# Voice Agent Stack: The Right Tools for Production Voice AI in 2026

> Build production-ready voice agents with the right stack. Compare MCPs, frameworks (CrewAI, AutoGen, Swarms), APIs (Deepgram, ElevenLabs, Vapi), and learn cost-effective patterns for voice AI in 2026.

_Maximem Team · May 15, 2026_

I

# Voice Agent Stack: The Right Tools for Production Voice AI in 2026

I built my first voice agent last year and learned something fast: picking the wrong foundation turns $100 into $300+ per minute in costs. Or worse, builds a system that sounds like a robot. The problem isn't the individual layers—speech-to-text is solved, text-to-speech is solved, LLM reasoning is solved. The hard part is threading them together without adding latency overhead that kills the conversation.

I'll walk you through what I've tested, what's working in production, and the tradeoffs nobody talks about.

* * *

## Why Voice Is Its Own Beast

Text-based AI systems have a luxury: time. Users don't mind waiting 3 seconds for a thoughtful response. Voice is different. A caller expects to hear something within 300 to 500 milliseconds. That's not my number—it's what human conversation expects. Faster than that and it sounds unnatural. Slower and the person on the other end starts to wonder if the line dropped.

Here's what runs in series: your speech-to-text system processes audio (150ms). Your LLM generates a response (300ms). Your text-to-speech engine turns it into audio (100ms). That's 550ms before your network stack even gets involved. Add network latency and you're already cutting it close on that 500ms window.

This architecture constraint changes everything. You can't just plug tools together and hope. Every millisecond compounds. Pick the wrong speech-to-text provider and nothing else matters—your latency budget is already gone.

