 languages (no Japanese), no translation or keyword biasing.",[22,3967,3968],{},"For bulk processing, pick the NAR model (ibm\u002Fgranite-speech-4.1-2b-nar)—non-autoregressive design skips sequential token generation, achieving RTF 1820 batched on H100 (1-hour audio in 2 seconds). No diarization, timestamps, translation, or biasing, but WER stays competitive.",[3970,3971,3972,3997],"table",{},[3973,3974,3975],"thead",{},[3976,3977,3978,3982,3985,3988,3991,3994],"tr",{},[3979,3980,3981],"th",{},"Model",[3979,3983,3984],{},"Key Strengths",[3979,3986,3987],{},"WER",[3979,3989,3990],{},"RTF",[3979,3992,3993],{},"Languages",[3979,3995,3996],{},"Features",[3998,3999,4000,4021,4041],"tbody",{},[3976,4001,4002,4006,4009,4012,4015,4018],{},[4003,4004,4005],"td",{},"Base",[4003,4007,4008],{},"Accuracy",[4003,4010,4011],{},"5.33%",[4003,4013,4014],{},"231",[4003,4016,4017],{},"7",[4003,4019,4020],{},"Translation, keyword bias",[3976,4022,4023,4026,4029,4032,4035,4038],{},[4003,4024,4025],{},"Plus",[4003,4027,4028],{},"Diarization, timestamps",[4003,4030,4031],{},"Higher",[4003,4033,4034],{},"Lower",[4003,4036,4037],{},"5",[4003,4039,4040],{},"Incremental decode",[3976,4042,4043,4046,4049,4052,4055,4058],{},[4003,4044,4045],{},"NAR",[4003,4047,4048],{},"Throughput",[4003,4050,4051],{},"Competitive",[4003,4053,4054],{},"1820 (H100)",[4003,4056,4057],{},"?",[4003,4059,4060],{},"Raw transcripts",[17,4062,4064],{"id":4063},"non-autoregressive-transcript-editing-beats-sequential-decoding","Non-Autoregressive Transcript Editing Beats Sequential Decoding",[22,4066,4067],{},"Standard ASR like Whisper or Parakeet uses autoregressive transformers, generating tokens sequentially—each depends on priors, bottlenecking GPUs with tiny forward passes. NAR fixes this via NLE (Non-autoregressive LLM-based editing): a cheap CTC encoder drafts a bidirectional-attention transcript, then an LLM edits it (copy, insert, delete, replace). This parallelizes decoding without losing conditioning, improving on one-shot predictions. Result: massive speedups without huge WER hits, ideal for hundreds of hours of raw audio.",[17,4069,4071],{"id":4070},"run-locally-with-transformers-chunking-and-fine-tuning-tips","Run Locally with Transformers: Chunking and Fine-Tuning Tips",[22,4073,4074,4075,3857,4078,4081,4082,4085,4086,4089],{},"Load via Hugging Face Transformers: ",[26,4076,4077],{},"processor = AutoProcessor.from_pretrained(model_id); model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id)",[26,4079,4080],{},"generate()"," with custom prompts for diarization (",[26,4083,4084],{},"\u003C|startoftranscript|>\u003C|en|>\u003C|transcribe|>\u003C|speaker_attributed_asr|>",") or keywords (",[26,4087,4088],{},"\u003C|startoftranscript|>\u003C|en|>\u003C|transcribe|>\u003C|keywords|>[\"term1\", \"term2\"]\u003C|endkeywords|>","). Requires Flash Attention for NAR (compile for CUDA 13+; issues on T4 Colab GPUs).",[22,4091,4092],{},"For long audio (e.g., 4-hour podcasts): chunk with overlap, prefix prior text for continuity. Fine-tune on domain data like court transcripts or podcasts using prior Granite notebooks—train on host-specific accents for better WER. Test RTF varies by hardware (RTX 6000 Blackwell hits good speeds but below H100 claims without batching). Build local agents to query via API for cloud-free transcription.",{"title":155,"searchDepth":156,"depth":156,"links":4094},[4095,4096,4097],{"id":3958,"depth":156,"text":3959},{"id":4063,"depth":156,"text":4064},{"id":4070,"depth":156,"text":4071},[163],{"content_references":4100,"triage":4114},[4101,4106,4108,4110],{"type":4102,"title":4103,"publisher":4104,"url":4105,"context":3923},"report","Granite 