![SVG\_04\_Voice\_Agent\_ArchitectureSound2.png](data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAABLAAAAK8CAIAAABwUdHZAAAABmJLR0QA/wD/AP+gvaeTAAAgAElEQVR4nOzddZxU19kH8OdcGV13ZXGX4MFdQ2CxhLhLG2uapmneJLWkpGkjjUvjbRogBAsWAgR3CAGCywLLutvIlfP+sSzMzM76rLDz+374g525cu6Zc2bOc49cFhwRSwAAAAAAAOB/hOZOAAAAAAAAADQPBIQAAAAAAAB+CgEhAAAAAACAn0JACAAAAAAA4KcQEAIAAAAAAPgpBIQAAAAAAAB+CgEhAAAAAACAn0JACAAAAAAA4KcQEAIAAAAAAPgpBIQAAAAAAAB+CgEhAAAAAACAn0JACAAAAAAA4KcQEAIAAAAAAPgpBIQAAAAAAAB+CgEhAAAAAACAn0JACAB+xDj13dSstILsin+ZR94ZKzd3ogAaxCelGlUDAMBvSc2dAABopVjQ9A92fj4r9OptJ1667jfDbv5fFq9uN8vEN3csuDXKZS/71mdHzPjkkt54Sb1WsZjb/7P/9bFW5vYqV47MHzfln8e0ZkpVk2Oh19929+i4q0VGT9vy8Vd786otZ7U/OjL5ssbNZ9+5VtIJANBiICAEgMbBi9YvXJOVfGvMlYYZs4ycPTVuwefVxXZBo+ZMjnAdusBLty1YkYZo0AshMfmmYRbm+TKTu86d3etfLx1UmiNRzUAIHXz7b/7Q/2p3lrLftuTrvXk+CdaQyVc0aj770LWSTgCAFgNDRgGgsZRtW7ws1bUVxozXz0xuU83XDgsdN3NSqOsGesHGxatzcG/fC7HjjJv7GyqFKkQkdZg1Z5CxyRPUGiGTAQCg1UMPIQA0Guf+RUvO3v+bTle+aJh83ZzkDh/865T3m/UsYsqc0UGurW89d83CDfm+iwe1lM2ff1JgvHIKXrYn9RrtfZR6zp7Vy2uoQiTG3zBv+PztG8qaOE2tjh9lciuqGgAAUDcICAGg8Sg/f7v0l0ee7iNXNDOZ3GvWjO7vvHpY9bK1EDt57gi3uVpa2qoFm0t9mCD16KLnn13kwwM2G0O/m2d1rPIbXIi84aYxz29cVYi+1Ybwp0xuPVUDAADqCAEhADQi7eSyhT/9pvegq50sUqfkOX3ePLy/8twrIXHazCEm13hQPbfs210Orwc2xPSdNHvG+JGDenVrFx8VZJGZWlaYfencyYN7t32/fOnqA5le9zNOfffM5zMDrpxEz/vvLX0f3eh1IhizJg25MXnS2KH9endKiosMtohqSV5OVlbmxVMHd2zZunHzjp9TS731ocgRPcbOSp405vo+3drHR4dYDUwtK8hIOXFo1+Z1ixet3J3m/ZLqxDxszsw24tW/uT0jvSwqLqxiuK0QOmHulPDVC2oabWtuP/6e++Ylj+3XKT7cyksyzx3Zvu7bjz789kCuHn3XgkOvjrg6KFJLeffGUc/t9ZpX9bzkqj4OMaz3zDtvv2na8N5JMeFWvTjj7E9bV335/qcrjhe7XI88/OWdy++PEysdVu7//L6M511e0C58OLv/83vqOt+vgZlc1dUZE4bf9dBds8b275YUEWiQnCsfbnvvCrvbrvUue+5HCe467fY7bps+qk+72IgAXkU21pDaBudzw6tDLXOjHumUejy9dvPvu19tCSn7XxiW/PY51xEMlbZx7vj9oJs+cpkJ3YAPuim+KwAAaoSAEAAak35h6cKdzw8cdXVZDikpeXb/+fsrBXpiu5mz+hvd4sFTi7/52VnpkKZ2U//wyp8fHp3gFjySGBiR0DUioevAsfN+9fuLmz959vevrTxnr7R3rYiRgx/884tPz+oRJrmeQw6JTgyJTuzca8C4Wff/4ciro8a/ftR98Kshcexv57/42KR2Vo+0RSb1ikzqNfzG+5/6/fp3nv3N6xsvNWg1kqCxc6dEu8y15MU/vvRcxjMf35NY0RxmASPmTYtZ9Hl61WGDpefdb3zx12kdzFfSGprYY8S8HsNn33rz248/+u/aJcXHl8wMbW547qN/3js48mrWhyX2HHdrz7Gzb1r0xK2Pfnu+qdZx8Ukmu2NywuTnPnvzvgFh4tXcYuSac/Uue+4nEqNGPPreW0+MSzA0YzY2vGz4JjfqxhcdvrX4oJvquwIAoGZYVAYAGpWesWrxj24dEmLitFnDzJ7biZ1nzO4tuzSNuOPgt9+c8BhayoIHPblk7UdPjPGIBj22MiWO/vWXa//39MCgaraqiqnbnV+uWzT/pp7ubdCaBVz38IK1nz8z2aOF55m0CU99/sOnd3RtwHokLGz8LRPDXEOVos3LV61bsdJ1CR9mGnLTjLaVu0suk7ve+9GSv7tGg1f3lKOHPPnZf/86MrTGXwhfX7LUds5b3330wPWRXrKeGdvd9Pq7j3Vvoofj+SKTPQ8ZMPCp/374wEDXIMFdvcueOyFi9B+//e/vxid4mf7YZNnY8LLho9yoCx89qqTGD7rJvisAAGoDASEANC6e+8OCH/Jdu1CE6MlzRwa4byX1njWjm2sblTt2fbPsnPtdfyFhznufPzU0TKhF85AJYdc/+/nrN8XX7VuORU5+46uXpibIdW2BCjHT3/ziuTFRrk1XrpWkH9u3e+e+Exk2/WpTk0lxk176z5+HB9ezlStE3zBnrGuoqxeuX7Ip33lg2aqLrsGK8brZczt7D1YMPX797l/GRFXZXiVm6TZ3es/qgwbfX7IQNHzOlKQqFnEhIma57tePjQ+q9hg+4oNM9sSCpz/5cJ/Kj7AgVv5SvcueJyFk8sN39/JyoorzNX42Nrxs+Cw36og3PCas6YNuwu8KAIBaQUAIAI2taMOiNVluEWHY5Dmj3Zo4hr5zktu7DmHnpVsXfOc+Eo+FTP2/56ZEuj2k0HF+3d/umdKrc8e4jgNH3/OPNRecrs05IWryX/4wvi5tqcCxf3jxpkS3/giu5R9cOP/eG0d17dQxJqlb1+un3fyb1xbsSXO4nokFTXj2T8lxLgGWXrD73fsG9RwwZMrMKVPG9Ogz7ZlVqcqVXZjc8c6/PNq7Xr00QkLyTUNcO/b0go1LNhcRKQdWrD7n2qUqd5kzx9s5WPj0px7s69bHypVLm1596MZ+3Xt06Dt+zv8tPFJc0yjIRrtkrmbv+vLFh269Ofn23/5zbYrdrYEuhI2dPPRy97Ky7bnBUbFtIuJH/eWA26A65cD8wfFtImKv/Gvb9491nEDY8EyujAmCwBhxveTCru++eu+td979/JvVey+WXo4T6lv2qlDrbKxR3fPZB2WjHrnhk/Kg6z4ICKv9oJvyuwIAoHYwhxAAGl3ZtsXLLs57OOlKR4oQMnbW5LBVC3Mvt3pMg2fOSHTtZtEL1i9e475WhxBz433T3MJBvXDLc3Mf+PhcedOu7ODKf915rGjxuhdHXe3YEaKn3zX9xR/+k1WrVh6LuuGh2e6LUuhZa5+efc9/zlyZjJhx5kDGmQPff/VeUu+EIv3qjg8kx4iuu333hzv+svbKabX8gx89+nS3rf+9J+HyVszQ5Y67h73+5CZbbVLmQuyUPM/tyXh67rrlm4qJiJSfv1tx9sHfdr7yxS61nzln8D9+2uY+X5NFTpo3PsQtsC7d+9Itd795rHzCZv76f//2YKqw6bO5CVV3fTXWJes53z+TfMeXlz/UTRv2FC5b/+Lgq8GrENitV1tx7TGNiEjXNJ1I1Dwb8VzXNFVtwKSyhmdyFfTCfR/cd+8r69OvxCPMZDY6GlD2qjhPXbKx5lTXLZ8bXjbqmRs+KA86982zNqr7oJvsuwIAoJbQQwgAjc95YMHSM67dKixw5NwpURXNU8uI2VPcWn96zupFGwvcW3WBQ0cPduvU0tIWv/Pfc+5dAWf+98aSDNeGHzMPHD/UY3hqlQKHjRvqNtCLF//4j99+dcbb0jS284dOXXlAYuDQce7dSVkr/7PWMwgt2f3DrlKX14TIkWP61Pm+v9xrzqyersPo9Jy1y7ZffjSH+suyladd81mMv2HeCKvHIUwDhg10y0k9a8U7Hx9zXb6H56z710c/KdWE0Y1zydz504cvfOXyoarn12845TaRVIyIjmjsXy4fZLJXesGmFx6Y7xIkEBG32+y8AWXPm2bOxoaXDZ/mRp34YMQoVf9BN913BQBAbaGHEACagHJ48dIjj/z+uqsPJDQPnz01/n+fpepEgSPnTnbr+tMurfp6i8fjB6X2XTu5TS7jtr3bD1ZqINr37/zJcVfs1cYkM3Xu2kaiX7w9+NCD1L57Z/dxlI6dy7/PqLnHQGrfvZPb+qhCzL2LU+6taTcxpnOXYLarpidDuDH0u3lmB9cvbj1z3dLtV56Nrh5dvurE4117XNlCiJh685iQDStdomsxsVM798a248DWvZ5Pe9Qu7th5URvQvoofiUa6ZPXo2nVn3Xpy9OzMbPdPQDY2dsvYB5nslZ69+rPF3p/2Xu+y51XzZmPDy4Zvc6NOuC96CKv/oJvquwIAoNbQQwgATUE7tWzhftcJfsw4aNbMJJGIhY6f5baaI6lnly7e7TkAj4WGu41yJD0/I6vyMynInplZ4NYSE0LDal4ts/wUYZ6nyD13vqgWTTAWFl7LU3jsF1zbpFWwDJuT7Da2Vktfu2KHS1isnli57Jhrv4QQOn7ulHC3FmhwqPtl8qL0zDLypGekZ1XdNm6cS+bquTMX3Uf2cYfD6f4RsMZeX8MXmeyVemTvwSpG/dW77HnTzNnY8LLh09xoMFbnrKr+g26i7woAgNpDDyEANAn94tJFO18YPPpK3xQz9J6T3PG9f+VOnu2+wIxyYvHiQ5WXfKjUKmuM9mE9G8n1bVxLUt2+g4PG3uT2ZDzi9vOlsTfMnOHyksgv5Wm9oq8ENMw6Yt702IWfplXX8+Et/dVfU6NcMreVlnnO9NK0pugYctFomczt2Tlengh/5Rj1T7LniZo5G31RNpprVU1B8Ay7mMXq5dks1an2g26q7woAgDrAFwwANA09c9XijX8aNe1q8Cf3mDWj9+L0m0a6PouLOw5++83Jyus/8LycAp1cpj0JYTFRBiLPyNEUFe3Zk5iXX7u2MM/LzXc/RXjbpEC2I6+m0LNS2rRL6z74cmeNE5v07B2ZdWims7AJt0x07yZg1qGPvjm0ht2M18+Z0e6L989czlS9IC9fJ5eH57GgmEhzpZwUY+Kiq15TptEu2csBmrRnyEeZ7A1XVWdV11LvslfV8Wr1UuNoeNnwdW5UnVTPF5jJ7BH9MUv79tF165ur/oNuku8KAIA6QUAIAE2E563/el3e1LnhVxpDUqfkJ1/IHeI6W4jbdy5anuKlVa2ePXHayTteXYeemQcM7WP6bof7NEJT/6F93abocPvJ4xdqMYGQiNSzR0/aeaeAq6cwDp0xKWbh1+k1tMTUs8dPOdzSZsrb/dkba0pqddraEmKmzRkTWI/+BWbsO3tul3///Wh5Nmipp86V8r4hLpfZd0hf0+LNbjkpJg0fllB1O7hpLrmWfLMQCBH5LpPrqt5lrynVMp8bXjYamBt1KA9Op3voJkbFRgnkckOKhY694XqT7/orW1TFAQC4DEPSAaDJFG38Zo3bbW6x7fSZ/d3iwZKtC1Z6XzyiePuPu90epibGz3nkliS3u1pSu1uemOnWr8VtezfsrG1jq3j7hh1lbo8XDBzz+9dua2/ysq2pTc9OoRUpL9q+cZdr2oSwaQ/f2tlQ9ZkM0YPmPXX3gLos6yG0men+ZLw6kDrPmdvnSnLs+7btsbk9rzEm+dd3tndNjBA99ckHelf3TPCmuORa4orTvXeTBQbXJ6YjX2ZyXdW77DWdWudzw8tGg3KjDuVBz8nM0dyqQuToSf0sV/eMmPj876b49KnwLajiAABUQEAIAE3Htn3x0ovVDKrT89cvXpPr/f6+nvHdp6ty3J5vHzL65W8+fOqGXvHBZnNwXO+pj3+x6I+jg90eVZj53ZfLa/cQQiLiWas+WpLmlj4heso/v1v79iMzB3eMCTabzEFRbXuPu/mxN5ds2vbWjbEVp+KZ33283HUJFhYw5LnFnz4+qX2ga2oEc2SXIdMffenfG/bt/P6tR0bF1KGhKXZOvrlfdRFataR2ybOuN1akNmfdgvVuK++woOEvLv7k2VmDuiREx7XvO/XRd5a/nRxX9YBRapJLri09PyvH7QkZYvsbH5rTJy7IKEuSJEmSKNTyrD7M5Lqqd9lrOrXO54aXjQblRh3KAy8+dtR9PILU8f6Pvn353uRxoybNvHf+wpVf3N5O8mmZbUEVBwCgAoaMAkATch5YuOT0g0928f7Vo2evWrixsMrZNwWr5s9fN/q1yVcn4DBTuykvfD7lhSr20LPX/eXvP1R5QC+KN/z9j9+M/vDmRJchXWLodfOe+2zecx6bKkdc01b0/ct//W70WzOuPHGayW0m/WHBhCfzL545k1agSAEh4dGJiVGBV8IN7u2ZalWSe8+e2cMtVFF/+efkUf+oYoQii75zwfY3x159uoQYN23eqPlb1pUSEfG8la99+NPEZ1w6Z5kxcfwzH45/pvYpavRLrj37kZ9PqdOuPqeNSW3nvb1m3tsVfzu3/bb/zZ9m1FgOfJrJdVbfstd0ap3PPigbDcmNOpQH9ej3a8/9umsnl9VspMgh97805P66ZEydtKCKAwBwGXoIAaApqUcWLzlcxYoL2qVVC7ZVfv7BVfrFRb+6983dtVsjRs/f+897n1zg/WlgVeJZa5687YU1qdU9k9376dKWPXrXyz9mqW4D3QRjWFL3gUOGDh3Yu3v76MB6dz4Z+t88y+2RgNx5aNG3J6qcr8azVn2z2W2hQyF8ys3jroyscx59/5E/bcrSqrxKvXD/x18f8PJYD9dtGvWS60A7893y/fYGTyT0dSbXVb3LXlOpQz43vGw0IDfqUh6Unz96c31O1V8Set7eb9efr9/E0CqP2VIqDgDAZQgIAaBJaaeXuz+Q8Ar1zJLFezwfP+iB5+/8Z/LUX72zNa269h53pG374L6p817eVZfewQq2Y1/cMfHm5775JV+t0968+MB7N0+66+VVp4v1GnbkWnHK7u82naltsGoZPic5wW1qpGPvkiXnqlvRMveHJevy3QfYjp0zNeJKK1M5/ukDs55dddZWOanceWnTy3fe+69D7v0SXFc9A8hGvOQ60c58/vTftmVXHd/WRiNkcp3Vt+w1kbrksw/KRr1zoy7p1NMWPf3A+weLvBRMXnpy+dNz73zjQP26fKvRUioOAEA5DBkFgKalX1y2aMcL14+xejSbleOLvz1c+fGDldlOf/f8rHXvDpg0Z/rEUYN6dm0XFxlkkUm1FeWknjt5aN+275cvXbk3vSGjrLTsXe/9etKX/xhyY/LkcUP79uyUlBAZbBa10oKc7Oys1FMHt2/avGHTjuOVggVn6o//uHvrR11Gzpg+Yez1fXt0TIyNCDSL3GkvK87PTj1/7vSJI/t379q6bc/RLEetG7lB42+eHOX2ZLyyrd+sqqHvs3DTN9/nzLrl6n7MOnze9LivP7lUsV/Zkc8eHL5lwj33z0se069TfJiVSjPPHN62dtH7Hy39OU/oPSrc7ZYhL8zzFl83ziXXlf3wB7eP+GnuQ3fPGDewW/vYUKss1vGBb42UyXVW77LXJOqWzw0vG/XNjbqkk+f++OeZwzfd/sg9yeMHdkkMNToLM1NP7l+37OtP/rflvF3qMamemVW9llFxAACIiFhwRGxzpwEAAFoYIf7BJdtfGWa40orW8xff1ufxNbbmTBQAAAD4HIaMAgD4I3ObLu08e2mvYKEjH31osOs0Jl62a8serG0BAADQ6iAgBADwQ0LohJe27V7xwdM3DW8X5DZ5wBA98JaXvvnojg6uy+1r6d9+/n0VDwQBAACAaxjmEAIA+Ck5uv+83/ef97RWlp1y6nxWfqlmDI5p16VdtEV06zrkWtqKv768qbi50gkAAACNBwEhAIB/Y6IlqkOfqA7e3+Vqxo8v3frkigwscwgAANAaYcgoAAB4xdX8o9/89ZbRt3100OcL7wMAAEDLgFVGAQD8khzaedCosSMG9r+uZ9d2ifFRIQFmg8QVW1F+RlrKySM/7di0bvnaPRdKMXEQAACgNUNACAAAAAAA4KcwZBQAAAAAAMBPISAEAAAAAADwUwgIAQAAAAAA/BQCQgAAAAAAAD+FgBAAAAAAAMBPISAEAAAAAADwUwgIAQAAAAAA/BQCQgAAAAAAAD+FgBAAAAAAAMBPISAEAAAAAADwUwgIAQAAAAAA/BQCQgAAAAAAAD+FgBAAAAAAAMBPISAEAAAAAADwUwgIAQAAAAAA/BQCQgAAAAAAAD+FgBAAAAAAAMBPISAEAAAAAADwUwgIAQAAAAAA/BQCQgAAAAAAAD+FgBAAAAAAAMBPISAEAAAAAADwUwgIAQAAAAAA/BQCQgAAAAAAAD+FgBAAAAAAAMBPISAEAAAAAADwUwgIAQAAAAAA/BQCQgAAAAAAAD+FgBAAAAAAAMBPISAEAAAAAADwUwgIAQAAAAAA/BQCQgAAAAAAAD+FgBAAAAAAAMBPISAEAAAAAADwUwgIAQAAAAAA/BQCQgAAAAAAAD+FgBAAAAAAAMBPISAEAAAAAADwUwgIAQAAAAAA/BQCQgAAAAAAAD+FgBAAAAAAAMBPISAEAAAAAADwUwgIAQAAAAAA/BQCQgAAAAAAAD+FgBAAAAAAAMBPISAEAAAAAADwUwgIAQAAAAAA/BQCQgAAAAAAAD+FgBAAAAAAAMBPISAEAAAAAADwUwgIAQAAAAAA/JTU3AmoFUEQTGaL2WyRZFkUJcZYc6cIWiiu65qmOp1OW1mp3WEnzps7RU0KNQVqCTUFNQUaW6uvZahHUEutvi60Aiw4Ira501AtxgIDggKDgpmAzkyoG0VRCvNzHQ57cyekSaCmQH2hpgA0ttZWy1CPoL5aW11oLVp0QCiKYnhEtGwwEJGqKE6nQ1VUzjXcWYAqMSYKomSQjQajIIpEVFJUVFiY19zJalyoKVBnqCmoKdDYWmktQz2COmuldaE1EU2WwOZOg3eiKEZFx0myrOt6aXGx3W7TNI3j+wZqwrmuqarDYSdOkiwbjEZJluy2suZOV2NBTYH6QU1BTYHG1vpqGeoR1E/rqwutTEsNCBmLjIyRZFlVlZKiIl3XmjtBcO1RVVVVVdlgMBiMxLnT6WjuFDUC1BRoMNQUgMbWSmoZ6hE0WCupC61OCw0IAwODLdYAXddLiopw5wnqTdd1XVMNBoPRZHI4HJqmNneKfAw1BXwCNQWgsbWCWoZ6BD7RCupC69MSZwMLghAYFExEZSUl+MaBBlIUxe6wE2NBIaHNnRYfQ00BH0JNAWhs13QtQz0CH7qm60Kr1BIDQpPZwgRBVRRVVZo7LdAaOGw2XedGg9FgNDV3WnwJNQV8CzUFoLFdu7UM9Qh869qtC61SSwwIzWYLEWFUMfgK51xx2KmiaLUaqCngW6gpAI3t2q1lqEfgW9duXWiVWmJAKMnlaxljSDH4jKI4ichoMjd3QnwJNQV8DjUFoLFdo7UM9Qh87hqtC61SSwwIRVEgIs715k4ItB6qphGRJIrNnRBfQk0Bn0NNAWhs12gtQz0Cn7tG60Kr1BIDQsbKv3QwZRl8h3MiYkJLLPD1hpoCvoeaAtDYrs1ahnoEvndt1oVWCZ8BAAAAAACAn0JACAAAAAAA4KcQEAIAAAAAAPgpBIQAAAAAAAB+CgEhAAAAAACAn0JACAAAAAAA4KcQEAIAAAAAAPgpqbkTcK3gfXqWLumsS8SOHLVOPy5oTXJWc4hyf6wuEbuQIX+bz1pa8gCaGdPvG1HyQgQxIuLi6xutbxa6vR8Wqjza1TkhXI+Vud3J8u3CqUJx70Xjh5lMJ3KpOJdpOiuyC0eypc+OGzeUNu21AFTBHGXbPEyJZkREBanmEXvkoqY8PeOjOjj7yaQr4rdnpNQan0In8J5xzrvaqIND9WiZOxzipRJhY6r89QUpFb9M4FOx7cu2XqfKVW+wcnfQI5caehYxyPndOHsPRsUXzP32yc5a7cT79Spd3IHe32T9Z6n68VTbBJGISHfKj60zr6w4hGB2fjXRPrTirXtXm3/UKw5QfT2SlSvHLKdqLLtU3J4qv31KTkFFg7pDQNiiWUKUx7upBqJtdmlJPsPjYAFciVZlRhhdvlPC9BsTtHcLRbXiXWuE4+thjq4VP5mykQcatTbBWi9N+jhT0r0cj0SBh1q0EUnakCj94Q3mH2r3yw/QmPjwRDWy4n5gcLQyzigvdTRlAvRRHRz3WUmzGXafkVKr3ZQZtEcG2Z6MunqTxWTWgs1a9wjNVGR9Mbea25oArYigT4jhvMywroiRS9gmGJRbE0yrz16+I9m5rXOQ6GXvetQjSeSxQeqc7ur4SD53u+Gk1184gKohIIRGIQgk6KTWvCFA/XVMVHoIRESciBFvH6/0OSbuv/xDyCd0dHYRievC+uPGTzOFEsZjArUhseoAL3dP2emz5ifOMbNVe6SPfYyZJLNya6xp/XnchYFmxmR1eiwXiPjlP7UZMfqy80JLLJlMv3lA2VNRXCDSHOLCk4ZVuUIJ4+3CtGlJSgMaqFxmTGmJFwzNLDfdeG+poXzuU4e29ufidZHY2fPGv6YKnIg4ZRZWf4DGIgUp46w87Yz4i07kHvINbufsnGI8rhOJ2q1JupdWeF3qEdekl7aYdnAeHqz8vo+zt0QhEY5HY+XHL+HmC9QNAsL6mzKo+P0Ezrj4xnaj1tYxL1qLZsKpLMOLPxl2ONw2eHOXUUyyz47Uwxg7nm6Yf8i4y0HE+B3Di1+KJNKlZ9ZYFri/8tQaU8j1JS+EXz7X8L4lKX2JOFu0I/DpzDonNTHB/nx7tZuVhxnIzKjIzg5nGf59zLDVRkQ0pE/JVx10URfe32z9e/nAVKY9Mbbst8Fctxnu+cG0SaWgYOXhLs7JEXqCkSsO4Zds+dNjxrUlnlnx6nYjtXXcGq1F2ozTNxqP4rtJrtMAACAASURBVB4VNB5Bmx7PJSKuSIuz9NnxumhVZ4TR/hwiImI80UKMSHeIn52Ud+hERIfypHXnjV4PZrcLxwoFrVB4M0wZ2VkTicVYdIFEDL2B5hUao4wxEBE7fUEqTlD6CXxIohp7wZBWESCJZvVXvRy3xWihunDokuHvafrrQ5ztBMpNsQw+IClEJOgjOjjuS9SuC9ADGMssFjekGN46J+VwItfhcBfNd2Zrv+moDAzgzjLpu+Omv10Q1Gj7nqHOMFZ+IufCmU4iUnJNY7cYLlSK0EwRzsejuUDEVfEf26wfVLTFD+ZKS88YAllFC1XUx3Rw3tdG6WXlAUTZJdK2VMNbp6ULmmd6bsvSnums9LPyH/cF/Sq1hgsBP+S0iVts5f/lRVGXXywukbZkuk+cqbbI1WoDV4wP6mB/LEntHUABjIodLLNUOHTR9H/nBKVikw6xWgcm/CdNcr0trtmFDFmPD1JuCTP+KYdCYpXpZtIVIY3rCYarm9W2Hl2+bpZaKBzViQpEFqZ+0U4XGPUO1aVLolqLdAJcgUVlGoxpD15f9ts4PVwiWdK7x9nf66tEuW/wwCDbfeGk6iRLvE+i47Ohjj4egwQa9/eMR4aqEyL0OJmKHSxP46EWfVRb++cj7CNkIqI9Z+UjOpGgJ7fVLUREJAWpNwRyIrqYKm9XKSLGvmS07ZEErb2Riu2MGfTBiY73R5c+FOxxIu2ugWVPJWhxMuHeFDQ2OVS5MZATUUm2/Np5KYcTMX1yomouf5uzDDvnRIJZ+cdw29MdlfHheqS3wTkedOKciIgXOlpkJwz4F318ohZARDpbe8a4Kp84kTFCmWKpeF/SnhlW9rsELU4is0Ef3M7+ZT8lwvX7V9TuGVr6RS9lTIhu0YV8jceFqHddV7aknxrl/jVtibV/3VcZZOEmgUIC1Nv7lz0aWqek8u4xagwjIspLM/7Ho2dGZ8XlbWtRf3BY6ac9nSOCeIhIkkixwercHmXfDXN2d6+e5mj7F/2cwwK5WajbhQC4qbHI1bpMlktoW/Zpb2VkMA/glGEnMuhdItQZMdrVmI7pE2J0ZpfW5bvtyB3S1+lMZ/r09mow49PaKiGM0lINm93is9rVI2+u1IPy37Ca0wngAgGhDyh5pmkrA3uusXxrIyIKiVaHu89xLko3jVsdMHxN4BOpTCOyhDp/k6C7/oTplX/PuPDx5qB+B6TySUzbfgpouyQoaWl9ugeJWHq66c71gd1WBA5ZGzBwZeCcE4JCJAUod8ZyRqQVy19mMk4UHe8cZyAi3jVe6SAQ6eKS86Iiao/2cXYSSSuVH18X2H9N4ICNpq0KCQbtiV5KrGvKGYVq0otbAwauCrxhv3wJ3YPQmPonqAmMiNj2S1JGjrTZSUQUGacMuzzuga09ZTilERElRCiP9rZ9Mqpkz7Ti5QMdoy1ejiZJPNLEk8LU++K5SKQr0vIMhiIMzUswazMiOSNSS+TvC4X1aaJKxARteoJe3lJNaOO4M4gYUWGO8eY1gT3XWRY5eIDL13J8G8fvorhIbO8x6+BVAQNXB9x7TlCJktrYfxXufi6RLd0d0HNF4JSjooOIMT45TuOZpr7LrJ+UEhFpNsPNS4OSlgR13Oyle5CIEqx6eZPibIFgq+KKEpLsT0ZwgSg3yzhrdVCX1ZaXs5hOFBLheD5Jd22RSDJdOGO+YU3gwHXWt3PrcCEArmoscrUvk+V6ROgBRFqJ4bbVgcPWBl63InD4JsufzwtXppyLVnVCMM/JkA94/oSwLWfli5xCY5wzop23RRJxYVGKaPdIcC3qkcsheUKw3j1EG55k/12iLhARp8MFglqLdAK4wpDRBuPCmpOGX1QiVdpeQLPNxAQ90kikuGxwRrrEiThbc1Z+Nt4Zx/iASM1w4Wrm80buiUjPFYNi1IeT1LYmMgskGi93SbYN4CIxlYTVZ6SnYpQ4gzIv3rTqvD41nktEjjx5STFJIepoMxGRLmi39C2bR0TEExgRkSVM7SfKq64OiWAbjpo/zWacKMuBe7bQmEQ1OU4XibgqfZ/FuCquzWSz23DBoM6Ipg2XiBMVZ5vmbBLv76TcEK22NxIjEkR+XaLjk1B++0bTTrcZrrxr59LdnS//UVIivX/AvLCsGS4LwFV8vHOgSEQsJV06phNPl4721Pow6pmgdDxpPMH5gCjNREScrThm3GUjIumNk/JNg5TAywfgQ2JUKxFxHhHleDeciIiZiIiI8aGRmpQjXvnxUXPld9KZSnQ6U0rrqrUTeKSZ+/qeMb8+RjUTEReWHzfutxOR9Mlxwx2RjgTG+8dowWeFKwuoqsWG5w/LRzgRiVnE59R0IZiyDt7UWORY7ctk+QEzbUwjLlqVlwbzXYXi2WJ2KFdamMeudN3Fxyg9GFuW7hnpEZE9z7CwwPl0qPq7AVogI1uWYXEh3deAy2Oi+sKYEtdXCnON76az2qQTwBUCwoZjqRWV3llxN0h0j4Zylct/c4UVcYpjZDKQt14KYo0RRgn6zYPK5sdVnrvMjRWNgbIcw8Ii9TfB/Pq2zi5FNNXKidiO89JFTrJRDxWIiGSzPtTsdr+LCTxYoqtLx3D2SyEW4YCmEBCljDcRESmFQppJ62Kk3ELBRpqV8TGJSuglOY+IiAoL5df2ya8RRQRqg6KdD3ZV+hpIsirJYaadWVUe3GTg0QYMe4bmxvRpiZqBiDj9XMI6BGnExMOlrE8AlwKV6SGGfxZQiIEzIiLhUkVXgs3G8jkFlhdfxsOMjBEnRu3C1XZuR+eB7kPHnDYxq/zrW6fyPgShjpMZLpUKOukiUfsQ3UyCl+e2MD3cwBhx4iy94ndTs7MsogQiycCDGF1pfCtFwskr56/LhQBcVWORE+pQJsuPeOi06ZMw+z0ReqdopVO0QkScs5Mp5jsOSpmciOlj4zTRKa/L8ZYeLnx7TnokVA02cOJsQ4qcxj27EWuuR96oGsspFXdcMrxzSjqj1yKdAO4QEPqAXlG1qqhivI2Fyr9RZItevnq43UllnGsV3wOmy+PU9QST+56+SJ4U4vx1rC4RleYa791j3GsjKc6273olyO0axAVnxQf6qgEhyl97UBuBdKe0KE3gRLqDFXAKYVRw0TJ0r1TtdxNryEJyALU3MlENZ0REhnDHwnFua/AHRCnjTfIiO0Vb9YJSofy9nGJxdbG5IED9qj0XGA/0fHAVO3LUOuMk65hgf7+f0t6g3TGgLOVHyyfFiAqh2YiByvQQYkTE+Oz+JbNd3xP0aQn6v/KFAifjxBnpsSaiEiIis5mHXp1LxPIcnBMxLv5zvfWdYm9nqfiP3tCRKuyXTCmjozOeUVic4/Yg6UPXdrTAAxkr1oRcJ+dEjPErCRaNevmse9XBilySoOp09fekFhcC4AWvqcjpdSiT5XS7NH+L9d0AvU+w3jZAG56oTAziXdra550NeLOQBJM6MZSK0uWdVfRZZ14yfN9DnWUkzSZ/lV75Hnpt6pHL9anywyvNa701vapPJ4AHzCFsfIxP7eoYE8DDAtQnuqhhjIjY3mzRSUKWnelExLQRkVwiatvGMdPqtqtDLf9FZHGBekDtmqaBAdrIaHV0xb+RodwkU/nwocJC8ScbaUwfF6daK+2YcdGwxk7E9EERukiUdcmwSSEiUoukzTYiouBYxxNRvLwhbTRqYzrYP++teF+xEaAxMYMyPbrKwWxMUmfEcoHxif1Kt40t+0sX55RorU+oNizR/qs4LhCRLp4t9dL25To7fsH0h7OCSsQk7dHuamRjXgVAtXj3BKVz1V/7ifFKf4HtyxLtRMT49K6OwWYKCVCe6qIEXN2K7cqUyoiIabd1V7qU3wEWeGKE8uRA271BXg9cCWNlGiMiQdY7mKvrObdnG97JYjoRk7Tfjyib31EZFqb1iVCTO9k/GVv6eAgnYrsyJBsRMT25q2OQmVvN2oPdlDhGRGx/plh1M9UXFwL+qMYiV+cymRDjvDVGN9rELZfkL0+Y3km7vKJpiMyJKCJa7SfQjjSxpNKO5bgifXZC/j5dWnjcsNfb8M1a1KNaqT6dAB7QQ9j4OCs2Oz+beHVSXVm+4c1UgRPtviRltVFiGJ80oPjnPswkcaf7I2vsheIJXe0j8PYdy450JNKlp1ZbFlc3I5gntbF93ubq30quafQucZuTZhgptq19qVXIMuoDA7z1PariFynCzK66RES6uOK8eHkKlSa987M8fJDSQdIeGl5yu5NKiMIMXCZyXDKjAwWaXkSsMlImIspPNY/cI1+5f2qOsm0apsQwGpjojD9vIOJRIerdIerd7rtnZxoWFFZVctmek8Z1ibapRgqNddwfJr+c11hXAVAdQZ+eoEtExIXXN7rc0Wf6vSNK/hhBolmZEWF69oLxP+3VB4IoNMqxaIqDiIptQgnXAxlxzogo9bzxtTjt+SgeF29bG2vLcQhGgx4kEtPFN09yqs3IaJ0dLCA9iARJnT+5aD7R+VPWsYe9zdnjwtf7zNGDbY9FcMmo3tZbvc3lrY+JiCj1vOmNhNJnI3hYlOObKVf79gtyjH87L1R6ZttVPrgQ8Es1Frk6lkkeHuF8sbM+n5jNyYqIRxi4RKTZxc0FjIiPjNWMmrQuq7rpM4dOmx88XfXbtahHtVB9OgE8oYewCQj/3Wt+6YKYqpBTZT+nGu/dafxZIyIqzjA/dFg+aGNOnZWUiR/ttbzh3vrUig3P/izvK2UOXv/ho9wpv7DDtDhXKCHeIVQPKDQ8eFCqPAqCiP2Scvl+lVokLXZZLjkr3Txzs/ndVPGUjSSZBxJLLxJXnzH+3ykRy1VBU2N8YqJqISLONlyUXEfT2HIMq8uIiAxh6g0WWnvY8vwx+fsc4ZyNlehM1VhqofTNL5bZe+TUqqsTt0tvnBYdREzQb+uuJOCnE5qDIUyZaiUiUvINy11LORdWX5TKewUntFEDVPGV7dbXUoUMlexOYU+K6Z7Doo2IiBU5iRORJn6yw3rXYXljvlCgU5iBKw7hUKb87mHj8tJaFm628Rfze+lillrzurvcIb2xLWDmPuPiTPGCgzl0KrILx7Lldw+aPi9vhmrCR9ut9x0xbCtkhRpTNUovkhb/Ypm+3fBL9Ytd+OBCwC/VWOTqViZZera8KE06VsIcgh4h8TKbsPui8ZGt5k0qMYM6MZLbsuUtDWsb1VyPalZdOgEqY8ERsc2dBk/xiW2JqCAvt7kT0lBXHtf+ynrre9fCnAdTiOPb0Y6eAtt+0Hr7WaGVzQcMCQsnoksXU5o7IT7TamoKtCioKdeWpHDVVCydcBIRSQbt7oFlz0VzgbP/bQ98tuqVk6B5XYu1rHXXI58ITrBtG6gc+Cng7hQ8xra2rsW60CphyCgQEQXH27/poUaZ9VCB1BL57QutLRoEAGiVBnQuey2W2RyUp1OI6fJDCC+mmt7Obu6UAfiZwlRzr1Rzc6cCoD4QEAIRkSTr7QJ0SWepufK/fjJVtToWAAC0KCcyDD+atB5WPdrIFYWdKJTWnzf8+6KYjx4KAACoHQSEjWjNnsC2e5o7EbWTm2LplNLciQAAgDo6cs50z7nmTgQAAFzLsKgMAAAAAACAn0JACAAAAAAA4KcQEAIAAAAAAPgpBIQAAAAAAAB+CgEhAAAAAACAn0JACAAAAAAA4KcQEAIAAAAAAPgpBIQAAAAAAAB+CgEhAAAAAACAn0JACAAAAAAA4KcQEAIAAAAAAPgpBIQAAAAAAAB+CgEhAAAAAACAn0JACAAAAAAA4KcQEAIAAAAAAPgpBIQAAAAAAAB+CgEhAAAAAACAn0JACAAAAAAA4KcQEAIAAAAAAPgpBIQAAAAAAAB+SmruBAAAALRo10eoT3Z39g7RLBJv7rSADxQrbF+u+NZx44E8sbnT4i8Y0bAotUewFiijErUe+U52MF/cn4to4pqHjxAAAKBKj3V1/rabXWDNnQ7wnUCZj4lRR0arzxwwf3Nebu7ktH6M0eNd7H1CtQy7kOdAXWo9ugTpwyLVzZn6F2cNzZ0WaBAEhAAAAN5dH6H+tptd5fTqL6avzxmKlOZOEPhCuIHf39n5q86Ov11nO5AnninG9JnGNSxS7ROq/eec8ccMNDtbFUaU3MZ5Y7xyuEBEf/s1DTXzGmOWKMmiRZl4pImbRG4WORHZNGbXWLadZTrYhVLRpjZ3KgEAWoUnuzsERq/+YvrwJO5/tx65TvbKEaNV5Hd1cD7T0/7gTktzp6iV6xGsZdgFRIOtDydadtEwJELrH6YiILymoXJeG4Jk3jdM6x2ixVn08ldKVFaiklNnRGSV9QCJBoRzIuJEaWXCoXzxYL5YpGBgBgBA/fUK0Yno63OIBluhd04Y7urgHBKBe6iNLtjAC5xokLROnFOOg4UaMTX02oaAsKWLMfMxMUqvEI0xSikR16XLZ0uETJtg1zy3NIkUY9bbB+hdgrUpCcrkeOVQvrgpU8qwYTAM+B6W2WgkWO6iRbFKnIgwUrRVyrILRBSEKYQA4PcQELZcVolPjlcHhKt2lW3JlPbkStVPxbZrlFIipJQIGzOkcAMfFKEOjlD7hGr7cqU1aVKZiptz4DNYZqPxYLkLAAAAaEoICFuoLsHaTUmKUaDNGdKmTLlyf2D1cp1sTZq8KUseE60Oi1K7B2uLzssnitDhAD6AZTYaFZa7AAAAgKaEpkaLw4gmxSp3d3AWONibxw1r0+ocDV5hU2n1JenNY4YChd3d0TkxFnMKwQcuL7Nx1PThSUSDvle+3MWXZwxGkZ7paW/u5AAAAEArh4CwZREYzW6jjI5R9+SI758yZNt98AFl2YX3Txj25ohjYtTZbRQM84MGwjIbTeCdEwYiwnIXAAAA0NgwZLQFYUTJbZT+YeqWTGlNmve5QwaBhkaqE+OUniF6glUPlomIChVKLRUO54s/pEs7siWn7rmXytmSC4Zchzo5ThEZX3TegGVAoN6wzEYTwHIXAAA+I0QMvvW+fvnLP1l13ElEJEQNu29uH4PNyUQqubBr5fojeeHD7hmrLF20J69SG8rzWJf3teucabaskwe2bz+Z5/UXkQW16x9deOCU90OKbcY/2D3lo7Wn6zsMDMB3EBC2IBNjlYFh6rp02euzeqLN+hNdHTMS1YBKizqGGyjcoPUJ1W5v7yxW2YqL0r+OGbMq9S5uzpQkgcbHKLlOdX06PnoAAABo/YTwrh3E9PyYrm1NJ07ayxtReu6+rxftyRMihsycO6bzmSW5dTje5X11ZozoPvGG2VP5VytOlVW+086C2g3slPrTqTwfXQZAo0FU0FJ0CdZGx6p7csTK0aBRpMe72O/r5DSLxIkO54vr0qWdOVJKsZDvJCIKNVDbQH1opDoxVukZot/WTpmZqH582vDOCaPD/cbThnQp2MDHxSgXS4UTRRgwDAAAAK2bEN6ps3Zs9d6Q5O7tTKeO2VxDNzUvJb2sW0gAqwgIxfBe0yb1j2IqZ7Yj65buyqqmx5A7co7+sLPdQ306B54+WBzQZeLkAfFGySCUndyy+scL5v4DOwZEJd4yt0/B8fVrUqLGu76bUkpE3NpubPLgpBCTmrpj+cZjBVb3I6SUCh6JyTa2GThxbJdgmbGSc9tWbjtTFlb71AJUDQFhi2CV+E1JyqUy4btUzyFiUSb94yG2PqEaJ1qZKr961HiuxDOQy3ZQtkPcmyO+eczYPkD/XXfH1ATl8a6OEVHqg7vMHl2FKy5ICWZ9bpLz9WNGPIsCAAAAWjMhqlNH5fR3WReCL4zs09F0/LBLRMiM0Z3bWAoOFFe8JMT27CcfXPjxURsXDAahxviKO7OzCgLDQhgVlZ3fvPSkXeVCQPfkGwfEX9i8f+/pAb1Tv159UiMi0ebxbjqRHG7NXPD1DyXWnlPnjumSsvSkxxG2kntijO1Gjgk68s1XZ0rJ0nXi7BFJqYeS6pRagCogIGwRJserRoEWpsiq7hahdQvWPh9aFmPm50uEx/aaf86v+bkRZ0uEX+8xX3fK8PYgW98wbcWY0ru3W467PHBC5Wzhefnxrs7JccqSC1gXBAAAAFotIap7B/vxFQW6Wnzs4tgB7c1HfikjIiFy4G33XMfJkXt6w5qTdh5RvjXPT8sKHzJ5QuDpM2dOn8up7UkYEZOCu40Y3jtC1jQxJKQ0VKY01w0qvZtOpKWdOF6kExWfOJE1ok2keNbhvg0/65YYITGpTUhcSPLsAUQkGoSSQGP9UgvgCQFh84sx8wHh6uYMyWNN0SiT/tnQshgz35sjPrTLkuusQ2/ewXzxxh+t7w+2DY1Uvxxmm77JmmG7unumTdieJY6IUrdn65k2DBwFAGg6se3LfoiUB+yW7dW+svU6bdsB6z0pAiciQXthfOm9ouG27007dCJBe3qUM2WHeVt82ZaeeoadmMgdxfIr+43rbE037qN9l9IPZNPUI2L9FsONbV+2pZeW57z8pz3dPP6gVPvFqhp4dvAbYkyXLsGR0pz7BxNx0WQK6mg9eqiMSM/e+5XLEjIVbSFeemrtZ1lx7ZKSek2+pcfur787Zat2GT5miIwKKU7N50Jo7zF9HVu+WpjmYDFjb7ueuS3qXv27lw9VaRtyT8zCn0nPOrhqwaESlyTVKbUAVUAw0PzGxCgOlTZlug0WNYn08RBbrJnvzJbmba1bNFiuwMnu3G7ZlSNFm/UPBpcZ3TsXN2VKDp3GROOXFACgJSopFGIT1HhGRGSOdI5UhfMVb0mB6nCntMVBROTINE5YFzD8+4C3nOrfumumJkzhpfPmx88IDVkh0ZFhGrUmcPCawMFrAkfVJRr0ydnBL4jxnToU7/jPO5/8+51P/v3uJ8uPhHTubK2mScXMQUGs+NKJQ7u2HCuNiAhgQmSfEb3jvPefCKaIbhOGxJ4/dLKYk0E22IqKnJzkyI7tggQiIk1VDQYjIyJv7xKJcV26BgkkBHbpEpWZli15buORGGvWhbTQHn3jjIyIpIDISKvgmVrfZh74D/QQNrMgmfcK0bZkSh5Pn3+si71PqHa+RPjVbrPK61nDFZ1+tdu8fHRp3zDtkc6O148Zr7xVprI9OfLwKGXVJV6M59UDALQwSqG8yqJODzC8V8xHJOqHLkqdOlx+q22MVpJhyCaKvrK1znZmC5Y43UJkJyJRn93Lfl8ElxgvzjO+8LN8VKXAKMc73dUIgUwCHThlfv684CCKj3O81l0J1ogEtu2w5W9ZjBm0e6+z3xHCiejURdOzx6Qc4l27lb4XLO3U9SgDj9GkP+817lcpPsn2lmyaekTo6O1dZlQf7++YZaFsm7DfqQ8pNs88XmP85v1EXg9V/dm95gD4ITGuW/uyU0sqpghqaScvBA/tGPBzWlU7sOCOY6f2DBK5QPaULWtzuaF7545RRTvcNhIiB952Tx+NSC/LPLFrybaTZZwo65d9xZOn35xY7HTai4p1ItKzTx2VJt95+3XZh1cvr/QuESk5pdHjbnkg1Kymbl92oqww0HMb98Tk2Eo2fRc6btIt90icyJG+a+26rPZuqcUkQqgnBITNrG+YxhjtzXH7IKLN+n2dnJzosb3mfG99g12CtVuSlGFRaoKFE1FqGduWJS9IkU4UeU4yzHOwx/eal44uvb+T87/nZNcFZnbniCOilevCtK2ZKAYAAC0MF1ak0tuJ+kenteRg8atT7PcdOBER08fG0I/7mVvTT9QnROs7U6UCIiK6rpttts00d71YSrxfz7JXOgkzj4m2fMNjW4xFOgkG9eWR9hmZlkUObVYXZe8+62sFjBgPFBkRDeluu1UxzflBypW1Z4eXPV8Y8GQaEbFoI/tiq+Wkzsf1L30iUb7rnOsIIy/vDutmn1hkvmGHWCqrfx5dJhZ7uURjtH3DZEf5/0+eMt9/RqjXobzs0sdbDiAk9EPaxe8/W+Dyt3puwyfniIi2f7LAbUM9q+KVA0s/PXD1daltNDty8LzmtuW/395e+VR64dGVC4+6v5a+ffFnFZvmeb57Yf0HF9w3r3wE98QQ2S7uW/npvmo2AKgXRALNrHeIllIieowIfaKrwyzSylS58ioyBoH+1Nt+azun6+jzzkG8c5Djrg6Or84Z/nrIpLjfIfopT1xzSZ4arzze1fn8wavjiXId7GKp0DsEASE0Dd41yf6XLmoCY8QoK8f42/3yOZ9PdhCU925QV64yr67qPinTp3bSzpyST9R4akl9dZxthEAkUIRMhQ5SiJRc06w9clYtE1P7cwF4k35JzhjunGzXkzKN+/TL4YxgVsdw8bnSy9sYo+0bJ9stRhLyDbdeEnQiErQx0VqSbv+0vANR5NYCLhHpRvXh7spQC3fqFG3iJVZOduFALvv7dXbDJWl3lrS1kEjQh4bT+gNiDidyigtThS+iNDFNJOIXs+WzOhGxM8Us2sLdf5wqvSvo14fT+n1CCREp4rIMoa+3C3Rkmsa5zJwk4vU6VOVdvOcAAkKoOzVlw6KU5k4EQGNDJNCcTCLFWvQf0t1mDxoEmp6ocqJXjxo9tjcI9OWwsiGR3n/UREZ3tnd2DNTv3G7xiAlfPWqcEq8kJyp/cQ8XTxaJY2MUk0h2zMOARiYGOf/Rgy/YEvi/EiKBdwjRi5olHUyf3FlZf1Y+UWPbUJV+930gEUmhjtWD+B/XmXbVNa6r/bkAvOEOaVmx48Vu7IttoloRzkTHqOYs4/mK0ujINI3dLSsG7TdDy/7VVZx2RLITE0hYf9j6J7c1B/Vb+tg7p1lvOic4mf7AiLJ4IiK2/ZB1ZrA6NEKdNcD+4HnrbWeJvM8hYCq/fEqdE/Pcpvp366Qeh6q8i9ccAAAA77CoTHNqa9UYkcdzBYdFqoESP5wvVn7e4J/72KqKBq8YGqm+0Mvu8eKZYuFogRAo86ERbrufKWGMqG0AwkFodEzmYTq7VF42dXYmT8zlRILy3vTSf/W2fTDYtnBM2fwEvfzuSGSk8/3RpevG1UilJQAAIABJREFUlWwYW/Z0zOW+CK8vRkU7PhhTsmF86dpxpb+rWDV8QGfb4rEl2yeXvpKge/RjjOxmHyZrjw8tXTjMMVriifH2/40v2TSxZONI25yg2l5L5ZTIQc4FE8tusXIi6t2t9MeBSjTzOFdDMxD8EttwwvjeUePCq7dP9JHRfFuG52Q8zSm+9ZPBkeScZSbShU2ZNKmj0kEkIpIMeq8AzhgFSiy1SHASyQHqpJDy/XhiAC8slFacMf3tnNg5RJN0YUcOjU/SQxkxg3Zzgr4vS6zPL4Qu7M6j8Yl6ABEzaMkxes0PTfLhobzmQL0TAADQ2qGR0pyiTJyIMtwf/DAhTiGiH9I9P5ouwdotbWu1Btvt7Z3/PWc4WeR22HXpco8Qx4Q4dXPW1SOnl4lEFGnkx+uVfoDaU/Plfxfa3plQciBHOpwvrb4oHS2fOsR0Q57516kCGZU3RtlvyrV8TcpLvfQlOy3f25hsUd4Zbp+UZ14ren3R+Uo/9cAu66/yGRd4aHk7UdDaOCy3bRQp1L5soHPAJdNul2cQbzlm2t7OuX6HZYVKgsX53976+u0BnxZRm6Syhf2dhzcZahzeKZi9pGR1keF3J9Sv+jvPneR/iRP/uFXO5JTpci4AV8YY++Ypl+/cpadYHnN4eaWcvVD+uJCIqLx0M4M21iy9V+QlulEKja+ml/y5k7b0kLj/mOWVHvb3xzkEnUQurDliPlIiLD0uvdm79JNSwa6xS+XT8Bgf0d12TxBx4oIivvKT7CDaedT89XX2pRO4yNjJC+Y/pDFO9Rn0vO0X04aBtrUTKKdMOlAolGlejuJ61UquadYe722S2hzKg7ccqMdFAAD4BQSEzSnCpJeozGO4Zs8QnYh25nh+NLckKV6eWuONyGheW+dfD7ktP74zS3qym6NXqNvJ7BqVqizChGWpoPHp4hc7A74L1AaFq9fH2Rd2FJ/ZZF7tJNLFDZmCTkQOaX2hfXIYLWXqMLMWNlC7l4iIBXGKM5EpyMuL5iC1X6HhyXzGiUhn+TqRQKSLKy+KDiIqlI7JzlixyplD5jC1Z4H8cBER0YVUeVdPZaDJcMJWw3WYwr2khJyUet78YkTpfwaxD7ZatzprOAj4s/Szlk5nPV7z8spA97+1YuOMtRScYGuTYzha8Z2dftbS02XHHw8E/Hh5a2HpIcvSQ25HyM403ZrpcRb2vz3W/7m/xJ3ix3usH7tvdvyYdVrFHxdOWScSEdHZE5f/4/VdUqT3dwS8zokk7cnh6i9nBI9fGm/5QFm1PlQNZ/eWA9Bc8h2sU5DOGHFMqG6NQgw8pdKgNri2ICBsTmaRSio1VRMtOhGlFHtWreFRdehlGB7pOcbnXCkjogSLZ+xXqjFz/YfyANRNXrG4tlhce17KH1t2YwRfnUZEJFYUdlkgImLE9ULjI9vc1m6xBnl90etJmLOimOu6t4f/XtmuXpfgNXlERCLvFsgLFIo2cUYMzR5oDIWp5impzZ2I2hEsyvxBjk5EJpnOXjA9m9siDgXN4kCeOCRSTU50LrtgwHdjKzM2Ro0x6asuyTVvCi0YAsLmZBK5U/dslAbKnIgKKj0bMM5Sh2/ReKtn4FfgFIgoSPY8iF0jEwJCaHyiVZ1sETblCKWcjFath5GllvfFCdrMRH3FaYEHKskh4tqDZCN5b2/HQ5HS/GymEcWFalqBmJ3r/cV9vZx3hkpv5zPOeLjEcmsx28muUaBMpFJZnnS4l3NWgPx5CbVJVAaXSR94Tr/1wuYtJZmchvSwTS8wT/tJe3uwbXahZXGZ27kA/I1eKj/5o2/aiD48FDSL/XnS5kz9xnhlSISWZcd0ztYjzMhjTPrBfHFHNgKKaxs+v2tGnW6q4Q4ctDiMD+xk+8MAXdAZ48Kuk6a3cln5CM8zRsfCcVqExLYcNn9jI53kZ/bof+5V+qNEKqPCAuMf9omZNu8vPrtff7Fv2SaBHETrDlpfzaspGbq45DyfP6L0DkV8bZvx2UP6K9eX3i1w5hBf31/zBEIi0r2lhMfa/p+9Ow2P4krzRP+eiMhV+76hBYlFCMwqCTC7JMDG2GAbA8Yu27hsV5W3mp6u63memh5Pd83Mvf3M7erb7eppt10uyrvBGGyD2XcjVrObRRIgtC+pNSXlHhHnfsAYtIFAKSKX/+9LuRJlxKtUvpn5zxPnnP8nRvrPB6VGWfpdmf3TKe4fD+lLu53LuGtAU4ABAALQR+X681ZhYpQShTHCAFLRJWyp1R22SPij+jsEQi05FRaq6zmU1+lh0QYeqeNNrm7fotXb2cjwgXZcna3nFaeRepWIOnoNPBpFsmK+Eww9pUv394d1f9/Hv7DDl0x/d6HbTc3Nhtf39dx2pc8bLRbDr/beeqPu1c03RhJU6Xfber/EsaMXQwp+3vm31vh07R0ql9sMC3bcqZI609y6n/6zqsI8u6KvcwEABLGTLdLJFnzsBPBFmAOqJYdCob1eG6vtAhFlhPUMigctd3HBzEFLz8tAh4dwIqruFRRDRO7ArhMAAAAAAEEJgVBLzU4hVOI9pvD92CYS0YO99htcWyEpAxsgVDitrdT3uPHBeJmIfmzvdjKTRCESb3biaQAaUXWvbjZtxTK3AAAAABpBEtBSo4sRUaKp28fh6zsQLkjqOd+otEP87FrPmNenj6/qL3f0/MsuTJaJaGf37Q0TjQoRYYY3AAAAAEBwQiDUUmWXyImGh3YLhIebpE6ZjY1UM0N7jpv84ZzxkOUO198XW6T/+WPPeVYjwtQxEUqnhx3tvgxUVhjnRJU2LDMKAAAAABCMEAi15FSozi5kR3Sbw+dW6dsqHSP6XY6rx897VHr+sPmjq/o+rx1VOP31iv75QyaZ9xzx+91YJxF9U63zdM+Yo8KUGrvgxBxCuBv1DkZEKSYsKjaEIvWciDpljN5rDM/2AIYuAwC4DoFQYz+2CWkhakz3VZj/tURvl9miYZ6JUT2zmkelt88aH9oT+pcr+lKraJOZTWalVvGDy/qFe0L//pyxdxqcEiM/lCzbZPZOSbcrTmMMPDVUvT5lEWDgTrRIRPSrUT2/sAAvenq4m27MKAYN4dkewNBlAADXYf1fjZ1ukxamyPmx8ra6m4uIWpzCB1f0b2a7/pTvWLI/pNXVM+OVdQh/OGccyPGjDfxf85yM6P3Lekv3xWOmxiqc0xm8F8Jd+pdLhgVJnuey3CqnP5UYWtz4ft2bIvX86eHuvx3jUjn9f5d6Xv4N9xme7QEJXQYAcCsEQo11eNiP7eLUWHm/Ree4ZWHRfys1zIqXJ0Ur7051PHOwj6tAB0In0LtT7alm9WSL9O+l3d7zzBLPj/WcbRU7e+1MCHB7VzqF/3LK9I+THatHuFePwC6WQ0Ll9MeLhuPN+L5GY3i2BzB02f3EiGbEy2MjlDAdLsAOHG1udqZNxPaSAQCXjGpvX4NkEGluQrd9JlwKvXLUVOdg02LltbPssYa7fgGN0vOPZ9inxSqNDuE3x43u7rMH5yXKBoH2NaKH4V58Xa1bsi9kb4PU0XM1XBisLpkdbpJWHAz5t1IMXPgEPNsDD7rsPmOM3sx2vpjlSu+1Wh74tdHh6mujXM9n4ssyv4c8oL0Gh3CiRZoZL59sEW69qtPiFFYfMn84w54