4.1 AI Foundation Models","IBM Research","https:\u002F\u002Fresearch.ibm.com\u002Fblog\u002Fgranite-4-1-ai-foundation-models",{"type":180,"title":4107,"context":172},"NLE: Non-autoregressive LLM-based ASR by Transcript Editing",{"type":187,"title":4109,"context":172},"Granite Speech Model Github",{"type":187,"title":4111,"author":4112,"url":4113,"context":172},"llm-tutorials","Sam Witteveen","https:\u002F\u002Fgithub.com\u002Fsamwit\u002Fllm-tutorials",{"relevance":4115,"novelty":156,"quality":193,"actionability":4115,"composite":4116,"reasoning":4117},3,3.05,"Category: AI & LLMs. The article discusses IBM's Granite Speech 4.1 models, which are relevant to AI-powered product builders interested in speech recognition technology. While it provides some technical details, it lacks actionable insights on how to implement these models in real-world applications.","\u002Fsummaries\u002Fc09281106c1de2ef-ibm-granite-speech-4-1-3-asr-models-for-accuracy-f-summary","2026-05-07 13:40:02","2026-05-07 16:37:55",{"title":3948,"description":155},{"loc":4118},"a46a387d67c4fcca","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Tymq54Mn8SU","summaries\u002Fc09281106c1de2ef-ibm-granite-speech-4-1-3-asr-models-for-accuracy-f-summary",[209,208,211,4127],"ai-llms","IBM's 2B Granite Speech 4.1 suite offers three trade-offs: base leads Open ASR Leaderboard (WER 5.33, RTF 231), Plus adds diarization\u002Ftimestamps, NAR hits RTF 1820 on H100 via transcript editing.",[4127],"dF2uBIfxfrOwqTG70jiimSEB82hxedQZTBWqe0_5R-8",{"id":4132,"title":4133,"ai":4134,"body":4139,"categories":4175,"created_at":164,"date_modified":164,"description":155,"extension":165,"faq":164,"featured":166,"kicker_label":164,"meta":4176,"navigation":196,"path":4190,"published_at":4191,"question":164,"scraped_at":4192,"seo":4193,"sitemap":4194,"source_id":4195,"source_name":203,"source_type":204,"source_url":4196,"stem":4197,"tags":4198,"thumbnail_url":164,"tldr":4200,"tweet":164,"unknown_tags":4201,"__hash__":4202},"summaries\u002Fsummaries\u002Fdda195cde5fb0456-qwen-scope-saes-unlock-actionable-llm-internals-summary.md","Qwen-Scope SAEs Unlock Actionable LLM Internals",{"provider":7,"model":8,"input_tokens":4135,"output_tokens":4136,"processing_time_ms":4137,"cost_usd":4138},8913,1989,15174,0.0027546,{"type":14,"value":4140,"toc":4169},[4141,4145,4148,4152,4155,4159,4162,4166],[17,4142,4144],{"id":4143},"sae-decomposition-reveals-interpretable-llm-features","SAE Decomposition Reveals Interpretable LLM Features",[22,4146,4147],{},"Sparse autoencoders (SAEs) translate high-dimensional LLM activations into sparse latent features, each corresponding to concepts like languages or behaviors. For Qwen3 and Qwen3.5 models, Qwen-Scope releases 14 SAE groups across 7 variants: dense models (1.7B, 8B, 2B, 9B, 27B) and MoE (30B-A3B, 35B-A3B). SAEs train per layer on residual streams, using top-k (k=50 or 100) activations; dense models expand 16x hidden size, MoE use 32K (16x) or 128K (64x) widths. Except Qwen3.5-27B (instruct), all use base checkpoints. This layer-wise dictionary enables diagnosis of issues like language mixing or repetition without weight changes.",[17,4149,4151],{"id":4150},"steer-outputs-and-classify-via-feature-interventions","Steer Outputs and Classify via Feature Interventions",[22,4153,4154],{},"Apply steering with h' = h + αd to amplify\u002Fsuppress features: suppress Chinese feature (ID 6159) to fix English prompts mixing languages; activate classical-Chinese feature (ID 36398) for stylistic shifts. For toxicity, build classifiers from features firing more on toxic data—OR-rule yields F1>0.90 on English for 1.7B\u002F8B