Xq3w91/bmD6bTrQP9InNKjPyvec5Us1rnYC8cNjU6uiX/RJM6I04+1ixasAMh3KuSDnH1YbPWVQDcD3i2AwzGjDh5QpTyyTXDvgZ87AwojGhpmvvRFM+P7eKpAX9GBR+EPOATttVJTplWZHgk1m0ksKRDfGxfyOlWMS1E/Xqu7d2pjt57UfSQFab+xzT7hjk/XSm6ZF9IqbVbi0qMr8hw22S2o35AuxoCAAAA3LOxEUqDU0AaDDyc6JtqfbNLmBIt3/mnwYehOX2CXWZfVupeGOF+LNWzsapbTrM4hRUHQ14b5Xp5pHtRimdRiudCu7CzXnfEIl2zsXa3QESRejUzlE+Pkxcke3IiVCKyyez9y/p/LzW4e+XHpalyopGvuWpwoHkBAABgiEXoeTsWZApQnFOzi0Xd/cwm8CkIhL6itEPcVy/NS5StHnlPfbe/i0uhf75k+PSa7s1s99JUz9hIdWyk62/G9L0MeqeHfV2te+eSoanX2qREVJQkT4mRdzfoLndgcNi3nHyc76hhO2r4EQtzY2dIgH6gUwAGD30EALdCIPQhu+p1oXoqSvToGb91F4rrLE7h784Y/+GccXqsMj/ZMz5KGWZWI3SciKweVmMXzrWJu+p0R5pFTz9Xlc5JkAsTPadbpb31+Lv7nPRQeiWbv5JN7S5+oIF21rIdNdSOzc8AukOnAAwe+ggAboVg4EM40TdVOoHT7ATZLNG31VLv3SY8Kn1vEb+33N3MXYnxpanylBj5RIv0dTWWfPZpkQZakk5L0rnC6UQz7aihHTWstF3rsgB8DDoFYPDQRwBACIS+RuW0oUrX7mGFSZ4Us7quUtdjgdB7kGhSV2S4E418d4Nub72ENOgvREZT42hqHL09iVd2ES7vAegTOgVg8NBHAMEMgdDncKLd9VK1TXgq3f1mtvuQRdrXKN3bAjBmic9NlGfGyTaZrblqwLxB/9Xn5T0A0AM6BWDw0EcAwQaB0EeVdgj/fMmwMNkzK96TH+s51qz7oVls7mudmD7FGXherJIf6zEIdKxZ2lGvw5qiRHR27jWtSxisny/vISKia/9SHrVFVssQ9cGr0CkAQ80vusyP+0iXs/g3j6S6nDIREbdf/PaLg9U9F1jQJY0Zo6/8sdLujUunmHni0iciij8/0KTevGlY/qK54+J1nJPSfnH3+mO1d/dRrI9jAgwNBELfZZfZ11X6Qxa1IFGeFe+ZHe+ptgulHeLVTtbgEJ29ruIwSZRoUrJC+agwJTVE5URnW8V9jRJ2nwcAAIDg4ind8cGm8v4veWWGpOwHzE3n7xQImSCQqt59aBSSpheNbt35yYY6NxfM8dHibVNdX2fhzsvf75A6kAZh6CEQ+jqLU1hbod9SyydGK+MjlcJET1EiEZFNZl0yu77NoF6gMImbJU5EnKjGLmyt1Z1pEzs92Panmwn7h9dWV2hdRd+afzGgd5t2F/18AU9IfAYRtXe0DG1lEHzQKQBDTdsuC8I+kpLmLC8Q9n+5r17ImLtitm37huZxuYnRugVPpTtrDm06VBM2pqgoL9XImNx8cs+uk02G3CceT2+3UGiIrexwc878tNZ6Cg0PDaOr+zcdrlOSc5cUjQrV6XRK08ktO89aegdPZg4xuuq7ZE5Eqt3STEQkRfV7Fntje3Jyy/qvz3RwEmIffH6e+9sNF9NmL7w+QqiLHltYmJtm5KrSenLb1tNtaq9DicOnP1I0wqwojDceXrfnslcGPiFYIBD6h04PO9goHWyUjCJlhCpxRh5nUE0iGUVORFY3q1RYs0uwOFilrY/BQ/B3fU7xD9G0JAAfhE4BGLwA6SPd6Pkvvi4TEcmNRz7fcv7wnopnCh8ceVyaE1ey6YDFxo+faEgyH1xf3KySED2tMKd97xfbWzy62Okr540v31hKQri5bfNne9pUFpY7LszY9u3afVZh2NzVU0aeqr/UdH7bJyecKumSHlw2Z/Tlry72Or9afebHqY8//dyomprqqis/llS0KdG5tzmLkDDn6VmjQs+e6GSxI4d7rn7Xxint+qGE2PyFecKxLz8ot6ui0cg4CT0PdW2rMzerceunB2tVJul19zCiCUENgdDPOBUqsYolVq3rgKHX1yLgGPIF6AmdAjB4AdhHntJda7pdMtp4bEfF088ukIu/3GdRu/16zDQsIy7aVPBEFhGRZNRVhROR2l5Rbf3pek21vbKmUyXibW2d5tAQxjxJkwty08OZqhojzNfCGXX0PD93VR36/D8uJKUPGzZ89Pzns09+uk2+3VnUptJrxoKssJPnjNnD3aXfdXAy3SgvJVV/rbjCrhKR4nQSsZCeBYe5qus8+YXz6dK18rJrtfiYCHcHgRDAt9x6iQ62CQboDzoFYPCCqo+YKSZa55aFUKPEyN19CI0x19U9G/ZW3VwRJiyOFPVmnFTpp3/inDGShs+aE3d147pzHapxzNLn4vtbq4G72uvK2uvKSlsNq6dkhpbe9iyq5XK5cc6IyHrzCNflDZ13mNnY81BElV+uvZyakZn54Kop1RvXHW3E3EMYOARCAJ9wteOnr2aPNZGMV3GAfqBTAAYvGPuIhY8pmE5HP/kmbPGCmelf7qvwyLKiM+iJiLijpsKelzv6ZO0lqyIYY2MM1ubbPiyC3sC7rDaVWGhWVqLQ2efPRA3P0luuNtpUpo+KiyRbWXt1hT33NmdRW8ou64pm5xrslzd28JtjmNxRU+WaND7jRF25TRVNJsHp6F1wmxJicFoqL1rqnTHP5sRI1Oj2yuMGwQGBEMAnTP3Wzy/OAbgv0CkAgxcUfaQbvfClN67v86CUb99YP3GKcvjrS61dbHvpU4/NTP90X2VlWUPugudeclfs+3L/8e0HC+c//vJUxkmxluz7urn9dsf2lB8vzSl8YkmHQ7Z62voZyxPDM+cUzYrQcWJKW8nenWXODnb7s6itJdf0v8yz7djf1e2YassPu47PL1z+q1mq7Gn5YevWM+0tPQr+5kdD/uIH0/VEgtJyZs8VpEG4KywiNknrGnpKSc0govZWf13JCnxTZHQMEfns2on3AJ0CQwGdAjDU/LHLBtNHb411EtH/vmD0bkngIwbz9/XHXghI2KEOAAAAAAAgSCEQAgAAAAAABCkEQgAAAAAAgCCFQAgAAAAAABCksMooAPgsIX7GL5+aoHc4Vc4Uh6Xs1KFDZa0erauCICakF768crRg96hERPK1HZ/uLPPRZ6SYvfg3OaXvbrys3PlnSYzMmlqQn51kJFmRne1VJ4qLL7TKXqiChYxf+uKiyPOffbyv+qdChPTCl+bbv15zpOl26/r3ccc+CTEjcxPaTly83SYBUlRW3py8MSkhpMhcdjRdPX3o+8ttA3lcwDvaXGxkuMoY8dvvrQf+KVLPK7owwuTfEAgBwJepLSe++PJ4q8oMsTkLHnlyEf9s02W79z9TCIKgqkGyGxcMDm85/VWfYYYJAqmqL3zgZYJAd/FsZiEj5q+apTu29YtvGh0qkyLSJ44K17FW+eff5Z5/NRY2enyspdo+YnxacfW1u4jOA74jix2RO6b8dP+BkIWMnP/0TOnYti82NThUEkxxI/OGRxtY2xC8jkA/TrWK0+Pkpanub6r0eNgDTEGinGhUt9TqtC4EBgWBEAD8AXc1X9x1ZPivJowKu3Kmg0xpeQsKRkfoGOu6Vvxd8dXOXrfYU4t+Nd1wtUsIM4QaOs5s3XupjSJyChbPHiY62msaWQY79eFOXvDKVOmKzRAtNRw60D52QW6KQdIL9rLvt+6rsAlpRS9P4WU8cUS00Vaye3/bqLmTU6Ok1iNbNp28/Z7FEETE7MWv5rnPdhijTe6K3TvP8TELHpoQaxBEiVsvHdxZXGXnJGYv/s2kzpPOxBHxobqO87v2tGTOy8uICRUaj2/+9myzTMRC0h6cNzMnSiKBd1wu3nr0Wpdp/IrlcUc+2lNJSQXPrxx9Ze17B+vZsMKX85o++eacI3xUQdH0EWEicVvlD7t3X2zx9KzkxxsVCpEjC5fmsuPbdl/sEA2i4vZ0j3ZC1Pj8TMvRv55qdHAi4rK14sQPffxqZ1pMd1ekjQsxY8aElxd/0ZT7zJhMY0Wpc6BhoK87MvPEJasST67ZXq0S6XIWvzTi4vvblQdnpBnC4554Zrxc98PmA20ZPR8WIWpC7vDGo3891eDgRESqo6n0+6afTtP7Ye9UxezFr+Y5z7QZo82mMGPbD5v2lraj3QfpZKt0oFF9NMUzPVaxOINgC8SgEW3giUb1TJt4uAmBwr/h7wcAfoK7myztYdGRjFwZs+eFn1//2VUbmbMXPDkrvWqP0POWHSqJYUr5t1svu/RZhSvnja7cwWfPNp75/OMLXabRj60adX3bXilcLd+0aZeLk2hs/rrMKXMhNGfpo7kpVQfqiXQxhrovvtjrGbbgmUeLSjau/Xy3LmfJsxNTz+yuxPVmwYpFT3ri1RyViOSKvX/ZU0HEoqXGjZu/t3EiYrqrB7686PBwEqNzVz6Sl/zZgVqViIT48M6P1n9i1Y967Lkli0u/W7f2gCNiyqrl+VmXtpZ6Qh8omB116Zu/XOlShfAJjywryKrfdLWmyjExPVaollNTXA2OpNQooVGXlmKvOe2g8ElF8+KuffWXUy1q5LjHlz2Ub/niUDN1r0SMJSIyJE6evzjTsuubo5UObhzz2OvjKt7/6kzHrcFMiEuKstY2uPoKa7cckIWOv6siOZEQP3aUvmR3dXu7uX7qmNHmsrO2gSXCAd/RXXn4UNUD48o3bij1EAuf8kSvh6U9LjHaWtfnb8f6etgve4hYuFi/YctBO4ua9tTjecmXd9UgEQ7aR+X681ZhYpQShTHCAFLRJWyp1R22SPij+jsEQgDwL4yExPS0yOTIpU/mEpGoF7rCzImxPW4xMispDdcqnJzIVVXZPD8tPoHHNV3d0aES2cpLamdlEhGR0lBZ5eJExKSIMbNmjo/VKYoYGWmL0lE9kVx/5apNJdbU2NYlVzS6OPc0t8gjwvSMHHj/C1K89fSt899EIrX22rWfA4sUPWbe1FFxei6rhpiwrhgDq3UQkVp7ubRdJXI1NVqdzqtVNk7U0djoGRFuZMRTRqSGxZgeeXoSEZFk4K6wEKa2VdWJc4eFh8rD+OWjpRmT0sxluhSxprhd1Y3MSGg8/12Lh4jaS87WzMpLNh9udvSohIjF5z2xpOvHjd+cbZKJiNxVxeuanQMMZUTU7YDSXRZJJCXnjFFLNjSqXC3/sXpW/qiwc6c7BnLye7yjLqmPh6Wd6Od7CvHTly6aEKHT09XNH+29Jvb1G1E7kdpQUWnnRLyjuV2fEirS3VyAC/062SKdbMHHTgBfhM4EAD/B9HHxkZ01bZwiSbWc2bL2XNeNT3pC2rwet5CYRsTE69PcGev3GiWuKCoRkRA1ft4k1/efratzscSCZ6YxgRERKdcnFnKu8p+mGHJVvc3hICip8o0BYyF55sJxrp1fflzr5OLwR345Wbyx0oJ6/YlGqqLe+E9SVZUEgYgRUdPJLRtOdc9qjVV1ERMyR3pM1SerK/QPTs3M1IXXnWpSe68P/vPdblZCRMS7LHVickZq5MWmZg8Rqbbmalvv6psaWiNSEg2srY9vOW4e8G6LJH16zsiwCFqxehwRkWg0RY+JOXtsAFdb93NHzjlj9FPvMWEAS1hwIlKbG9sjkq//dqrlyMYPj0bkPrciVmT9/UYiEf3c7ZxzxrBYBgAEOrzOAYA/EIyxY+ZPT6o8V9bJuaWqLmrspGQDIyIpNC4uhHrdwohIShmVHS6QEJ49Ot5SZ2msa4rLGhEukBCSmZ3S89swvU7v6Ohwc9LFjRgejpdGuDd6vc7e1u7ixExpo4YbBvbVgaf2am3spNxUs0BEpAtLjA9hRCQ3VDckTJka01jVLFtqGuNypyRZqmoVIk99RWPC2DFRIpEYMWbCsI6qur5XSLFXfr9ub9PYRx6bmqBjREJY8qhhkT3XflDbzp6oSJhWNDnBJBARkyIycvOGm3qWfpdFMuPw8Rlt+z55/9/+8ud/+8uf/+2Dr07ps8fFdessXcL4wkkpxu5n6veO3N3RSbExoYyImdIyE64fintkRW8wMOrnYVFbz56oTPr5tyOSDHqR3e436lOfpQIABAiMEAKALxPi8p5ZPUEhUu2NpUc3FpfZOZGzfP/mqMKFT6+WOJGr/uj2HU29bmklclts8YWrXok0emoPfVNqt1HxwbRFz76Q52irbmhxKMqtX4mplgsnOh96bEVqp9vt7OjEFWJwT9Tq40fHLnrsyYx2p+J0NQ9wERXedW7XFvO82c89r1dVRq7GE7u3WWycu2qq2kIy7NV1Cin11S2mceaaWhcnoo7Te/ZFFz32ykSRMXvF4e3Hm9XrQ1u9D+2sOfLljrwnH35ct/PbkxH5j42reP+rM55udXHb5Z1f8KlzC56eHiISV7oaSw4Xu3uWfndFMnNWTlpz6Z6fx+zVhktX2JKclOLG2htHZOak7DEJJ4u7nek2d6yuPHEo56Glz6a3dTnaPR1cICLitZfOC4XLXxrvqjzy1e4+HhbqKtvxmTp1XsHT00NEVVE89qYrB49Wq/39Rn3+hfosFQAgULCI2CSta+gpJTWDiNpbW7QuBAJKZHQMEdVWV2hdiNegU25LTCt6Jafi/e1XbrmETtSJqkfhzJi+cNnE+q83DXSJi6CCToH7gxnHPvxo+LENR1p8/vsXr5fqj12GPoKh4I+9EJAwQggAwUKIy3usMNskSJJSd3LHBaRBAA1x54Wt67UuYmD8qFQAgHuAQAgAAUmp2v1uVfeb1IbDX392WJtyAAAAAHwSVk4AAAAAAAAIUgiEAAAAAAAAQQqBEAAAAAAAIEghEAIAAAAAAAQpLCoDAIMhJM99ZUbHF1+dsnIWMu6JVx/s3PCXneUKCclzXp7RtW5D2YjHFxv2rTvUemO5dmaeuPSJiOLPDzQNwVrzzJQyac68B4aFC4osu9uqTuwpLm1V7ny/vg41sDqZKWXS3IIHUsJEUt2tV08e2F/iGHtPvyCLyF01n3+34aQVq58GJV3suKJ5+ZnhAiem2mqO7Nhxts139mMQ0gtfmm//es0RL/atGJk1tSA/O8lIsiI726tOFBdfaOXZi3+TU/ruxst37Ftx5MJXJlSt+eqSy2sVAQAEJwRCABgMtbmuIXJUku6U1S0mJhhbunQp0UJ5Ew9PTCTLwY7e2YY7L3+/Q+oY5KdKJgikqj2OLsROemxpZtXmr3ZW2VQmRWROGhmjZ62OoQtYQsykR5cbddtfAAAgAElEQVRmVW9av6ParoohKRNGhuuZY8hOB4FLiMlbMDP0x3Xv/dgmk2CMTggb4Kb2/eizQ3wJCxkxf9Us3bGtX3zT6FCZFJE+cVS4jrW6B3wEtfroxha3ZwhrBAAIEgiEADAonoba9pmpcUJJfVRydMupS8aRiSbW5ElKimgoa1bJQCRG58x/Jj0lUt9xZse3h+t1I2cvjCj+/ECzYfj0R4pGmBWF8cbD6/Y25Dz+xPBOi6I3mEPp2sHth2udYtSYoqK8VCNjcvPJPbtONhlyn3g8vd1CoSG2sp07LnV2+7wrJE2aYDj33bEqm0pEXLZe/eEEERExfcLERYWTEvWkWMv27DxUbqPetxiT85YUjQuX7U21HVFxjRs3Xvr5wFKPMizuW85oPP/dsWq7SkSKrfbUGSJmvnG/Xud1xMxcMdexecPJLi5E5T9bqHy74ZQzKW9J0QORSldTTaeeGof87wU+yhhiVLo6u2QiItXZWu8kYiHjVyyPO/LRnkpKKnh+5egra987WM+GFb6c1/TJN+eNOQsemhBrEESJWy8d3FlcZeckZi9+Nc99tsMYbXJX7N75Y+yi30zqPOlMHBEfqus4v2tPS+a8vIyYUKHx+OZvzzbLTJc8aeHCcdFM4QK1n9q25VTrwL+pEWLG9lOA80ybMdpsCjO2/bBpb2m7SmJUzkMLp6WKjs72yibjJNPZ//i2PGJ8fqbl6F9PNTo4EXHZWnHiByIikYgMyblLJ42KDzN6Kr//em9pu9rnuYTUaU9MqFrz1SW5z5MCAMBAIRD6CGbIWfbSqJIPvvkRF7+Af+FddQ1KdmK40J6U6Kk/V2seNz5BuuAaFtde+72HyEBCVIyy+/PPdwqZD62eMvLUlorr92PGrNysxq2fHqxVmaTXqdxAQri5dfOnJ1p51JSnH869+uXFjMKc9r1fbG/x6GKnr5w3vnxjKQnh5rbNn+3p41o6ZoqJMTT18YlWiJ1WNN72/efvVcuxuU88OTPzr7s6pva8pSt/3sjGnZ+ua+CJ05c/K9wSzITo3B5lbDhx/fTMFBPb5xn7Pa+118/ETSvIbtnz6fo6NXnG06sEBMJgpTacOdW0YtGLL9ZX1zY2VFy+dLnJoTpqqhwT02OFajk1xdXgSEqNEhp1aSn2mtMOzt1XD3x50eHhJEbnrnwkL/mzA7UqEbFoqXHj5u9tnIjEWBLiwzs/Wv+JVT/qseeWLC79bt3aA46IKauW52dd2lqqZuTlsuMffXLBxUnQG9hdpSje0U8B4WL9hi0H7Sxq2lOP5yVf3lUbNqlwhvHs2vcvdbLIiU+tEh1EJMQlRVlrG1x9jWEK8RGOjzd80kaJc55+JC/58q6a/s71s14nrUEiBAAYMATCoSIkFz6/NOLwmq9Lf77uR4jJe/qFjIt//up07+vouNxw5qCz5Z4vfhFHPf7rGW1ffbS/0Wvvgsz0wIrVWRf+gowKt6da6i0R2YnmtkSD5Wxni7k1Kjk20pWo1J+3cSIitfXqZYubc9ZY35YbGsJ+uht3NdV58gvn06Vr5WXXaq1kILWtorJdISJrZQWfMyyqMyMu2lTwRBYRkWTUVYUTkdpeUW2947NcTJ/7wtxMo165tPWTfe3JyWLFwVonJ2ouKbM+nhwXEtrrlo5kVnXA4iYiy+XylmE3D8VMw3qX0XbLv/dXAzP1PG+s0DMQMlNSErv2fb2Lc6ovvdKSNIDHGwKT0nTmm3dLo4elpCQPGzHvqSmjd32++XJ7VZ04d1h4qDyMXz5amjEpzVymSxFrittVIkP0mHlTR8XpuawaYsK6Ygys1kFEau21a7abbzFq7eXSdpXI1dRodTqvVtk4UUdjo2dEuJFRV3O1JWHGwwVR12qqKsur2++uYqmfAhoqKu2ciHc0t+tTQkXSJabH1l+80qkSkbXkYt2Dw+9wYLW27FKbQkRNdc368aEikdzPuW7epedJCYEQAGDAEAiHitpwodS2akyWuezCT+/NQkxOdlTN6bLOPmd1KK2Xz7Xe1woBvERuqGuZNWxsSlR7TYuqdtV7JmUMV8ItF5rV63FJVa9/NuMqZ7fEJ7Xx0JdrL6dmZGY+uGpK9cYvLxCJgnj935gkMBdjzHV1z4a9VT9/tGNhcaSo/Sw2wR0tLa6JCdFCWZOqVO7/y8dHxy95NlkgImLUret4X7f0r1cZt5yx2TUpMUYos/T96bPXWTjn9NNjINx4LG48PKQq97b8DQQMxdFaeaW18sqFK85nnxs9TLpc2lhVFzEhc6THVH2yukL/4NTMTF143akmlYSUmQvHuXZ++XGtk4vDH/nlZPHGouGq3O15pCrqjf+98Z+kqioJApHadurbj8oT09OGpc16fEbLvs92VPQ5ZNcXIbm/AviNhuecM/bTrT0PqzY1tEakJBpYWx9zfG8UylVVZUy4zbl+1udJAQBgQPCqOWRUS0lJW/KY0TcGRIS47JzQqvNX7JxYSNr0Zb/49d++/sZvf7F0VnqIQMQMOU+9tvQBAxExY+KER5b/8m9ee+NvX1n9dH6KRETEDAnjH1n+0t+89uZ//uWKh8ZE3ybJs5DxT7/65LzJC59e+eyvfvniMzMzrpfAQsY//dqThVMfXrV81UsvPL9yRvr124WYqatfKhp+/anAzBMff/3J0ToSovMenpmqTyv8xcuvv/jM7GQ8U6Bf3N5QJ2dMyZLrLApxR73FOGFCQkt9g3z7u0mhkSa3pfLi0UMnq0yxMRKREDFiVJKBMUNidhZrqGmtrrBn5o6OEIlIMMbGRei63Z+FZuTPyAq/GTHV+tPnXOPnTE0PuZ4CDQYdIyLuqKtVho9NMTKSYrNHRTTWNdl639JQT2mj43WMdPEjM2Nuya3cUdNvGWr9mbOu8XOmXW9iMSRl8sTMm0Ogvc7brNg7bCHRESKREJaSGs2IO+rr+LCMCIFIiEhLjxnEXwH8mxCRPjItUs+IiMTw5DizvbNLIZIbqhsSpkyNaaxqli01jXG5U5IsVbUKEen1Ontbu4sTM6WNGm7od6T6dsTQ6DBmrb9y7oeDhyopIS6EEekSxhdOSjHe+XgDLsDTUNWSNHZEmEAkRmTnJEtERGrb2RMVCdOKJieYBCJiUkRGbt5wUz9H8cYvCwAA/cEI4dBR20rON+ePHRVx+lQ7J3FY9mjjtf1XnJyFPbB40Rjb3i/euWwLGVG48uGHOj/fePbGZZksZNSix/LZsU3/8ZXFpQtPiiKViJlGPvRYHjv8zb9famXxk5YuXjS95fOD/QxKEBFJKWn6L9eua3AbMhetKph69cO99SoRkZiarvvys/V1bl3i7GVLHmr9dOMlWz/Vt/6wrThzddaFT3DJKNyJ2lLbqJ+e2Fjn4ES8pb7VmKera7DffqiBGRLzFz+YricSlJYze664abzaZhEmrXhmYZhkPbtrS6PsbNp+sHD+4y9PZZwUa8m+r5tvvaaNRaaNyegoOXxLHc2nNm3ic+Y+9VKEqCiys/naoQMWTmrz0d0/PlL0zG/0TLaW7txR7lap9y3H9pcvXfjCr5TOxlprq8dzc5BFbTneo4wm680znv72W5pbsPylUIFzV3Pp8QNufvMfe56FU+nJkrFzl6/ssnV1uTuJSG06tv/aowuWP2WzuZzujsH/LcBfsZCU3MJZD5uZQkztrD6+6VidSkSumqq2kAx7dZ1CSn11i2mcuabWxYl49fGjYxc99mRGu1NxuprvaUlSJsVMWDhnpIlxEtSOkn3H2lRiYUnZYxJOFvdxPBYzadlr466/7yhVB9cdOep8eCAFcOvpPUcSFi5/Jddpa6tqanKLCifitss7v+BT5xY8PT1EJK50NZYcLnb3fRTVC78sAAD0i0XE+tyklZTUDCJqb23RupBBY2Hjn3xlXPVHa481C+kPv7CQ7f7r1go59IEnf5199c9fnbZyIhY2Zdnq0aVr1pamPfnSqJIPvi0f9cRvxlR8sP5k+823PGYe+/hvxlZ8sP6UlRORkD7vxUL7Nx8ea76ZCG+ZQ8hCxq98YdSlDzecsXEi3ZjFv5pQtWbdOTuFjF/5wpgrn3z5QwcnYuETn3op7fy/b77ojp76/ONh+9fsvqZe33vtxayL720o9QTaHMLI6Bgiqq2u0LoQrwmcTiEiIhaW+0T3HQvv8PMReY9Ms+7aWTbga9xuT5AkkmWVhOhJTywNPfThwfognYSETglmzDj24UfDj2040uLVp7+o06keDychdPSjT42rXr/xVFdwhzp/7DL0EQwFf+yFgIQRwqHEuy5frJyROzb2hyOhOSPVK99We4gEU4hZ7ez46d2Q2zs6ZHPIz9fJMLPZrHa0d59nyEJCQ6TYvKefn/jTDZIklxhue2qX66dPyaqqcOnGxCziTvtP8zW4w+ZgJrOJaOC7PgH4EG794bsd3jscM2XOW5YbL4p6oat0z46GIE2DEOS488LW9V4/qpg0deWcDImLeslVeWzn2SBPgwAAvgaBcEhx59XzlXPmZqc3hw13Xd5YrRARd9jsQmp4CKMOTsTM4eGSo/7nWfXcbrOz9IhQRtab75jcbrd76s9+8s052yDfRoXQ8DCBWlUiITQijBxXHUSkqIog3EikeoP+5+mCHG/acP/wzhMbvtDw9LayXR+VaXd+gMCl1BR/8lmx1lUAAEA/sFTI0OKu8ovluuyieeldF0uuz/njtoqympiJM0eES0yKGDE9N6b2UoXtZiC8duFa5JTCB+KNAgn6iGGJEQJxe/n58pjcopw4k0BMMIQnjkiPvKc/nRA3IW9UpMjE8JEzx0dWXql0cVK7mpp5UkaijogZkx4Ym/BTNuQep5OHRYbjOQIAAAAAEKAwQjjU3NUXy5SciZ1nL9yYksE7z3+3PeThWc/8dqFO7qg6s33HmQ5ON64A5bbSrZtMRXOWvDrLSJ6u+rM71jdYZVvZtk36ebMffWVOqKQ6O5oqjx8or7yHauSKCw3DH19dGK131p3dtrnExolIrireX7v0oedectq6LOXVDWr49R9Wqk6enPjoslfzyXZm80d7sM8vAAAAAECAwaIywYOFjF/5QvqZ9zZfusNuAAEq8CYuo1NgKKBTAIaaP3YZ+giGgj/2QkDC5YAAAAAAAABBCoEQAAAAAAAgSGEOYfDgtnNf/J9zWlcBAAAAAAA+AyOEAAAAAAAAQQqBEAAAAAAAIEghEAIAAAAAAAQpBEIAAAAAAIAghUAIAAAAAAAQpBAIAQAgYCWa+bPDOrSuAgAAwHdh2wkAAAhMGWG0sYjSQlvsClvTqnU1AAAAPgkjhAAAEIBGR9LmBTwtlC52GvY1h2hdDgAAgI/CCCEAAASaybG0toBHG6i4gd66nGhT8O0nAABA3/AeCQAAAWVWIm0s4tEG2lbNVu5lSIMAAAC3gbdJAAAIHItSaW0hD9XRunJa/T05Fa0LAgAA8G0IhAAAECBWZtGa2dwg0Psl7PVDTFa1LggAAMDnIRACAEAgeHMc/9ODXBLonfPs9z8Q17oeAAAAv4BFZQAAwL8xorcn0xtjSeH01nH2UZnWBQEAAPgPBEIAAPBjIqN/msp/MZLcCr12mL6u0LogAAAAv4JACAAA/kov0rsz+JJ0cii0ej/bXad1QQAAAP4GgRAAAPySWaIP5/KCJLK6adVedqxJ64IAAAD8EAIhAAD4n0gDfT6P8uPI4qTlu9n5Nq0LAgAA8E8IhAAA4GcSTLS+iHIieZWNlu2i8k6tCwIAAPBbCIQAAOBP0kJpQxEND+NlVlq2m9XZtS4IAADAnyEQAgCA3xgdSV8V8iQznWmhFXtYi0vrggAAAPwcAiEAAPiHybG0toBHG6i4gZ7dz7o8WhcEAADg/wStCwAAALizWYm0sYhHG2hbNVu5F2kQAADAOxAIAQDA1y1KpbWFPFRH68pp9ffkVLQuCAAAIFAgEAIAgE9bmUVrZnODQO+XsNcPMVnVuiAAAIAAgkAIAAC+681x/E8Pckmgd86z3/9AXOt6AAAAAgwWlQEAAF/EiN6eTG+MJYXTW8fZR2VaFwQAABCIEAgBAMDniIz+aSr/xUhyK/TaYfq6QuuCAAAAAhQCIQAA+Ba9SO/O4EvSyaHQ6v1sd53WBQEAAAQuBEIAAPAhZok+nMsLksjqplV72bEmrQsCAAAIaAiEAADgKyIN9Pk8yo8ji5OW72bn27QuCAAAINAhEAIAgE9IMNH6IsqJ5FU2WraLyju1LggAACAIIBACAID20kJpQxEND+NlVlq2m9XZtS4IAAAgOCAQAgCAxkZH0leFPMlMZ1poxR7W4tK6IAAAgKCBQAgAAFqaHEtrC3i0gYob6Nn9rMujdUEAAADBRNC6AAAACF6zEmljEY820LZqtnIv0iAAAMD9hkAIAADaWJRKawt5qI7WldPq78mpaF0QAABA8EEgBAAADazMojWzuUGg90vY64eYrGpdEAAAQFBCIAQAgPvtzXH8Tw9ySaB3zrPf/0Bc63oAAACCFhaVAQCA+4cRvT2Z3hhLCqe3jrOPyrQuCAAAILghEAIAwH0iMvqnqfwXI8mt0GuH6esKrQsCAAAIegiEAABwP+hFencGX5JODoVW72e767QuCAAAABAIAQDgPjBL9OFcXpBEVjet2suONWldEAAAABARAiEAAAy1SAN9Po/y48jipOW72fk2rQsCAACAGxAIAQBgCCWYaH0R5UTyKhst20XlnVoXBAAAALdAIAQAgKGSFkobimh4GC+z0rLdrM6udUEAAADQnS/uQ8hVlYiIMa0LgcDBGKOfn1qBAp0CXufdThkdSVsW8uFh/EwLPbpDszSITgGf4qfvR+gj8Do/7YWA5IuBUFFkIpJEUetCIHAIgkBEiqpoXYg3oVPA67zYKZNjafMCnmSm4gZauou1uAZ/yHuETgGf4qfvR+gj8Do/7YWA5IuB0OVyEZFOp9O6EAgckk5HRB63R+tCvAmdAl7nrU6ZlUgbi3i0gbZVs5V7WZemnYdOAZ/ip+9H6CPwOj/thYDki4HQYbcRkd5gxIUJ4C06nZ6InM6AmsCETgGv80qnLEqltYU8VEfrymn19+TU+stfdAr4FD99P0Ifgdf5aS8EJF8MhC6X0+1yMUEwGk1a1wKBQNLpJJ1OVVWnI6BedNAp4F1e6ZSVWbRmNjcI9H4Je/0Qk31gbgg6BXyH/74foY/Au/y3FwKSLwZCIrJaW4nIYDTh4gQYJMaY2RxCRF2dVjXgJi6jU8BbvNIpb47jf3qQSwK9c579/gfiXq1wMNAp4Av8/f0IfQTe4u+9EHhEozlM6xr6oCgKETcYTTq9XlFkPFfg3jDGQkLDRElyu13tbS1al+N96BTwisF3CiP675PprfGkcvq/jrN3Lni9xkFBp4DmAuD9CH0EXhEAvRB4fDQQEpHb5ZJ0kl5v0BsMnEiRZa0rAj8jSbrQsDBRkhRFaW5qCNR1jdEpMEiD7xSR0R+n8Zezya3Qq4do7VVfnGOETgENBcz7EfoIBilgeiHA+G4gJCKnw84YMxiMOp1OpzcwQSB+/RIk37kQCXwLY0wURb3BYDKZjWYzEwS329Xc1KAqWq9rMZTQKXC3vNgpepHem8mXZ5JDoRf2s63VvpgGr0OnwP0UqO9H6CO4W4HaC4GERcQmaV3DHegNxsioGFywDndLVdWuTmtXZwfnQfEuhU6BezOYTjFL9OFcXpBEVjet2suONQ1FgV7Wu1MeS+y6atNd7DIEx0sFaCDw3o/wjgP3JvB6ITD4QSC8zmA0mkNCdTq9KErXN7IE6I1zVZYVxeNxOOxOpz0IZzigU2AgvNIpkQb6fB7lx3GLk5bvZufbvF7mEPq5UzLD+Or0TiJqdIn7ms1lXQatS4MAEQzvR3jHgYEIhl7wd34TCAEAwHckmGh9EeVE8iobLdtF5Z2+e6Xo7QmM8mL5gmEUZSAiOtlEn/nkHEgAAIAh4tNzCAEAwAelhdK3C2hUBC+z0tKdrMrmxwmKE9Xa2WELa3Ox1BA62MgaHFrXBAAAcB9hhBAAAO7C6Ej6qpAnmelMC63Yw1pcWhfkPXqRPCrdOrFFJ5AHFzcBAEBAwwghAAAM1ORY2ljE401U3EDL9zKrW+uCvErpvsZBuJ7/fgKF6Kiqk8lY/gAAAAIUAiEAAAzIrERaV8Aj9LStmj1/gNkDfQey3Fg2IYaGh1FuHLPJVG/XuiAAAIAhgEAIAAB3tiiVPp7HzRKtK6dfH2LuILiQstpGl62UZKZ4Ez0QTS6FKrr8eLYkAABAnxAIAQDgDlZm0bszuF6g90vY744yNWiun2xzs2MW1upisUbaWIELRwEAIABhURkAALidN8fx/zaJGNE759kfTmtdjUYYEe///wIAAPgvSesCAADARzGityfTG2NJ4fTWcfZRmdYFaadH/MuP5+OjaX05aw+sZXUAACAI4ZJRAADog8joj9P4y9nkVujVQ7QW27XfwBg9N5LSQ2lqPHXJVOfP2zACAAAgEAIAQE96kd6byZdnkkOhF/azrdXIPN2cbWWxRpZspnFRlBFGZ1uDaF4lAAAEGARCAADoxizRx/P4w8PI6qYVe9jBRq0L8j0uhU63UIODjQynGhuda0VgBgAAf4VFZQAA4KZIA30+j/LjuMVJy3ez821aF+TbQnWkcHIE+paMAAAQwAStCwAAAF+RYKJNCyg/jlfZaPF2Qhq8oy5PzzQ4LESjUgAAAO4JLhkFAAAiorRQ+nYBjYrgZVZaupNVYa2Uu5cbR69k8xgDlVmZglmFAADgDzBCCAAANDqStizkw8P4mRZ6dAers2tdkH8yCCSrlBtHv32AJ2OoEAAA/AFGCAEAgt3kWNpYxONNVNxAy/cyK/bWu1fVNrrQzjLDKdFEeXF0roXZML0QAAB8GwIhAEBQm5VI6wp4hJ62VbPnDzA7AszgdHroeBML05HFwY41aV0NAADAnWCVUQCA4LUolf48mxsEWldOvz3CZFXrggKIwAibEwIAgO/DHEIAgCC1MovWzOYGgd4vYa8fQhr0sh5pEFMKAQDAN+GSUQCAYPTmOP6P+SQyeuc8e/uk1tUEurw4eiWbc86udWpdCgAAQHeS1gUAAMB9xYjenkxvjCWF01vH2UdlWhcUBEwS55weTuUJJlpXzjwYjAUAAJ+BEUIAgCAiMvrjNP5yNrkVevUQrb2KzQbvh8ouVmOjnGhKDaHRkXSmmcmYXggAAL4BgRAAIFjoRXpvJl+eSQ6FXtjPtlYjDd4/TU52oY2yI6mmi8604pEHAABfgVVGAQCCglmiD+fygiSyumnVXuyIoI0QiVwqYf0eAADwHZhDCAAQ+CIN9Pk8yo8ji5OW72bn27QuKFhhn3oAAPA12HYCACDAJZho0wLKj+NVNlq8nZAGfcfkWCpI1roIAAAIbhghBAAIZGmhtKGIhofxMist283q7FoXBDeE6/mKTNIJFKGnbyoZxzIzAACgBSwqAwAQsEZH0rfzeWoonWmhJ3Yxi1PrguAWLoVZHGxsFA0Po3gTnW9jiIQAAHD/IRACAASmybG0sYjHm6i4gZbvZVa31gVBL40OutZJ46MpNYTcKratBwAADSAQAgAEoFmJtK6AR+hpWzV7/gCzYy0TX9XmYmUdzCTSlmqmYogQAADuO2w7AQAQaBal0p9nc4NA68rpt0cYNjkAAACA/mCVUQCAgLIyi9bM5gaB3i9hrx9CGgQAAIDbQSAEAAgcb47jf3qQSwK9c579/gfCFYj+KDWEnh/FdXh/BgCA+wLbTgAABAJG9PZkemMsKZzeOs4+KtO6ILgnAqNnR/I4I+lG0V9LSUGmBwCAIYZFZQAA/J7I6I/T+MvZ5Fbo1UO09irTuiK4R5yorJ1NiKFhIZRopnOt2IsCAACGFgIhAIB/04v03ky+PJMcCr2wn22tRhr0bzaZLnewybGUEkLE6EoH/qAAADCEEAgBAPyYWaKP5/GHh5HVTSv2sIONWhcE3tDpoasdLNbINlUyD5YFAgCAoYRtJwAA/FWkgT6fR/lx3OKk5bvZ+TatCwIAAAB/g0VlAAD8UoKJ1hdRTiSvstGyXVTeqXVBAAAA4IewrDUAgP9JC6XvFlJOJC+z0uLtrLwT08wCXIyBMkK1LgIAAAIRAiEAgJ8ZHUlbFvLhYfxMCz26g9XZtS4Ihli0kd4cx1/O5okmrUsBAICAg0AIAOBPJsfS5gU8yUzFDbR0F2txaV0QDL02F13rJJNEL43mITqtqwEAgMCCVUYBAPzGrERaV8Aj9LStmj1/gNllrQuC++VCGxsVQUlmSg9lp5oJmxMCAIC3YIQQAMA/LEqltYU8VEfrymn19+RUtC4I7iOPSn8tY1Y3izHwSL3W1QAAQADBthMAAH5gZRb9yzQuCfR+CfuvP2CAKEglh1Cnmzo9WtcBAAABBNtOAAD4ujfH8f82iRjRO+fZH05rXQ1op86mdQUAABBwEAgBAHwXI3p7Mr0xlhRObx1nH5VpXRAAAAAEFswhBADwUSKjf57G3xjL3Qr9upiQBuFWkXp6NI0E7EAJAACDgxFCAABfpBfp3Rl8STo5FFq9n+2u07og8CWM0a/GUIKJu1W2o0bragAAwJ9h2wkAAJ9jlujjefzhYWR104o97GCj1gWB72l00JRYGhFOlV3YjhIAAO4dAiEAgG+JNNC6QpqZQBYnPbmLnW7RuiDwSa0uYoxGRNDoSDrVwlzYhgQAAO4J5hACAPiQBBNtWkD5cbzKRou30/k2rQsCH7arll3pIIVTmE7rUgAAwG9hH0IAAF+RFkobimh4GC+z0rLdrM6udUHg88J0pHKyyVrXAQAAfguLygAA+ITRkfRVIU8y05kWWrEHs8JgQLBJPQAADBICIQCA9ibH0toCHm2g4gZ6dj/rwqd8AAAAuC8whxAAQGOzEmljEY820LZqtnIv0iDco0g9TY7VuggAAPA3GJYuju0AACAASURBVCEEANDSolT682xuEGhdOf32CMmq1gWBfzJL9Lvx3CCSxcFqbFpXAwAA/gMjhAAAmlmZRWtmc4NA75ew1w8xpEG4Z3aZTjQxkdHyTC4wrasBAAD/gX0IAQC08eY4/o/5JDJ65zx7+6TW1YD/K++iSbGUaCKnShWdCIUAADAgGCEEALjfGNF/n0xvTyKV098eY384rXVBEBDcCm24xojowQQSkQcBAGBgsA8hAMB9JTL6p6n8FyPJrdBrh+nrCnxyB2+aFsfPtDKnonUdAADgJxAIAQCGRISeHoim4oZuN+pFencGX5JODoVW72e76zQqDgAAAICIcMkoAMAQ+S8T6IsCPjX+5i1miT6dx5ekk9VNy3YhDQIAAID2EAgBALxvdCStHsVNIn0xj4+LIiKKNNBXRVSQRBYnLdnJjjVpXSIEAcwkBACAO0IgBADwvv+Ry3UCEVG4ntYX8fx42rSA8uN4lY0Wb6fzbVrXB0Fgajz/u0kUa9S6DgAA8G0IhAAAXvZoGhXcMjs7zkib5vOcSF5mpcXbWTn2A4D7IiOMRej5knSt6wAAAN+GQAgA4E1Gkf4hl/e4URLIKdMv9rE6uyZFQTDaUkVOhcZG8exIrUsBAAAfhkAIAOBNb47jaSF93G6U6N9n8hDpvhcEwarLQztriYiWpHMBw9IAANAPBEIAAK9JCaE3xvb7r1Ni6eO5ZMDrLtwvxQ3M4qQaGxlErUsBAABfhX0IAQC85q9z+KNpd/iZLVX04vdM6XlVKcCQ0Ivkxib1AADQP3xTDQDgHbOT7pwGuzx0pYMZMVwD9wvSIAAA3B6mswAAeIEk0P/Kvd0PdHloTSn700Vqc92vmgAAAADuBIEQAMALfjmaxvSzlmOnh/5ayt65SO2IgqCpWCM1O7UuAgAAfAwCIQDAYMUZ6a3xfUwKbHXRB6X03iVmdd//ogBu0gn0SjYNC+X/4xSzy1pXAwAAvgSBEABgsN6eTBH6bre0uOgvpfQfl1gHoiD4AI9KbpUbBJqTxLdVYw8KAAC4CYEQAGBQ8uNoZdbN4cEmJ717if58iTmwmAf4kp01bEwkn5VI++rIiScnAADcIBrNYVrXAADgr6IMtGcRv77JW6uL/t8f6ZWD7FAjk7GrBPgYq5uGh1GCiVwqK+/UuhoAAPAZ/jFCKAiC0WQ2mcySTieKEmO43AX6xlVVUWS32+2w25wuJ/Hg+lSOTrn//iG7KVTXJXNaUxXxQWWUS2UxyVrXNABB3ilBa3ctC5V4vZ0T4cUBAAB+4vMb0zMWFhoeFh7BBGyZCHfH4/FY21pcruBYUw+dooUQUX13QmOLS/hjeXSNQ6d1OfcouDol6DEipH8AALiVTwdCURRjYhN0ej0RyR6P2+2SPTLnCr7Lhn4xJgqipNcZ9AZBFImoq6PDam3VuqyhhU7RSpSed8okq3442BKUnQIAAAC9+e4cQlEU4xOSJZ1OVVVbZ6fT6VAUheMTLtwJ56oiyy6XkzhJOp3eYJB0ktNh17quoYJO0ZBTYSr3wzRIRMHXKQAAANAnXw2EjMXFJUo6nSx7ujo6VBULosFdk2VZlmWdXq/XG4hztzsQNwVHp8CgBUWnQC9miTyq1kUAAIAP8NFAGBYWYQ4JVVW1q6MDYx1wz1RVVRVZr9cbjEaXy6UogbYfMzoFvCLgOwV6eDSNnhvJr3awduyTCQAQ9Hxx/QlBEMLCI4jI3tWFz7gwSB6Px+lyEmPhkVFa1+Jl6BTwogDuFOhN5lwn0OxEvG4AAIBPBkKjycwEQfZ4ZNmjdS0QCFwOh6pyg96gNxi1rsWb0CngXYHaKdDbwQYmq/RANMUYtC4FAAC05ouB0GQyExHmsYC3cM49LifdeGoFDHQKeFegdgr01uWhMy0kMJqegEFCAIBg54uBUNJdXz0fk1jAazweNxEZjCatC/EmdAp4XUB2CvTpUCOzecgp++syuQAA4C2S1gX0QRQFIuIcy5+B18iKQkSSKGpdiDehU8DrArJToE+VXfQPp5mM1w8AgKDniyOEjF3/mIvrWMB7OCciJvjiE/6eoVPA+wKxU6A/SIMAAEC+GQgBAAAAAADgPkAgBAAAAAAACFIIhAAAAEFKEqggmV7LIYbFZQAAghUCIQAAQJBSVJoWz7PC+YhwrUsBAACNIBACAAAEKU50qoWIaFKs1qUAAIBGEAgBAACC18kmRkQTo7kOnwgAAIISXv4BAACCV5OTqrvIIFJGmNalAACAFnxxY3pfwCR17nD3qhR5YpgaJTK7i5W2SpvKDV82MdddHIXPyXJP1pHqETdclWq8uF3cwI+s83ywyDFfJC7rfv2daTt2nYKAkJRpPzhR1vX/A3sqpNkZt/uB746Fv1ZLJKpFI12/HCaPC+EmztrcrLFLPN8mfVqqOy97v2wA3/TVNdYlU9tdvL0BAEDgQCDsg2T2/M/pzpUR/MaiazzCxPNT3PnJnqeumF46L1kGGu3UOVmuX4aQ4tAfuyrVeLPGoTsyQNBg6rJ8+/9OUsWf/j+Pl3i8WX0gll8qRyCEIFJt07oCAADQDgJhL0x5Jf+nNNjRrv+XEt1JBx8W5/lP2Z6REp8wwvFPXSEvXBMw0navuI4xjxcHSyEotdQbXrTpr1/ynpXh/K8pqkisvNLwhxqBExGnVjf7sPZ2P9BoJSnS8+sEVSTqbNP/35d0F1xk0KujY+SHkjnCIAD8/+zdd3hc5Zk+/uc9Zao06t2yZMu25G7j3nDFNoaAKaE5QKgJ2Q27EH5LspslCbub/ZJOQkhCKBtsiik2NuDecO9FLmpW79Koa+op7+8P2VhlbMtG8oxm7s/FdSGfOefMMzM6mrnnbQAAIQKBsDtrovfxKM6IdLf84l7TBi8R0ckm6YSXb5ioRjI+e7h3YqnpmE5ynHvvbG8io/Lz1nnZokqXtpQWWJfUKftneqMZEZFo9q6+y0tESoNpwW5DZbj384Xu0Yzayk1PNmjPDVPHW7jDIa3LNf26XHDR9Z+57FqDlqg+cZP3WxHaIBNFSMQ1Vtkqbik2vlYmtBEJZu/KW9yzJWqrMs8/KNcTEZEtxbVnqhLJ6Eh22H3nBV3Q52R4nkjVJoTpYYzVtonbSwx/LJbsnIhItH39SM0r6rQXRyg3WfnOo7Zn0KYJ34zXJe52dfzIW+MvbGxrl3bXClr3fS+7gyFGTxGIiM6WGT+sYToRkXi4Vl55rj9LBwAAAAgkmFSmGz46TuvIWrVV8jbvpRsqKww7FSIi0arODOubO7Mke/4xThlMpDCKDVcfn+z8zSB+I18SJvI5KeqEcC5prM5DuqQPjVG+P6n9jQxdJNJdhnermE4UluD9lrXjCD43RYlgxFXp4wpBF7XHZjr+MVaZH6lbdKFJ48mR6qMTnGtuUuO7rnFsTnD/4ybvrHBuxm8cBAzdzeo5EdGUkc7Xx3keGqSOsXB8SQYhSxIoM5Iw1ygAQKjBH/7uEi16x5NS1i506TamsSJXR8rhg0xdDuHcR8OcUmua+Jn1LQcRkeYy3L/WlrbGNuyrLo14AglvfBU+c0v4jF3Gkxoxpt86yjO+U5S67jP3EteE/ztsnfW5bcLGsFkbw8dvMW90EzGaOlQZLRAR7Sg0FOvERP2BwbpExAzqbQnEiJpr5E1uShnseSGei8SO5FinfRk2ZUPY48WCSpQ22P1MTJc7kmQqKzTftjF8yhbrnxquuU6A/qA2Gf5ax3Qi0aDdOszzv1OdXy5tP36L8+dpOtbohhD0dBb/XhYfEYE+/QAAoQXfhvcBTuzqO/mi2A3vNjFO1N4kf9zgmRBPolWbEUZnvvGZe0sTDzRpt6a7n7LxaIlkxocIRESiRUsXKFsnpVle1eR5KYYPS/NOzjflJyqzZSLONpVILcRvSVStRMR5bLznzzFERKwjKjM+M06T7OLXHyvUNsNPT8tnOBGJdf37kAB6jQvvH7CWDfU+lqpMj+RhjIh4RLj62E2ODMH6KIYKQ4jJb2bDbHxsNDvb5O9SAADgBkIg7K7GKeiki0SDw3SJhEudRkU+1NwRcFiFu8shjPjXP11TgFMV1nLhR6HJS5yIEY+WL307e91n7iVbnHv1DO+oHr8FjNGF6Ti4sKZQ/mG0Em1WHkiQ96ZoYUSaQ/7Yzojp0UbGiBOjITHqkC4n4OGGLv9WWoV8fOkMAUgX9p437T1vkmR9ZLS2eIjn+8m6gfEZqWpKiaEcv7QQSrIbadlgGhPFBcZ0/PIDAIQMBMJu2Nl6sTFDj2OUkKwsOidtuJgIk1O882UiIs0h7W8nIuI6dcxOYRAvpLVws267ltwmW/RERmWciGmDrIwRJ2KNCuPsm565d/ji4d6REhEXPjtuealMaCH9B/McL0Z1+SDQXG1Y61CeCOOLM90ZNs6I5ZXLJ3UiYo0ezokYF3+9zfpam487uDibP6k6obEFAg0z6IO4UK4QEamKcLpWONvKJye6ZwrEZG71d3kAN1idm2pdlGCmIeG8sLWf+6cAAEDAwBjC7hw1hneaiRMJJuWVWe7Hk7TxUeptma53x6uRjIizvQWGEzoREfewjok3Y2O1URIJBu37GWqX0YWMOTVGRIKsZ5h9NPFJUd4X07UEgz423ftIJCcizSEeaO+DM/vA+OgEdd7X/8WrI4w8QiZGRFw4Wie0cDLb1FtsPb4W1sSVJaKXyBqljROJa8LHZaJGRMQO1kpOImLailFKZsd3CwJPjVWem+J6HGOwIOBJEd6PlrZ/MNnzWKo6PUobF6s+PEqZIBARudqFKrSQQOg5YWfH7eTRkQYBAEIIWgh74OLfDpsHz3Dfb+O2KO/PZnSaaZTTqfPmF0oujCzSHPKGJs/4aJJsnrW3eZxEJiKt83Oqs5PNpNtIkNRfLm39JVFpgXXB6Usj6zQ3nzrecXjixdNzYeM54ylO+vWe+QqLpzFRfXZGp9u58P5+67u1gidGNwrqj+c45rRRVqwe6+vYkhLDjhGupQYiIke94YuLSxhXlBp/m6z9NJ4np7g2JbnsHsFo0G0iMV18NZ9Tfw+ABPjGBEmfOdgzc3CXjVwTV56XWv1UEoAfbakk/OkGAAg1aCH0QXXIP95lefy0YWujWKeSyqnVJRypNLy0L+y+01Ld13mOC28dsbxRKzRopGrC2XLjo8dke5dWBbbjrPn1arFOZT47TLrspoePGna2MqdOje3iO0ctL1QwvS/O3DssJ9/ywzwp30Mmiz7ewjadML/e7GM/7pXfrRA0IuJse+mFBQmJiDTxrf3WR0/LO5qEZp2iDVzxCNm18p9PG9c58JECAp3aZHjumOnNcvFUq1DnJVWnNrdwrMrwkz2W3zTgFxgAAABCAouITfJ3Dd2lpKYTUXNj0K5OcGm59jLzTUdl79WP8Dem3znF8YdBnDsNK7aaDvRY+XtAiIyOIaLK8hJ/F9Jngv5KAb8IvisFAAAArgBdRuGKBP0HM50P2niyiQuc9uQbDg3MNAgAAAAAAD2hyyhcEeexVj3VxFWPuC3X8hxWZgMACGoCo5uT+KPDOUO/aQCA0IAWQj/QWg3L1hquvl8g4OLLm20v+7sKAAC4MXROcxMpykhJVVTluPr+AAAw0KGFEAAAAC4530pElBHu7zoAAOCGQCAEAACAS4o7AmHPZWkBACAYIRACAADAJefbGBFlhGNFQgCAkIAxhAAAAHCJ3U1rSlhpm7/rAACAGwKBEAAAALrYW+PvCgAA4EZBl1EAAAAAAIAQhUAIAAAAAAAQohAIAQAAAAAAQhTGEAIAAEB3SwbR1Dj+aTGdax4Is42K0SPmLJ01epCFqarqairav2PHKbva68OFuKwZSQ0Hs+u1a7nTyx0lZtz6z7c7Pnxtd+01nQ4AwD8QCAEAAKA7g0BRRkoNo3PN/i7lqlhY5u1PLDLsXfPOh9VOnUlRQ6eMijAwu9rrpRRZfNaMcQWHrzEQXt9RAAABBoEQAAAAuitzEBGlhfm7jl4QYibNGlGz+7WD1S5ORFxtKjywj4iIxMiRS2+bO9ImEncU7v/yi+x6hcSx97ww032kwRxrtUSYG/Z/tPGsI33egiHGiIQVT01Syvd9srk2ed6S+eNiDEzQm3N3rNl9vpXFz3noviFnVr13ollIuvnJ5TF7V36WH9/lqE2FnivU6KuSy5Y3Wz3ZLNtks81oP7Rmy5kG5E0A6FcIhAAAANBdWTsR0eAwYkS9bmjzDyE+JaaxrMrTvUwWMfW2pYkFq149XK9HTXjo4Ttn17y9s46IhEixctWnOxws+uaHH5o1KPfzol07iidOLHhv1VmFWPikexfFZH/4Wl6bJkZOunvFsszK1Tl1+9bvSVuxfE7jvvAloyo3/+NMO+ftnY66Mp+V1IdfrrxoqXLVp5vbyDr2zsfumFD+f8daAvwVAICBDZPKAAAAQHdNHmpXyCRSpNHfpVwveVBGUvWJ7HqFSGs6c7Q0IiPVyoiItMrCIgcn0lvqmgwRNrHLUVJqZrpt0PS7H3/k0adW3Dk1kpttYYxIb8leu7VxyoP3pOV9vrHIdW0JzWclly+vouB8Gyfijvz82pS0ZHx3DwD9C39lAAAAwIc/nWXNXlJ0f9dxNXpdVUPU4GQTa3BeOad9fauuX3hQnHPGBKJOnTIZY7z2wJr3DrV1O5kYkRgjuDzGcKuBkfLN2ux8Hv31RsZYR7ssE/G9PQD0P/ylAQAAAB/q3QMgDRKR3nDsQGHSzbdNTzKLRMSkqIwZs4aZmVJRWJ00YWyMSCRGjZ2c1lJU5rhcjlNUzWgyMSJSynLL46dNT7cKRESyLTkxjBExU9rCb4+uXfvW+0eiF981NlLodtSV+azksuVJaWPHx0lEUuzEMYmVJVW9nywVAOB6oIUQAAAABjLelvP5W/qcpbc+MTdM4Fxvqzqza6eXc9fhDZtibvv2c5MlxhyFu9btrdeJRF9n0MtOnxRufeTZmzzFX636/Is1YUsWfv/7Rl1n5K7e/+VntZR5x7LUnM/fzW/3nv9833cevGNW9Xt76rsctT7f3emEQty07/zbxI44rRVtf/MTH5W0XKY8tdJuWfLw9+LCjK7C7R+dwgBCAOhnLCI2yd81dJeSmk5EzY0N/i4EgkpkdAwRVZaX+LuQPoMrBfpD8F0pAAOJOPaeH40999v3czC1KADcKOgyCgAAAJdlkUgcCEvTAwDA9UGXUQAAAPDt+yP5iAh69Qwrbfd3KSFCO/3pr077uwgACC1oIQQAAADfWr1ERIkWDGMDAAhaCIQAAADgW42LEVGCGX1GAQCCFgIhAAAA+GZ3ExHFmfxdBwAA9BsEQgAAAPCtzs1VnUSGLqMAAEELk8oMMGaJ0ixavInHmbhJ5GaRE5FLY26N1btZrYeVOUQX1rAFAIC+UOtiPz5COvIgAEDwQiAcGGwynxitjYvUki0dy9xSu8raVfLqjIissh4m0eQYTkScqMopZDeJJ5vEVgWjPgAA4PpxTgiDAADBDYEw0CWa+fxEZWykxhiVtItbquWidqHWJbh7LFlrEinRrA8N0zMjtFsHKUtTlOwmcVetVONCx2Doe9Nj1edGecdFahYJHxf7UpvCjjaIf8w1Hm8U/V0LAAAABD8EwsBllfjSFHVyjOpW2e5a6XCD1Oi5UoufW6OSdqGkXdhRI8UY+NRYdVqsOj5KO9ogbaySnCpaC6HP/DDL+/xIt4DfqX4QLvP5ierNCeqLx80fl8r+LgcAAACCHAJhgMqM0O5LU4wCfVUj7aqVe7YHXlmDl22sknfVyfMT1Fnx6qgI7aNSOa8VDQ7QB6bHqs+PdKucfnPW9EGxoVXxd0HBJcbAnxzhfWaE538muI43ioVtaOEHP2OMwmUuMtbk8XcpAADQD0STJdzfNXRni4gkIrfL5e9C/IMRLUlSlg9W6l3CW4WG7CZJvd4eeapOBW3CmWZhmE2fk6CKREXtoZsJTWYLEbW1Nvu7kD7jryvlt5NdqVb+ylnT3/INHv0G33nwc2lsX50UbeCTYrREi/55xY1uJAy+KwW+oXHR9K9jKMbETjT4uxQAAOgH+O45sAiM7hmszEtUD9vFvxQY6t198ALVuYW/5BmO2MX5ieo9gxV084NvaGykTkQfFBv8XUgwey3PQEQzYjFlMPhfo5eIKNqA0cIAAMEJXUYDCCNaPliZFK3urpU2VvluFjAINDNOXZysjInUB1n1CJmIqEWhCodwukncWi3tr5e8PRptVM7WlBkaPOrSZEVk/KNSvLHD9bNKnIjQU7Rf1bkFIrJhCCEEgI6eolFGf9cBAAD9A4EwgCxOUqZEq1uq5Z01Pl6XBLP+L1meO1PVsB6TOsYYKMagjY/SvjPU26ay9eXSH3KMdT1aF7+qlSSBFiUqDV51WzVeegAAuDqHQh6dzBKZRLrWAe0AABD4kAoCRWaENi9JPWwXe6ZBo0jPZrqfGO41i8SJTjeJW6qlA3appE1o8hIRRRkoPVyfGacuTlLGROorhih3papvnje8lmf0dH3z3l4tRRj4wkSl3CHktaLDMAAAXF21kwyMTBICIQBAEEIgDAhWid+XplQ6hZ4TSMSb9DdnuMZHaZzoiwr5N+eMxe3dg1y9h+o94hG7+GqOcWiY/sIoz7JByrNZnjnx6tMHzd2aCteXSYPM+rfTvL/LMWItCgAAuKo/nsGbBQBA0EIbUUBYmqIaBVpdIqt6lzfdkRHa5/Md46O00nbhzp3Wfzps7pkGuylqF35w2Lx8p7XMIUyM1tbPd2TZunyjq3K2ulQ2S7Q0GYPAAAAAAABCGgKh/yWa+eQYdW+d2G1O0XiT/s5MZ6KZH7GLd+2ynmq6hhUjTjaJ39pp3V8vJZn5u7NcieYuww5rXcK+OnFKjJZgxqIBAAAAAAChC4HQ/+YnKh6VdtV26SxqEunNGa4kMz9QLz2wx9LgvebuOs1e9sg+y0G7lGDW/zrNaewaJ3fVSh6d5idgUnsAAAAAgNCFQOhnNpmPjdQO2qVuI/V/mOnu6Cn6zCGzyq9z8Iai0zOHzB19R/9phKfzTU6VHbbL46K0cBkrUAAAwJXIAiWYKdGC9wsAgCCEQOhnE6M1xuiIvcvsPglm/YnhXk70wyPmJl9tg5kR2s/Hubcuas+5oy3njrati9p/Ns6TafMx+1ujhz17xMyJnhzujTd16SB6yC4yRhOiMWccAABcySArvTie3zfU33UAAEA/wCyjfjYuUitpF7v1CP2XLI9ZpC8q5J7jBg0C/Wyc+6EhXqHTESNsfITN82iG571iw8vZJqXrwMATjeLGSnlZivJslvenJ01fb2/wsHKHMC5S21OLXwPof5L6m4WuOQKRQLEytXhIIVIaTHcflut6eQamLxuuFRbIebx3233jWWnuX2SqgxgjRnV24/PH5OI+b/YQlNdvU7/40rwBo3QhKLQpRETh3afBBgCAYIAk4E8mkZIs+tbqLu+xBoHuSFU50W/OGbvtbxDo3VnOGXG+B/6JjB4Z6h0Wrj+yz9ItE/7mnPHWFGV5qvKLrnExv1VckKhgrWG4EVTphc3hRCRFeTZM5S9tMR281hjG9KUjlG1Fcp7au+2+iDbvr0bzD3eHv99OJPCMSL31GqsACEHtXiKiMARCAIBghEDoT+lWjRF1W0liVpwaLvHsJrHnChM/H++6XBr82sw49T/Hul86Zeq8sbBNONcsjI7UZ8aqX9VdetEL29lCovQwLbflGqYwBehbcXHel0crGSIXubDpnPl3NUyweVdOV9ftM3/gYONGOl4NMzxwVMoc6Z4l81EzHSs06S+HjLsuXAr85i7bDYUJnldGqskC6W7x9ZPmT7oGPibzaJ1VuomISGeFjSIRkaC8frvXWyKYzBRl4YUFpp9VCIqvwrTLbIxP8Lw8ShkuMoXTtlPW3zQSEZ88wvV4spZkYHvPmP+9QsC3LjBwuXXyamQUySiQB+3eAADBBYHQn+JNnIhqXF2C3y3JChFtre7+0mRGaA+m92rlwO8M9a4qNuS3djntlmp5dKTnluQugbDaKRJRnJHnXlf9AN+cYFb+e6y+5oBls4vJFuW12e4ljeYNrYYX8tT3JnmL8/kvksWX9si1nGpzTPuGeLftt6zv8q0I291pu2Dxrhqnb9sX9nYrDU5zrp7kPb3L0Lkrqdok/73F9dot7cft0ukmaUO5dK5juiWmGxrNP6gQyKj8fq77vgbLB+SjsE2iz43eV25Sjx+0PtPEuMCjOr5dEbTBHsuKHSJFuT+b4p1caTqE+ThgICttJ4NIsohACAAQbBAI/SnWpLerrFt3zTGROhEdsHd/aR5MU4TezTYqMnog3ftydpdGwgN10nMjPWOjutyZWyOHymJNeHsHvzHFqLPMWvQU7XEiImbjlGwi8lJFqfm/Yh0rp7K/7rHu8fb2bOZodUyz/P1WIqKyCvngGGWKyZDn6rSHLv7jQNjn4drUGHV6snv1MPHFXeYNXiJd3F4r6ETkkba1uJdG01rmozCTzcdGs029qcXwXBPjRKSzJp1IINLFL8pFDxG1SDmyN0kkwiIvMJD9Jec657sGAIAAh0DoT2aR2nt8Rky16ERU0ta9v+js+Gv4ODk7rnv3tGIHI6JBlu7Zz6ExM7qLgv8w4nqL8Z/29phaRuQjw3mzQgkmzoj1snWtl59YG9vETW3iplKpaYHzW7F8QxURkXjxmpOFyxZmtfnc6LsW78WrTddZL7/NAQAAALjBsOyEP5lE7tW7f07sWBiwWem+PflaFoBKsXYPfs1egYhsPVYddGtkQiAE/3E1yEdsnu/F8Y5fw+QoLYEREc0Y7bqj2Xz7fjl9rOsey4Wd3ZrveQ6/3u5slE5Heu8OIyIanKpMc0pH3F32FK3qbXG6lRERGa3aaCOr7mg/FLS7UnUTkTFcWR4p7mv0XdjlNh6N8D4SxRkRMR6DiTcAAABg4EAL4YBxTeOPMFgJgvszZgAAIABJREFUBgrdJb94WP/5WMdOiVRGLc3GHx8VeZLrf2Ok5/dItar0Qr5z1STv6X2GPF1cU8p/OcfxsCL+dq9p69cjartsN/4kW39luuO7Amce8XfHDD3WqOBThrt+PFkXdMa4cDDf9McG1tHDs9DoWb1Qi5XY7tPmj12kk4/Can1VW+uSf3JM/6+Jzl0CeYi2nOyYVAYAAABgAGARsUn+rqG7lNR0ImpubPB3If1uxRBvrEl/NafLYL8Tt7VFG/nkL8PrPV0aCbctah9u6+1gv7wWcfF2a+ct8Sb9yLJ2u4dN+jK88/bnRnlqXez9YsN1PYKBJDI6hogqy0v8XUif8deVUnp3KxGlrfHdUXJACshlA/31PAfflQJ9wipTtIEcGjW6r74zAAAMIOgy6k8ujcJ6tNGWOwUiSg/v/sl0T901dETbU9e9G+gQKyeickf3V9wqchemwwcAgCuanUDPjeVTYtEBBQAg2CAQ+pPdLYRJvNsQvtNNIhHN7LHe4Iclkta7N2KN04el3Vv8ZsarRHS6ucudmSWyStzuxq8BhDZd/sHngdU8CBBonCoRkQUDTQAAgg6SgD/VehgRJZq7fA7tWIFwcVL3JQfzWsX3etex891CQ0Fr91d2SbJKRFu6Lm+YaNKIqM6NCRABAOBKPBonIqOI9wsAgGCDQOhPpe0iJxoS1iUQ7q+X2lQ2OlIfGta9weLlbNO+uqt8Pbu3Tvrv08ZuG4eF6yMjtDaFHazvcnhGOOdEpQ5MMwoAAFei6IyIZAFdRgEAgg0CoT+5NapyClkRXcbweXVaVyYzohdGebrtr+j06H7LPwoNPvuOapzeOW94dJ9Z5d2/wX1htJuIPiuXla4Zc0S4VuEU3BhDCNei2sWIKMWMz4X9KNLAiahNRWsMBIpWhVe0U0P39yUAABjwEAj97HSTMNiqxxi6fLZ+NdfgVNmyQcqEqO5ZTdHppVOmpdvD3jpvyGsRHSpzqCyvRXyzwLBke9jPs0090+CkGHVpsupQ2R9zu/Q4jTHy1DC9Y8giQO8dbZCI6Hsj8MGwHz04xEsXRxQDBILCVva7M2xDGb6kAAAINhge7mcnmqQlKerUWHVj1aVJROvcwpvnDc9mef401XXnLmujp/sbcH6r8HK2iXoh2shfneJmRG8UGOq6Th4zLVbjnE7iEydcoz/kGBcnKY9keHVOf8o1NnjxAbEvRRr4g0O8Pxrp0Tn9Pqd7928AAACAvoVA6GetCjvdLE6LVXfVya5OE4u+lmecE69OjNb+Ms21Yo+PXqC9IQv0l2nOVIt+rEF6Pa/LJ0uLxKfGKqcaxTYFn+bh2pxvE148bv5/N7keG+Z9bJjX3+UEJ53Tb88ZD9vxfQ0AAAD0L3QZ9b+dNZJRpHkJXdaZ8Gj09EFzlYtNj1U/nOOMNV7zeK0oA393lnN6rFbrEp45bPJ2HT04P1E1CrSzFt8IwPVYWy7fudO6o0Zq7T4bLnxT7SrbXy/dv8f6Wh6aBwEAAKDfIQ/4X41LONogzY5XjzUInXt11rmFx/ZZ/m+Wc0qstnae49kj5hONvW0umBSjvjrFnWrRq1zsu/vNta4uyT/RrM+KUw/ZxTqsQAjXK7dVfGy/xd9VAMANIjJKspJIVNru71IAAKBPIQ8EhI1Vklul+9MViXVpCcxtFe/YaT3RKA626mvnOf4yzdVzLYpuMsL1v053fjr3Qk/RO3da81q6xEiJ8fvTvQ6Vba7u1aqGAAAAFomeH8Mfz8T0wgAAwQYthAHBqbKPSuXvDvPekaqsKeuS0+rcwv17rP80wvPUcO+yFGVZinK2WdhSLR+ok4odrNkrEFGkQR8axmfEqYuTlVEROhE5VPZGgeH1PKO3R35cnqommvjbhUaX2v0mAAAAnzreTPAtMgBA8EEgDBR5reLOaml+otqiqNuru7wuHo1+l2NcVSw/m+VdnqqMjtRHR3qeG+l70v82ha0tl/+YY6zvMTcpES1KUifFqNtq5IJWvK0HlmN38c0VbHMFP1DHvFgZEgACDOdERAzTkAEABB0EwgCytVoOM9CiRMXAeOdVKDrUuYWfnjT9Its0I1a7JVkZF6UNsugRMieiFoVVOIXsJnFrlXzALiqX6VU6N0FdmKicaJR2VON1DzhpYfR0Fn86i5o9/Ksa2lLJNldQM5b6A4DAoHMiIgGBEAAg6CAYBBBO9FmZLHC6OUG1SLSuXOq52oSi0+46cXfdtU1GLzG+PFWdFKMebZDWlssYAhLIIo10ZxrdmcY1TkfttLmCNlewvGZ/lwUAoU3jVNFO3utaAwkAAAIZAmFg0Tl9WiY3K2xhkpJi0VeXyt0mCL0OiWb9/nRvoolvq5F3VEtIgwOFyGhaHE2Lo5cm8tJ2QodSAPAjRaffnUEaBAAIQgiEAYcTbauWyh3Ct9O8z2Z599VJO2ul65sAxiLxeYnq7DjVobK3C40YNzhw+exQCgAAAADwDbGI2CR/19BdSmo6ETU3Nvi7ED+zSHxJsjI1RvPodMguH7GLdl/zxPgUZ+RTYrWpsYpRoEN2aXO1jDlFI6NjTs0r9ncVfewPRVFfFin5iPrQdyKjY4iosrzE34UAAADAjYAWwsDlVNnaMsO+On1BojonXrk5Xil3CnmtYmEbq3GJ7h79Bs0SJZq1jDA+IlxLteqc6FSjuLNWwurzAAAAAADgE1oIB4ZwmU+I1sZFaikWvaOV0KGydpV1LDNoEChc4haJExEnqnAKp5vEk01im4LxHpcEeLuH/eFeje5s9tDXXUat8emEKwX6WoBfKeAvAqPBVlI4VTr8XQoAAPQptBAODG0K21Mr7amVTCKlh2lxJh5n1M0imURORC1eVqoxu0eoc7FSh4/GQxjofE4qY/VrSQAQUgwCPTuGuzX69yP4qhEAIKggEA4wbo1yW8TcFn/XAf3P17IT+BwGAP4hCURE6mXWuQUAgIELgRAgsHTuFIqF6QEgQMgCEZGCQAgAEHQQCAECQmHrhcbAQ/X4Dh4AAo5FIiLChNUAAMEHgRAgIExbh+6gABC4OFFhK6tHtwUAgKCDQAgAAABXUeWgP5/zdxEAANAPsEIdAAAAAABAiEIgBAAAAAAACFEIhAAAAAAAACEKgRAAAACuYkQEpYVdWI0QAACCCSaVAYC+Jo+6/ZnbUj1ulYiIO8+t+/BYzB13R+x9/6v6vlpRQx51+5PDzr2xvki77C4sfPLdtxt3rt7XeC13yswpE+fOHzvIJmiq6m0qO7p9b17j5e/kiqeyTFjet48awH9WDOPhMv3XCdaEiUYBAIILAiEA9AMlb/Obl9Ias8T4tZpeE2In3rF8aNnnn2wpc+hMihg6cXiMgTW6uL8LA/Ari0ThMrl1akYaBAAIOgiEAHAjSVEjFy2akmpiTLUf2771BJv22Ky2j9eebOUkxM58dL533SdHWyO77HOs3jj57rsGN1ZTmC0snAp3rd9f1fPEQsrkOxeNCJNlWas/9uWWU3UaEUlx4299OCk2TGrL3r5hfxVLn3HbomEWTWO8dv/q7QXObkFPSJo43pj9xaEyh05EXG0pPHKUiIiYIWHCsoUTEw2kteRv37KvyEE9t5iSp9y5aIxNddZXtkbF1a5Zk3O5R32sztt/zzBA30u2EBHVOAnfjQAABB8EQgDoB3LmLY//s0pEpNYeeH9D0YXNQvTkhaOad3ywqUGRY2c8MH9c0dr88+Y5I8JOHW1jscOHKIVfNLHoad32WZNHQripad2HO1uEQfMemzT8eHVBj3vk9Wc2rjzq1klOmnnv3MyCT84RCVGx6vaVH1TzhNkrFk0uWts8OaN2w6o9lTqTDLLe46MtM8fEGOuP9+xiKsROXzTOsfv9v5WrsZPvvmf20He2tk7rvqV96vzhtVtWra7hiTPu+45Q2+nwHo/606NN6EYKA0jSxUAIAADBB4EQAPqBkrf17c5dRi/83zwoPS7avODuDCIiySSX2fT6vGLTgozwY9mmrCHevC9ayTy2+z5EpDeXVrTpRLypqc0SZmU975GZk25aMDnNxnTdFGEptjFykN5ckF/j4Zzqcs/rc5PF81XK1IW3UE5xUX5xZcsVH4CYNu+784aaDFrOhpU7m5OTxZI9lW5OZM/Nb7krOc4a1mNLazIr+6rOS0R1BUUNgzpX1uNREzV9s+cX4Iaye+hcMytpQwMhAEAQQiAEgBuIMU/h9k93lHVqHxMKikxzh0VWW4Z5Cj5t42TpsQ8LjyOdLvyTc+YjDpI0ZM7cuMI1q7NbddPI5Y/E+5oLUa/d99GHBanpQ4fOfGhS+ZrVB2u7NtNxV0ODZ0JCtJBfr2ulu9569+C4O7+TLBARsa5d5bivLdf0qAEGkpwmymkiIl/XHgAADHCYQBoAbhjuqihxDp2cGSESkWCKjYuQifSG/AJ5xM2TM5wFha3c9z5XJxiMvL3FoRMLy8hIvPCXTYgcPjzRyJghPmuYUFPptUaavXWl5w7uO1Zmjo2RWFj61FkZtkufcfXqE9mecXOnpVk7UqDRKDMi4q6qSm3I6BQTIyk2a0REbVW9o+eWmmoanBkvM5Ljhw+N6fTB2dcj6nHXAAAAAH6BFkIA6Ady5pInf6gSEZFWtOndfRc26w2HN+1ZeMtdT01jnLSW3J1r61tIb8wtNjwxxbF5Vzv3uY+9+cp3wZuOr16bfThv1MK772x1qS1K04X2Or2pXrrp/hXx4WLLqW1f1smDFt0+M81AJGgNJ7ef97L4wSPTW3P3Xzqnbj++fj2fO+/bT0aImqa67cX7vqrjpNsPbjt926IVzxiY2pK3ZXORV6eeWw7tKlq+5Lvf09pqK1saFeXSWhU+HnVbZPe7BgAAAPAHFhGb5O8auktJTSei5sYGfxcCQSUyOoaIKstL/F1In8GV8g2xiCm3TW/ZuiXf0zcDowRJIlXVSYieePfysH3/t6f6sl1E+/qu+1LwXSkAAABwBWghBIAQxVuOfLG5707HzEPn3zs5XhQNQnve9s01Vxow2Md3DdBvGNF9Q6m4jR+1s54z8wIAQBBAIAQA6Avckb/1H/n+rgKgbyVbaVo8HxnJjtT7uxQAAOgfmFQGAAAAfBsTRUR0rpmjdRAAIFghEAIAAIBvE2M5EZ1qxIy4AABBC4EQAAAAfEgNo3gTtXpZQYu/SwEAgH6DMYQAAADgQ0U7vXaWwmXCdDIAAEEMLYQAEKiE2GnfefGZ27IM/XN6MXXJY/dPi/i6K5w0dOGTKyaE96ZrnJAy/3u3Z8r9UxdAoOBERW3sVKO/6wAAgP6EQAgAAUqIycoQq5sSs9JN1zx+SRCu/sdNq8opsmYOi7ywpzQoa3Bzzvn23jSFcPvxdfvK1GutCgAAACDQoMsoAAQmIWb4CC1nw5HI5aOGmApyXFxImbp8wRADIxKtsVFVm14rzHwiNfuNHeUaicOXPjos5/+28AVPT5POO4zRUs2+L7OFSYsXZEbIjLUX7/1ib2Fb96inVRYUmW8eHnnicKNOcmpmelP+bgdn4ZmLl05OMUoGwZm/e8POEocweNH3ZhgL24VwY5ix9eSGHTktsTfdObHq7S/yFL88NQAAAAB9BYHQX5hx1L1Pjsh987PTHn+XAhCIhPjhw5Tzn9eVRZTdPH6YKfe0S688vGblYWKmtMV3zyg4WaqFZ/Y8TLLpRevXb/Vw49AlD9jOfPxeoYMsWYvvmZNWtqGke3zTanILDAuzIo/ub5TSR6TWF+xxcOLO0q/W5rtVLoSNWv6tySllX1UTieFa0boNBR5DxsIH5meWrGu9EU8BgN8MCSeVU3m7v+sAAID+h0DYZ4TkhY8uj9j/9to898V2CCFmyoPfTT/3909OtPbohcbVmpN73A3fpH1BsKZNmD1nXEaSTdac9pJzh3YdOt+oXXZ3Zh57/2MZZ9+6zgj6DQ8HuDZC/KgMd+76Zl1tyylfMHmo+cxZJyciwTZm0Tzb6XVbaxQW7uM4raa0zMOJhMS0wZHJkcvvmUxEokFoDzcxUrpfiHpdTqG0dHj0wRORI1PsubtdnIhJESPnzB4XK2uaGBnpiJKpmkirKS5xcyJPWan9lsFxAgIhBDHG6NtDKMHC38xjOU3+rgYAAPoZAmGf0WvO5jkeGplhyT/r6PjUKcSMyoqqOJHfo6MaERFpjQXZ32CkPjOmz7n37vT6XVtXflTjkqMzpi9c/FC0/O6XOT3DJ8CAIyZmZkbESfc+OY2IiyaTbZj1XHY7lxIm3TrVvffDM806kcg5sY7RhYxd/Ilrmt7xA+l1J7/8MPvKYwL12vwCdsuIlKbIQXV5W92cSIgaN3+iZ/d7q6s8LHHBiulMYERETBQu3BPWY4Ngd1MMJVp4k4ew2gQAQChAIOw7el1ubtOEkZnWc8fbOREJcVmjwsr2nndyYtbB02+dOz4tQlZbyo/v3rqv1MEvdRllpsRxC2+ePCLOIijtVSe3fHy4UiVmTBi7aO7UEXEW5q49t3/rtpzGzjNYCJHj546lYx9vPl6rEZG3Pm/Hl8a4h2dNS8nf7pr86F3hu97eVqwTMcuE5Y9nnPvbpwXhU26dnWqQEx9+aq7uzN70wZ6WMQ98d3jdUWdCWpTFIrcX7Pp8f6mDkxAzrTeH767S/fQ8QygQU4ZntO1f+d7xVk5E4uAlj0wdYT1zLnrObUPLNq4p7PjOhbe1KRFRFlbWZkhKT5Qop/MZeF1ZVdTUicl5eys9XAqLi+L2elfs+FlJ9QeyqzpdS3pDQT59a8k0qfrQjo7GfYNscLW2ejnJ8cOG2AQ7ERFJKSOybLmn2sOyMuPrztfrlHGjngqAG0sWaEkqJ6LNFaTi7zwAQAhAIOxDelPuGfvU0SMiThxv5iQOyso0Fe867+YsfOzty0Y6dnzwxwKHddjCB25d2vb+mlMXO14y64hld0xlh9b/9ZM6j2xLiiKdiJmHL71jCtv/2es5jSx+4vLbl81oeH9P3dfvzcw8aHB8a+Hm+ks9RHl7YV7NvEmp0UK+z+Iaj2zcO/SxjLMrL/T5ZFYiMTVN/ui9j6u8cuLN9965tHHVmhzHZR5b98MB+pGYPHKos2DNxcZ1rSq/LGLm8Bg9fVykuX7R3WlE5C3d+9HhUwfab/v2vUNbHM0eh9a1uzR3F+36PGrhkgcfkziRp/rgps12LWHEsPjW/V3vS2/ILfTOuqlub0lHHtTrzh5tW3rH/altXq+7te3CReetc8QvfOjpSJNSue+zPBdP6u+nAMBPpsRRrJGqneyo3d+lAADADYFA2Jd4a25u9c1jMmNOHrILg0YPFwq2lXqIhaVnpjac+HtBi8Kp+fz+IxMeG5Vuzc7rOIZZho4Z2nz8zexaFyfytFTWXNg4rOXEm+fsHk5Uc+JA4cSFQ6L31dkvJkJmNhvJ7XJ27gzH3U4XN5lN11CwVn06u9rDiby1J841PTk8zZh7zts3zwXAN6CVb37nw07/Vou3v1VMRCdePdl1x7NbPjh74cedRES07S9lF2/jrvKjX7x99NLOUnoCO3OytPs4W91+aNUrhzr9u+XcF6vPdd5DJGLO4h2btl46tHLn3yqv9VEBDAQH64gRq3ZynaN7NABASEAg7FO8veBc6azJo2OPHAgbNVw/v65cIRLMVove1nphJBN3traqFqv54hsts1gsemtz13GGzBpmlWKnPPjohAsbJEnNNXa+I5fbTSazhdGlEYPMZDEzT7P7Wup1O10XynI5XMxsMRMhEEKwUku2f1Ti7yIAApzOaV8tESENAgCECgTCvsXdhWdK587LSrOHD/EUrCnXiIi7HE4h1WbtCG/MYrNJrmrXxRzHnQ4nS4sIY9RyKRNyp9OpVJ9a+Vm2w/eEGNxVUW6fO3JE3IGa2guNFiwsIzPJVXq4UdfSNUG4+F5uMBq+XqCbdz+ZEGYLF6hRJxLCIsLJVegiIk3v7eEAoUEr69TwCAAAABBMhKvvAteCe4rOFclZi+antZ/L7Rjzxx0l+RUxE2YPs0lMihg2Y3JMZU6J41IgLD5bHDlp4dh4k0CCIWJQYoRA3Fl0pihm8qJRcWaBmGC0JQ5Li+zyWulN2V+dEaYsXXxTcrhBkKyxmQtumx1Xuu9Qpaa319t5UnqiTMRMSWNHJ1wId1xxu3l4pK3TeYS48VNGRIpMtA2fPS6y9Hyph9M1HA4AAMFBwt92AIBQJZosvpby8itbRCQRuV0ufxdyfbQ2b9T4CYPbTmw6UnGhHdBbX2I3jZq1eMmc6ePinWe2bz1c6yUpbtRNMfbjubWuhuJKPW3ygqVzZ00flxHtLsupbNOVxuIKNXXy/CVz58y6aczwGKGhvKi2y5BBtansfJU0eMrMeYtunjEpI8pduGf9V7nNOpHeWtsWO3Xh3CkjRwy12Gu0FGPt0ZwGnXi7g2XMWTR/7pTRlprsYnf8mHGsMCd81m2L509M9pzduuFknZf3+vABt7qFyWwhorbWZn8X0mcG+JUCASr4rhS4KlmgZ0fxBDMrbCN9oP1tBwCAb4hFxAbcbHkpqelE1NzY4O9Cghuzjnvgu2kn//Z5jnr1nYNBZHQMEVWWl/i7kD6DKwX6Q/BdKXBVD2XwyXFk99Dvspm7+7RLAAAQ5NBHBAAAIHTdnMQnx5FHp7fzCGkQACAEYVIZAACAEJVg5ncMJk70YSGrcfq7GgAA8AcEwpDFHdkf/Dnb31UAAID/1LrYhjIui+wU+p4DAIQqBEIAAIDQtaMaSw4CAIQ0jCEEAAAAAAAIUQiEAAAAISTDxuclY3EJAAC4AF1GAQAAQsX4GHoog2SBqp2Uh8UmAQAAgRAAACAUMKJFKbQ0lTOi/bWU3+LvggAAIDAgEAIAAAS/MdH81lTSOX1eRrswkQwAAFyEQAgAABD8zjSyg3X8bBOdbUIaBACASxAIAQAAgh8n+qgIURAAALrDLKMAAABBKMpINydhNlEAALgKtBACAAAEFcZoRjzdnsZNAtW5KBeziQIAwOUhEAIAAASPtDC6J50PCiMiOtVAlQ5/FwQAAIENgRAAACB4xJhoUBg1eeizUjrdiEGDAABwFQiEAAAAweOEnQwCO2YnRfd3KQAAMBBgUhkAAICBKspIy9MownBp8hhOdLAOaRAAAHoLLYQAAAADT2oYzUvi46NJYCQK9GmxvwsCAICBCYEQAABggJkYQw8P50SkcTpaT/tq/V0QAAAMWAiEAAAAA0xeC7UpdMTO9lZTs9ff1QAAwECGQAgAABC4Esx8YiyNiaQ/nWWeiyMDnSq9fJxpWHYeAAC+MQRCAACAQDQviU+LZwnmC/8cGUUnGy7dijQIAAB9AoEQAAAgIAiM9E4xL9ZECWbuVCm7kU40