models; English features transfer cross-lingually (stronger to Russian\u002FFrench, weaker to Arabic\u002FChinese), retaining 99% performance with 10% discovery data. These zero-shot methods cut compute needs versus full evals or training heads.",[17,4156,4158],{"id":4157},"proxy-benchmark-analysis-without-model-runs","Proxy Benchmark Analysis Without Model Runs",[22,4160,4161],{},"SAE features act as micro-capabilities for eval: compute redundancy metric from activation overlap correlates ρ≈0.85 with performance-based redundancy on 17 benchmarks (MMLU, GSM8K, MATH, etc.); GSM8K shares 63% features with MATH, allowing safe omission. Pairwise overlap, partialed by MMLU, correlates 75.5% with capability similarity—retain low-overlap benchmarks, consolidate high-overlap ones to streamline suites without forward passes.",[17,4163,4165],{"id":4164},"augment-training-with-feature-driven-signals","Augment Training with Feature-Driven Signals",[22,4167,4168],{},"For SFT, Sparse Autoencoder-guided SFT (SASFT) suppresses non-target language features via auxiliary loss, cutting code-switching >50% across Gemma-2\u002FLlama-3.1\u002FQwen3 on Chinese\u002FRussian\u002FKorean (full elimination in cases like Qwen3-1.7B Korean), preserving multilingual benchmarks. For RL, synthetically generate repetition via feature steering as rare negatives in DAPO, sharply reducing repetition in 1.7B\u002F8B\u002F30B-A3B. Safety synthesis targets missing features: 4k pairs cover 99.74% features (vs. lower for random), boosting accuracy to 77.75% when mixed 1:1 with real data—matching 120k real-only under budget.",{"title":155,"searchDepth":156,"depth":156,"links":4170},[4171,4172,4173,4174],{"id":4143,"depth":156,"text":4144},{"id":4150,"depth":156,"text":4151},{"id":4157,"depth":156,"text":4158},{"id":4164,"depth":156,"text":4165},[163],{"content_references":4177,"triage":4188},[4178,4181,4185],{"type":180,"title":4179,"url":4180,"context":190},"Qwen Scope","https:\u002F\u002Fqianwen-res.oss-accelerate.aliyuncs.com\u002Fqwen-scope\u002FQwen_Scope.pdf",{"type":4182,"title":4183,"url":4184,"context":190},"dataset","Qwen-Scope Weights","https:\u002F\u002Fhuggingface.co\u002Fcollections\u002FQwen\u002Fqwen-scope",{"type":187,"title":4186,"url":4187,"context":190},"Qwen-Scope Technical Details","https:\u002F\u002Fqwen.ai\u002Fblog?id=qwen-scope",{"relevance":192,"novelty":193,"quality":193,"actionability":193,"composite":3933,"reasoning":4189},"Category: AI & LLMs. The article provides in-depth insights into Qwen-Scope's sparse autoencoders, which are practical tools for developers working with LLMs, addressing specific pain points like feature interpretation and output steering. It offers actionable techniques for applying these features in real-world scenarios, such as toxicity classification and training optimizations.","\u002Fsummaries\u002Fdda195cde5fb0456-qwen-scope-saes-unlock-actionable-llm-internals-summary","2026-05-01 08:25:21","2026-05-03 17:01:52",{"title":4133,"description":155},{"loc":4190},"dda195cde5fb0456","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F05\u002F01\u002Fqwen-ai-releases-qwen-scope-an-open-source-sparse-autoencoders-sae-suite-that-turns-llm-internal-features-into-practical-development-tools\u002F","summaries\u002Fdda195cde5fb0456-qwen-scope-saes-unlock-actionable-llm-internals-summary",[4199,210,211,209],"llm","Qwen-Scope's open SAEs on 7 Qwen models decompose activations into interpretable features for steering outputs, proxy benchmark analysis (ρ=0.85 correlation), toxicity classification (F1>0.90), and training fixes like 50% code-switching reduction.",[],"zbictEOZXC-EHp6nI5NAS1Np-cHfHzWO9BF_YlaGEmc"]