sMJW/1UGAADBC4EQAADAb2KMlBZOw2x8mI2O2WlzxaWl5PfUUHYjK2xFYyAAAPQjBEIAAAhCx+7imyvYulI6Ut+l2S2gTIqjFRmXiksL63JrrYvVum50SQAAEGoQCAEAIAilhdHTWfzpLGrw0LZKWl9Ku6ouTcpywxhESg+jWBMlmXmihTlVeif/0q0V7dSmUFk7K2rj51tZpeNGlwcAAIBACAAAwSzGSPcPpfuHkkvju6tpfRnbWE6tfbpUgyyQReLRRhZpIIPAD9Vf6vZpk+n7I79uA+ROlYgu3Vrrop8d6/jnpY0AAAA3EgIhAACEBLNISwbRkkFc43TUTutK6PMyVu28eKtERGQUSGRERA2eSwcyolFR3CqRRSaLSAaBfVZ66VaTSL+c0hH5OBG5dTpUf+nWRg+db6UGN6tz8yonq0IbIAAABBgEQgAACC0io2lxNC2OfjmF5zXTujJaX8qezro0lo8T/ehglya7xzMvNeFxzteVMX5xd49GHp08Kmvy8mYvNXtY58lCdU6vn0MbIAAABC4EQgAACHWcqF0hkZFHvzClZ+dQx4nONDKXRk71wn+sozXw4q0/OYzIBwAAAxUCIQAAhBafXUZfOnalONd5JhgAAIBggkAIAAAhwaVRP00qAwAAMHAhEAIAQDDz77ITAAAAAQ6BEAAAglBBC20sZxsq6Lg9cBemBwAA8DsEQgAACEIz1mOKFwAAgKsT/F0AAAAAAAAA+AcCIQAAAAAAQIhCIAQAAAAAAAhRCIQAAAAAAAAhCoEQAAAAAAAgRCEQAgAAAAAAhCgEQgAAAAAAgBCFQAgAAAAAABCiEAgBAAAAAABCFAIhAAAAAABAiEIgBAAAAAAACFEIhAAAAAAAACEKgRAAAAAAACBEIRACAAAAAACEqEAMhFzXiYgY83chEDwYY/T1r1awwJUCfS4orxQAAAC4gkAMhJqmEpEkiv4uBIKHIAhEpOmavwvpS7hSoM8F5ZUCAAAAVxCIgdDj8RCRLMv+LgSChyTLRKR4FX8X0pdwpUCfC8orBQAAAK4gEAOhy+kgIoPRhK5w0Fdk2UBEbrfT34X0JVwp0OeC8koBAACAKwjEQOjxuL0eDxMEk8ns71ogGEiyLMmyrutuV1B9zMWVAn0rWK8UAAAAuIJADIRE1NLSSERGkxnd4eAbYoxZLFYiam9r0YNuqgxcKdBXgvtKAQAAgMsRTZZwf9fgg6ZpRNxoMssGg6ap+HQC14cxZg0LFyXJ6/U0NzX4u5y+hysF+kTQXykAAABwOQEaCInI6/FIsmQwGA1GIyfSVNXfFcEAI0lyWHi4KEmaptnra4J1Jn1cKfANhciVAgAAAD4FbiAkIrfLyRgzGk2yLMsGIxME4pyIiLifK4NAxRgTRdFgNJrNFpPFwgTB6/XY62t0LZin0ceVAtcqNK8UAAAA6IlFxCb5u4arMBhNkVExGCIF10rX9fa2lva2Vs5DIhfhSoHrE2pXCgAAAHQ2AAJhB6PJZLGGybJBFKWOpZMBeuJcV1VNUxSXy+l2O0NwTB2uFOgNXCkAAADQYcAEQgAAAAAAAOhbaEAAAAAAAAAIUQiEAAAAAAAAIQp/wrB9AAAgAElEQVSBEAAAAAAAIEQhEAIAAAAAAIQoBEIAAAAAAIAQhUAIAAAAAAAQohAIAQAAAAAAQhQCIQAAAAAAQIhCIAQAAAAAAAhRCIQAAAAAAAAhCoEQAAAAAAAgRCEQAgAAAAAAhCgEQgAAAAAAgBCFQAgAAAAAABCiEAgBAAAAAABCFAIhAAAAAABAiEIgBAAAAAAACFEIhAAAAAAAACEKgRAAAAAAACBEIRACAAAAAACEKARCAAAAAACAEIVACAAAAAAAEKIQCAEAAAAAAEIUAiEAAAAAAECIQiAEAAAAAAAIUQiEAAAAAAAAIQqBEAAAAAAAIEQhEAIAAAAAAIQoBEIAAAAAAIAQhUAIAAAAAAAQohAIAQAAAAAAQhQCIQAAAAAAQIhCIAQAAAAAAAhRCIQAAAAAAAAhCoEQAAAAAAAgRCEQAgAAAAAAhCgEQgAAAAAAgBAl+buAXhFF0WA0iqLEGPN3LQAAAAAAAJel61zTVI/bzbnu71quLtADoWwwRERGG2SDoipc55xzf1cEAAAAAABwWYxIEEUxRnI7nS3Njboe0LGQRcQm+buGywoLt4XbIjwut8fj9nctAAAAAAAAvcUEZjKZZdnQYK/zej3+LueyRJMl3N81+BYWbgsLtzna2lRV8XctAAAAAAAA14KTqig6122RUR6PS9c0fxfkW4BOKiMbDOG2CEdbe4A3sAIAAAAAAFyO4vW6nI6Y2AQmBGjyCtCyIiKjPS63rgdojAYAAAAAAOgNxevVVCXcFuHvQnwLxEAoiqLBYAi2cYOGW/58Nrey4P2nUnvxnF/TzsEhBB8yAAAAAIQGl8tlDQungFwxIRA/fBuMRkUJjHGD0k0/33OusiSvsiSvoujc+RPbv/zLswuSxT6+FzH9B5+drSw+8upCw4UtektJ9qkTJ8/X9e3o004Pp7I4p+Ts3u0r//OBUWEB8YvZTw8ZAAAAAMDfuK5rimoymv1diA+BuOyEKMo8sIYOanVn959pjBgxaeyEW3/wulQ25+nP6vt1/Qv18K8fvP/X/XV2re7s/tP1huTRE7PmfOfXI8KaFv94c0vXxyOKonZjx73270MGAAAAAPAnXdNFWaLA6wQZiC2ETGABttygeuLv//Lww/ff9/uTCjHzsOGDRCIiY/otL/7108PZp0tyD+5+76X7siyMiMThD//poz2HDucXnCs5u3fHypfuy7riNwHSyP9vw4b/mCARs9371unKkrNfPjNE7Nx/0rDkb3l5lQWrf/bYjz/ee+z8iS///sT4tOnPvLP9cGHOvo2/Xp4hXziT73ou83Ae+e4ji+/69WGFhLhZ88dIF3tsrv7Fk//xyZ6jhdt+NF4i05AlP3ljzZHTp0vzDh9Y+7tnb07s+P7AkLrg+dc+3H/iVEn+8RPb3v7BeOmy9y4lL/3JG9sPHy85fzrv+M7tq/9jWYLge2OXh3zLn8/mVp7/9H+f+enqXUeKcg9u++MDWaaO4lnklCff3HKwMPfA9r8+89T/bi4tOXfkF1MlIiLDsj+drCg5s/6pwYH4aw0AAAAAIYwTFwJyXplArCkgMSZFZ6RHC8SdBXnlGjHb7JffffWHi9Nad7/75w/PGqc+9Nt/vLwshhGLyhgi5W5677Xfv77qqDt99kO//tP3x1+hIVZvPPbZZ4frNeKegq2r3nx75WfZLT6aR6Wxj/9wllpc6Y7IuPXf39701wcTyvNqeMy4e3/642WRjC5fz+UIpuRRw+MZEXc6nBfztzTusecXsOxd245Xe203/2Ll7//plhEsb8uaHRXWccv+7e9//9FEEwuf/YtVf3r+9vHRDYfXfrLpaEv80HjhcvdunP3Przx1c2rjV3/9w1/e/uxgpSk1xep7o48KpdEPPZJZun3rGUfEyG/9+D/vimdELGrRy3/+0a3Dw5vPHDgtLvvXb6f2df9dAAAAAIAQEohdRgOPcckfjlX8gYhrdQf/9vxLX9o5i1jw4F2popa76sc//0eRbq1MWf+rRUsevfXXG1ed+OVd93gVkgwm40flCV+9six9ytRE4VRdp9PN/tH7L0wzEhH37PnV46+88UbWkjunxnpOffjKz7Z7iYgMPUrgLZ//+4ofbkv9t40fPzvcbP/oyeW/PDvz/+1c+UBU1sg0cV2L9bL11PaIl8Ylfzhe+YeOn/W2I6s/Pq1e/GbAsevnD373ozqdWMTy1+5KEbXid55+6NfHvdZbfrvl7XuGPXj/lLcP3H/PYEmv+uiZu17a2caJREnSbbf7vvdddqORcaXVXlGUnbP5oz/+t92lk3mEj40+HrJu/+Tfv/dvO71TadonTyRnjRoqUZ1p1reWxAla2cpnVvzysDf2vje3/G6h6eIB6qlVLz33ldCQ3RBYDcwAAAAAAIEKgbA3tMrDm46rY+ZPT4sdPW18gmFnjTcmMc7ISBr5zLqjz3y9W8rgZMEccfdLLz27bHyqzSB0tHupZkvXzptCZNrECeONRMTdFZG9m9JFLz+b5+B6W3OrTlzPO5PnJb2t1cEpSjZIRMJl66GegVCrO7v/dI3idTUWH9/24epdherFPKYVHTjSoBN9fUK9tKhYISJ3YUGVTrERCYmDkuKNjLT8k6faO2KXpqri5e7ds/ad324b+8KCh1+Z+ghx3Vm29RdPPr9qj6+NpT2f9Yq8IjcRa29zcCJZloiEiPgYIyOt7HyRl4g3ny+06wsHff0cVR5a//GhXj2dAAAAAABACIS9o555/z+/v85w62/X/e3uCT/8+Yov7n2rvqbew4ny3vvX/9lm70hGTNJqi6KX/+5/HpgsFa3/j+c/zXNPfO7v/zrHQNQ19Lm+eHboF53+LXKdExFjV+jAy1VV5USccyLiqqJ2vVlv8F1Poa+JYdQTf/+Xxz9zXP5eLp3QOHhIukRNinFIRrJAelNtTUVNvYeTafi4sdZPv2qnjhbCy967s+3Npxb/I3LQsGHD5zz1s/9Ysujpu0d9+KvTPjb+/v9v786Do7juPID/untGo/tGF0IIJIQubmQuA+a+ZG6wcRwcHMdeO97N5vCmdiubrVpvtrY2u5tK4i2bVGyvQ4jNaWPMfSjchwAjCSQBQuhG90gjIc1oZvrtH0IwM/3mkhAzYr6f8h+upqf7937vvd+bN5eU0chMJiJi9OgNP7m9sdnAKCBx9Cg1NRvDx6QOs8iZmJCzbHqi2Fp04lRZF94kBAAAAABwChtClzHt0Q/+dH3Fz6aM/+5bs7/4h7yd++rmbUpb/oN1XYdv60MTUibOGlvyT6s/6P3rIowJmojMBYsn+gvk9AdTZW1Ts5EJQXPf+fd/m1GTv/33+6rdDk7Hj2fV+f401eKCo1/buj3uTFPywiVRQk/Zzp35zWVsb/ULr47Y+NHeuEP5zYGp2bo/bvi5nbvnx/3iwI9jr1+9U6MV0hJDBCbr2nWq2b84qDjIKNaVsDrPfnOkafG65O9u3ZFwsSP1hZkai39UTdz8q9+9qLr2q+Wny6qwIQQAAAAAcAo/KuMG872dHx5skaXY1X+zJqnj1D+/+uPfH62Jmv/aT//+9Y3zUkzfHsirMDXs++/3v7nVlpj7y/ffndV4/mKHC38/g3Uc3fpR3r3OsAm5W7738pzE/nQKa+fG0/+/HMHaT/1y888+OnFXylq6ftFI/c0j//PWm/95Tc90Z3/5nb/9zYGittgZ6zYunx7dUtko27s7a7xTakyev37LT3/y5tL45ktf/OvPt1WaeAddDJS1Hf+Xd39zuKwzPPO59O79v91TKxOZzV71R0oAAAAAAIYMISw63tMx2AoJC/dTa/TdXZ4OBLyQEBwS1NXRKRORGPfqZ4f/Y7bqyvvL1n5cjU0hAAAAAHgt/4DAHqOho73N04HYwkdGYWhRz3l//99p8vKKWwKylr08K4C1Hv/zwVrsBgEAAAAA+gEbQhhazHU3b4tbcn+wKFjsarh98tM//tcHe+5jPwgAAAAA0B/4yCgAAAAAAMDg8tqPjOJHZQAAAAAAAHwUNoQAAAAAAAA+ChtCAAAAAAAAH4UNIQAAAAAAgI/ChhAAAAAAAMBHYUNonxCUteZHayeECo+OiMNnb3l73gg7f6tDGrPk7fUZmqcUnXNi1JjnMqN9p4el9BXvrEqV3OmIJ9VlrqTaU93xqI1Seu67a8dIbj7crbD718Zne6AOcIxZJqd/PegWp7cQRy54840Zw0QnR976xx99f0HCw2NC0LiXfviTn2+YaFFLvUr/RqCTnhX8M9d+Z26i6DgbUnjKzLWbXv/hltff2rz5tZUvZEWqehP43ttvvr3l++++8fp3F2YNGxp/HurZnsj99mhhelKeVE0YSGka0H0dPtbbRtETrLqP12Je5p/CE0juLayGk5c9iYWny3umnfdhXXeLq6IzMsL6nsWoErPHyCXFtSb++XL1xb0nK4xPLT5nhOjUqRlRT6CQCaLopU/k+FzviCfVZa6kmn/OoOZWEEVhoG10axT1b8i596gnkrGnOKSfXv69aZ4ybZMhJSNJTUQkhKWlB7e1eE9lVHhipdKSJml0ZE3ZfZnsZ0MISl30ypyoypOff/jpJ1u3/eWrws7AULVARMS017/c+unH/7vtYHXsvMVZIV7Tsw6GWT/T6E3jdkh4UsPV256x9BqUyTgU9Kc7nsTcsUy4dw4JeFqGxiuP/ZAWKr+XZZgSZSKiqy2qX9/U3Na5u/tl+ntFFXPnpEfnX2ySifySstL0pZ83yUQkhqXNXzgjNUQi9qAy//jx4hYjiSOmr51Q9cnuEoMYlDxz3qysKJXZzPTleTvOV5uCkmbOez4zQkUi0905e/DivQ6rP6YuRmUtXjohWiNKKtZecubo2aouRiRFZC5dMn2E1N3RVtnkPymg4KN9ZWaBcykpPfedHP11rX9kYECIvzb/65O3ukbMnJWkCR229jvjTXVXDt+KmLckO1IwM5Harh06cK3V8vZSeu4700xF7aoQdUCopvXqwbzS1t5r9hTo/CMDeiqOH73eGqJsMrnUUqZOmLTE6u5ayfaIVTy8bAiBE1e9Enf1k8PVMpE6M/eN1OI/fF1ulsIzFi+dOcrP8EBbUa/prY0WHcHpJqu0951pUiawTealhXHCOGy2SHX+/ryKHuVY8htpec7B+9lvWOS2kGUoe5/Tp23KTLbKii6oS7HquKKIvjYSUUDSzPWTR0YE+fVUnt+fV9oqE2842Qt7/yltsoN82pz816Y42ytT9LR1K5NK9+wpapdiZ2xaFnF516HyaOfZ6x2ijxt17Hbii8rBQLxOtH+Ro9dbApRt5449Xto5Q4vXZbLjMcaf43aHDZEmYerqSWkxIf7GytNf9o1SJ/PU3tzh3JqIcwtehzjBuipKtCnpozQVt40RGWliaWlzzmgH5/MLoLK8mAeh4LgyyB1VEt7wIFInjYqqKWkwO8iGGDH+udGNFz+91tDNiIiZ2iuu5BNZvk7LDI3ldYbM8DBB0Mc7qplWBrJwtPFrgs0w45QstdPp7+5k5JQ7gbdUcXvH1frpuAC6MEr5OeQtTBYUY+Y6m/LqqpBTfz5ZaSISQiavfimxaNv+MtNYxys7vybwepCXzN7StKc8cf7KnOEiEQmasJjgyq9/d+Se7EJaFKuJi7O47lE+w8csWD1VuHzoeHFflXFrxeFNPf4I4fYy9yA3WvdLIj8Vjh/ieKWw0N+FjHdXmyWmZuyjGN6e1HFVH5caE6zW3Th2omX0vJzkqGCx4fL+fQXNJnLyzAGGpGdzQzghwrxrzgNN34tMi+ONc2OMG04HFWjdfN2pp6K4bNGC9PjLTbUsIDVzpLbkXItMJIROWjhv2L3dH19rkcOz16xf+lzj5+ea+x4khIxbtHjU/a//70C9gYn+/mqTEDxu/pyIkq8+LuuUxdAJK9bPT7n/9R29xfxkurundhZ3GxlJkVNfXpGTsP1ULQubtGCWf8EXfyjpEMInbnhF6iYi/qWMREKodH/PgTNdQsT0DWtyEu4cqzx/rmpcdvnePbeMpBqzapFw+bNtNw2MRD+NoJy4QriqfveBvz6gwPSlLy/Ort1R2EUkRKoa9u4//YARCaFTlE1uCXKppfdG5Ey1vruUYnvECjcbvP4RQicumB1avGtroVaMmvrSS1KH9b/yusle0VIksIaXliKz8pE9lqm2w/ocKT3bIrckqJXtlXkh1Sfb5k052IisOo6kiMdRiLFhDz7b/ecWipjy4obF2bU7ipjjkWkVthA6Za2jfFqfHDw+V3nl5vwjlxLXLZ2uzQ+aN6Y+b+etB4w9cJ49smmUEJjoaifK9i8SPJ7TdgNn7InKtNurANxRZD+82hDOHHc0bMSYsO4/7dmmpbi5m1Y8GqXO5ik3VbzyQkSkvEV/1nmhp+pGbfakUQFlrRnpPaX72hNyHJ3OnfLKQhoyfhAKjvNB3hLsqOBLiuFBRKoRaTH3S06Yend3/GyIw+Ij2mvrDQ6eKYqBI8aO0LR+28a4d+GnfmALR22gvTOdlCzn019v3VJnk1HZjyTxarLg6mTk1E+nS7OzUcot1LXBjhYm3piR5ZvXWjZNGuVfdUcvRGVNCC07fs/ASHKysnNrArcH+ckkImKGuyd23SUiVfTkDbnG61erzfzaaJMWxWpS2OnSLH74cE3c5EW5oxuPfXWxsvvxhd1acXhTjztCeMtcmYp3UM2Lth8l0d5QcdHgLGS8AGyWmDFjH/dvTGjHZ7u2tfulrdy8KvfWNzu+ONUdNuWVjc+llBy8ZXRr4sAQ8WxuCN/LNGist34aid7LNLx6LtDNK5nqiovl3OzhF+paU8clNBTldTAiUscnxzbc+KbFSERtpQU1s3MSAs839z2hUiekxDcVHG4wMCKS9XoDqZNTR4REBazYNImISKVhhpAggawmjyoyY960tGF+zCRrokI6ozRCrTluZPT94rIOmYjaS4vrZo4iItVw3qXaiOT6isouRsR0zW1+w4MlIovZLzdXN8bOWjY/4l5NVWV5dZuyoXJd+b0HjIi6yu82LR0Tryq8SyTX3us9aKfJOtdaqry76CQeTjb0vO5RxycPqy/arzUTmVtvFtVNS7b5V043ddqpWdwEKtJSVMN/tNsscsttbzcvJGUm/RRdQJLNxS1vWlNa3GomIu2N0obZKfGqEsHpyHzMrXzyB6pe1hUfOpX4vbUr9Fd2bat0a/2w1yircxzNApuL8CM0cPrCoEy7vQrgOADFv6p5c9xxEm6XaM1E1FTX7De+b5Q6mactvCcCdm/NvYX7mKmmuHze9LFjtSm60t06luD4dF4BVIxtv+RBKjgWaeEWOocFn1dd1cNHxzWWH3307QI3s0EkRE5a+06mzJihqezokZudjFxvwsAWDvtnulCyHnUnf/pbT19nk5G/bClqcqng6mRUXlDtSpwWzXKxUDtemIg7ZrpuFVY9P2VsaNnN8OxMVrqv9uFrjy7UNJsJ60YyHxOCUpYsy27J23Wl2eRaWhSrSeEdl2YxSURCTM7aVZ1Fe78qaLLzDRwiF1YcF0cId5lTRXMOqqP566n7JdHJBHFicBYyNwIgIrn2zq02mcjQ1NCu19+tesCIdA0NxtRQf4GYexMHhoZnc0M4OYrzPg73oFNy483b3S9njvy2KTO29vo+O2/7O5kGAhE1XT2w55q957NiwvNLsg1Hd/6pVs+kUSu+P1kSicy8K/MvJRERk3tLBmOMCYJovSHUXtv3WXncyKTEpNlrZrXkbT9SYfuytCiIAhEjEqTHe2nZZDdn/JbYaani7g7j4WaDGBMEevjRG0Hs+1AVY3Jfu2Uzc9IPjv+Zm0BFWvhh9MPj3PLbywtJ2Y913Gs76jgrTkemQ44eY/fKUuiwSEHf4xcUpBbI6NaO8HGj7PaCohPtX4QboTic0xcupP3RJRxNQzvhuZV62dw33GX50fWdzVP76XLpFv1kbiy9Hbh+SUTl4YvdzM5bug/ZL4BOPJGC4xD3NKuDnOpqih+d0FR+xvLTz5xsyE31rWHD4zSCtltxF9b67ZefXGiyGD3uNaH/C4f9M10pWQ5vZ8vJZOT0o4nsLFXctrtWP10ugK4XaqcLE29FNlZfvzlr8fjh+siUtus7Hn8g2HFJIeWEdSeZD6ljZy6fG1jw5d7ed+v6ty64MYtZZ2OdlJA8Iry4qdmNb6zZRsObeqQcIdzm+EXbOchhk2EhJH3J4glRdkojay345q8d0xxPEKctHYyFrI8QNn7t6pwYieT6C385dMteDH2tls1y3/+SLMskigN95gBeCj8q44zcUlLSljwrd1zY3eLyhy+AGO9XNMRmZURIRFJYxoREXVWdxU7RWHu3btiECbEagYjEgACNaKy9Wxs9aeqIQJGISB0SFxNk86UCPz91l7bNwEgISEob1fuVA2N9VUt8VmqISCSFpWcmqB5e3MmlHmFGk9lPoxGISAqODBHa75cV5p85V0mxw5SPkRIzMqNURFLkuPSY+qr7ti/bcZvsYkuVd3cSDy8brEfXQdFRwQKREJA0OlbsjaqyOSZ1ZIBAJAQlp8WqnMdsJ1l2KNLCDcMy1UTq2PELJg33t02x1TnWeO3lh6PIm7ILHDVHTEzPjJSIpIjs9Nj6qvsm58PJImzn+bQ8mXtlwT9xdu7YpkPb914Pn7ssI1R0NXs2QXF7wU38CHl9wUn7wIdWbwy8OW7dVPvDhntBXmD8ueP01gMmNxecOXfhbP5di52Lnf7lFkBeeRmUguNskDvubuXFxbgxw1vLqq2/DavMhqwtuFIRO33h5NgAkYgEVVjy1JxRAfy+5jWBn8wBLhwuncktWU6nv30u9iMRpya7Phm59ZMXpxujlN8chwsTNxIikpsLbxjGL507oqawxN4HWYic1wQ3kklERGJI5sLlafeP7C/Smh1cwZZiNXFxFhMRUVfl6R0nm7JWrJwWq3ZvMjpNI2eE8Jpj76AL6ynrKD28Z8f2Xfz//nKiVMdcHioD5/pC9ij+9sI9n3384Scfbz1Y3MHcXGIc3VTQRCaNiQ3Gb0QNVc/mO4RXWqW5MbZbmiut/fvhKtZxq7Bx1vLwomNVfS9lMd23J/IiF658c6IkCF0V5w9fbn78iXxinYXHj4TMX/j691QmE+u+e2LH+ZrCYwcC583Z/JqfLAtkaLhy/FCj5SsrcvXli1nLV65LbtOb9Ybm3n0na//2xIXYJRvfnKp/oK1qauqRzIxYJ+9S/MBrS26ICza+Md5QdeVyz7gZYwIERqKsK827pFV84sFc3xr4wobNUYF++srT+292MLLOFr/JLrW0yRQ1Yclcy7szVZLNEat4uNkgc+WVc5lLV786UtvZ3WbUMZGImO76yQsxC9e+kqXrNnaadGbBecxuUaaFOGFYpLrywp5LIekZsVfP2i7olud8WeW8vRyCyjaTMmOKLrhvvzlyQ1vQvI0WzWHkZGRahb37uJN8Wp18TDkSKGXxwoQ7R3aVP+ipOJa/bs3SnMY9l5plF7Jn2y+8XnATfypx+oKbdkcVwI0YeHPc+gy7w4Z/Qf6Y580d7q1dWcqFqEnrf5jd2/XmqjOfF3COPIymo7rwEhE9To0QGM/rX34B5JWXwSg4zge5o4KvHB4UkzWyvfyC7Rt4ymywB3eOfs6mvTB/04wgiZi5s6H0/Nke7tjnDEISQrjJHODC4cqZ/JLlZPo3OngzgXdTZT/KJHJqMiMXJyO/fvIa68Yo5TfH4cLE700iYrpbNxtmz2i7cc9g99LkvCa4kUwiInHYhOfTAsSG2Rs3EhH13Du983Kds3WBOKuJ3O3aLO5doZi+5sLOIznrlq1RH913ru7RbHFjxeGlkT9CeM3hjnN70brJ9aEycC4vZPYebzmc7g3ophSa9sKLEed/e6isPx/HA48TwqLjPR2DrZCwcD+1Rt/d1e8rjIsw757zwN9iSdCbaf3poCJ3f1TG0yS1WjYaGYnBY1/ckF29a+81Ry8c9v826blvZ976cO8dzGJL/UqL4J+17MXQS3sucL+4BY75YPae0hz3jlv7RP+KcTM3zen4alfRIH+aykEyPTioBtdTWao8N0o1yYu2TGvbuSvf/i/IgmN4MgNezz8gsMdo6Gh38E1wz3g23yEs0krLTwa/l6WfGmUmoist0q9v+t/tGHKfj5Xip708N1nFJD+VofLS0YJnZFF/pjH9zYO7PB3EkOV72fPgHPfArX2if+X689t3PoX72E8mFo4B8cgoFULGL1n7fHx3wZFTyg/wAAAMumfzHUIAAAAAAADv4bXvEA65N80AAAAAAADgycCGEAAAAAAAwEdhQwgAAAAAAOCjsCEEAAAAAADwUdgQAgAAAAAA+ChsCAEAAAAAAHwUNoQAAAAAAAA+ChtCAAAAAAAAH4UNIQAAAAAAgI/ChhAAAAAAAMBHYUMIAAAAAADgo7AhBAAAAAAA8FHYEAIAAAAAAPgobAgBAAAAAAB8FDaEAAAAAAAAPgobQgAAAAAAAB+FDSEAAAAAAICP8sYNIZNlT4cAAAAAAADwxAjeus3xxg2hyWiSJMnTUQAAAAAAADwZoiiaTWZPR8HhjRtCvaFbUqsE0RtjAwAAAAAAcJfkp+4x6D0dBYdXbroY6+rs9A8I8HQcAAAAAAAAA+Wn8TcaDGYZ7xC6rEPXplKp1Wo/TwcCAAAAAADQf6Io+gcEtLe1ejoQPi/dEMqy3NLcEBAUpPbDnhAAAAAAAIYkURSDgkM7dG1Go9HTsfBJ/oEhno6BTzabewz60PBwUZTMZhMxTwcEAAAAAADgMj+Nf2BwcGdHe2eHztOx2CWERcd7OgZHRFEMC4/wDwwyG02yLDPmjT/VCgAAAAAA0EsQBFEQJT+10WBob9MajT2ejsgRb98Q9hIEUeOvkSQ1/hwFAAAAAAB4M1k2m03mHoPeO39FxobK0wG4hDFZ391N1O3pQAAAAAAAAIis5VsAAAC8SURBVJ4dXvqjMgAAAAAAADDYsCEEAAAAAADwUdgQAgAAAAAA+ChsCAEAAAAAAHwUNoQAAAAAAAA+ChtCAAAAAAAAH4UNIQAAAAAAgI/ChhAAAAAAAMBHYUMIAAAAAADgo7AhBAAAAAAA8FHYEAIAAAAAAPgobAgBAAAAAAB8FDaEAAAAAAAAPgobQgAAAAAAAB+FDSEAAAAAAICPwoYQAAAAAADAR2FDCAAAAAAA4KOwIQQAAAAAAPBR/w8Ss0KucKS9tAAAAABJRU5ErkJggg==)

* * *

## The Platform Question: Build vs. Buy

There are two roads here. One: use an integrated platform and ship in weeks. Two: assemble your own stack and own the optimization but deal with four vendors at 2 AM when something breaks.

### Integrated Platforms (Ship Fast)

**ElevenLabs** is the premium play. Their Scribe v2 Realtime STT runs at sub-150ms. Flash TTS delivers 75ms to first audio—the fastest on the market. The voice quality is clean, the infrastructure is solid, and the product is polished. But you're locked in. You can't swap Deepgram for speech-to-text or use Cartesia for TTS instead. You take the whole package.

The teams that win with ElevenLabs are usually optimizing for quality first. They want to ship a voice agent that sounds professional, don't care about shaving milliseconds, and would rather have one vendor to call when something breaks. Larger organizations and companies where voice quality is the whole product fit here.

**Retell AI** starts at $0.07 per minute and markets itself around conversation [orchestration](https://www.maximem.ai/glossary/orchestration). The latency is solid, not exceptional. The voice quality is respectable. But what actually works here is something different: Retell lets your voice agent hook directly into your business systems _during the call_. Your agent answers the customer, pulls their account from Salesforce, books an appointment in their calendar, all while the conversation is happening. Retell handles the [integrations](https://www.maximem.ai/glossary/integrations) you'd normally stitch together yourself.

This matters for mid-market teams. You're not trying to compete on latency with ElevenLabs. You're trying to build an agent that _does something_ on behalf of your business. Retell's architecture assumes that's your goal.

### Modular Platforms (Flexibility First)

**Vapi** is the opposite philosophy. They're not a platform—they're glue. You choose your STT provider (Deepgram, ElevenLabs, whatever), your LLM (Claude, GPT, whatever), your TTS (Cartesia, Inworld, your pick), and your telecom stack. Vapi orchestrates the connections between them.

The advantage: total control. You want the cheapest STT, the best-sounding TTS, and the fastest LLM? Vapi doesn't care—you build it. The disadvantage: complexity. When your system degrades at 2 AM, you're now calling Deepgram support, your LLM provider, and Vapi all in one go. You've traded speed-to-ship for speed-to-scale. Teams with specific vendor requirements live here. Everyone else usually regrets it.

### The Speed Player: Cartesia

**Cartesia** obsesses over latency and cost. Sonic Turbo delivers 40ms to first audio—fastest TTS shipping. Sonic-3 runs 90ms at one-fifth ElevenLabs' price. Their STT is $0.13 per hour, the cheapest streaming option I've tested. But the real differentiator is something else: their Sonic models _express emotion_. They laugh, get frustrated, shift tone. No other streaming TTS does this at scale.

If you're building for India or Southeast Asia, Cartesia supports nine Indic languages. That's not a nice-to-have if your market is there—it's table stakes. A voice agent that can't inflect naturally in Hindi or code-switch between Tamil and English isn't really an agent in that context.

Cost-sensitive teams that won't compromise on speed or expressiveness start here. You'll spend maybe $0.02-0.05 per minute all-in, which is less than a third of ElevenLabs. The tradeoff: you're with a newer vendor and you're betting on their infrastructure scaling with you.

* * *

## Indian Market: Entirely Different Game

If you're shipping to India or serving Indian diaspora, native language support isn't optional. Two platforms own this space completely.

**Sarvam AI** built a full-stack sovereign platform for India. STT, TTS, translation. Eleven Indian languages plus Indian English. They stream via WebSocket and price at roughly ₹30-45 per hour (about $0.01 per minute all-in). If you're building for India, this is your baseline. Everyone else charges more or supports fewer languages. This is what you measure against.

**Gnani built Inya VoiceOS**, which breaks the traditional STT-LLM-TTS pipeline entirely. Audio in, audio out. Direct processing. Sub-second response times with natural prosody. They handle something most platforms can't: code-mixed speech. Hindi-English mixing. Tamil-English. Real-world speech patterns that don't fit Western phonetics. Zero-shot voice cloning from ten seconds of reference audio.

The choice here depends on your requirements. Sarvam if you need reliability and breadth across Indian languages. Gnani if you need to support actual Indian English speakers with natural prosody and code-mixing.

* * *

## Agent Frameworks and Orchestration

Once you've picked your voice stack, you need something to orchestrate the agent's reasoning. Three frameworks dominate for voice-first systems:

**CrewAI** is built for multi-agent scenarios. You define agents (each with a role, goal, and backstory), assign them tools, and CrewAI coordinates the conversation flow. For voice systems, this matters because your agent might need to route to a specialist mid-conversation. CrewAI handles that routing cleanly. The framework integrates with all major LLMs and voice APIs. It's Python-first.

**AutoGen** (from Microsoft) takes a different approach: flexible conversation patterns. Two or more agents exchange messages until they solve a problem. You define the agents, their capabilities, and when they're done. AutoGen doesn't assume a hierarchy. That's useful for voice because you might have a moderator agent, a reasoning agent, and a tool-calling agent working in parallel. The conversation flow feels more natural because it's not strictly linear.

**Swarms** optimizes for dynamic agent routing. You create a swarm of specialized agents and define rules for when each one should activate. The framework figures out which agents to use based on the conversation context. For voice, this is particularly useful because you can have high-latency specialist agents (like a research agent that calls external APIs) and low-latency responder agents (that generate immediate responses). The swarm routes accordingly.

Which one you pick depends on your team's preference and your agent's complexity. Simple voice agents don't need orchestration—a single LLM with tools is fine. Complex multi-agent scenarios that span domains (customer support + billing + escalation) benefit from structured orchestration.

* * *

## Bringing It Together: A Production Voice Agent Stack

Here's what a solid 2026 voice agent looks like:

**Speech-to-Text:** Deepgram (if cost-conscious and latency-focused) or ElevenLabs Scribe (if you want integrated quality).

**LLM:** Claude via API (or GPT-4 if you need specific capabilities). No embedded models. Real-time latency demands cloud [inference](https://www.maximem.ai/glossary/inference).

**Text-to-Speech:** Cartesia for cost and emotion, ElevenLabs for polished quality, Sarvam if targeting India.

**Orchestration:** CrewAI if you have multiple agents. A single agent with tools doesn't need orchestration overhead.

**Telephony:** Vapi if you want flexibility across STT/TTS providers. Retell if you're building business integrations. ElevenLabs if you're optimizing for quality.

**[Context Management](https://www.maximem.ai/glossary/context-management):** [Synap](https://www.maximem.ai/synap). Your agent needs to remember conversation history, customer preferences, account details. Raw conversation logs cause [hallucination](https://www.maximem.ai/glossary/hallucination) and irrelevant tool calls. Structured context from Synap changes the conversation quality entirely.

This stack costs roughly $0.04-0.08 per minute all-in (depending on your LLM provider and voice quality choices). It supports multi-language, handles edge cases, and scales.

* * *

**Get started:** [Vapi documentation](https://docs.vapi.ai) | [Deepgram API reference](https://developers.deepgram.com)

**Read the docs:** [Synap Docs](https://docs.maximem.ai) | [CrewAI Framework](https://docs.crewai.com)

## Related posts

[Why AI Forgets: Why ChatGPT, Claude, and Gemini Don't Remember You Well](https://www.maximem.ai/blog/why-ai-forgets) May 10, 2026

[Image Processing for AI Agents: Embeddings & Vision Models & When to Use Each](https://www.maximem.ai/blog/image-processing-ai-agents) May 15, 2026

[MCP Servers Explained: What They Are and How AI Agents Use Them](https://www.maximem.ai/blog/mcp-servers-explained) March 27, 2026

---

Source: [https://www.maximem.ai/blog/voice-agent-stack](https://www.maximem.ai/blog/voice-agent-stack)
