Spaces:
Running
Running
File size: 9,187 Bytes
2a08875 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 |
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"**Links**<br>\n",
"Extensions API GitHub: https://github.com/SillyTavern/SillyTavern-extras/<br>\n",
"SillyTavern community Discord (support and discussion): https://discord.gg/sillytavern"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#@title <-- Tap this if you run on Mobile { display-mode: \"form\" }\n",
"#Taken from KoboldAI colab\n",
"%%html\n",
"<b>Press play on the audio player to keep the tab alive. (Uses only 13MB of data)</b><br/>\n",
"<audio src=\"https://henk.tech/colabkobold/silence.m4a\" controls>"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "lVftocpwCoYw"
},
"outputs": [],
"source": [
"#@markdown (RECOMMENDED) Generates an API key for you to use with the API\n",
"secure = False #@param {type:\"boolean\"}\n",
"#@markdown Allows to run SillyTavern Extras on CPU (use if you're out of daily GPU allowance)\n",
"use_cpu = False #@param {type:\"boolean\"}\n",
"#@markdown Allows to run Stable Diffusion pipeline on CPU (slow!)\n",
"use_sd_cpu = False #@param {type:\"boolean\"}\n",
"#@markdown ***\n",
"#@markdown Enables the WebSearch module\n",
"extras_enable_websearch = True #@param {type:\"boolean\"}\n",
"#@markdown ***\n",
"#@markdown Loads the image captioning module\n",
"extras_enable_caption = True #@param {type:\"boolean\"}\n",
"captioning_model = \"Salesforce/blip-image-captioning-large\" #@param [ \"Salesforce/blip-image-captioning-large\", \"Salesforce/blip-image-captioning-base\" ]\n",
"#@markdown * Salesforce/blip-image-captioning-large - good base model\n",
"#@markdown * Salesforce/blip-image-captioning-base - slightly faster but less accurate\n",
"#@markdown ***\n",
"#@markdown Loads the sentiment classification model\n",
"extras_enable_classify = True #@param {type:\"boolean\"}\n",
"classification_model = \"nateraw/bert-base-uncased-emotion\" #@param [\"nateraw/bert-base-uncased-emotion\", \"joeddav/distilbert-base-uncased-go-emotions-student\"]\n",
"#@markdown * nateraw/bert-base-uncased-emotion = 6 supported emotions<br>\n",
"#@markdown * joeddav/distilbert-base-uncased-go-emotions-student = 28 supported emotions\n",
"#@markdown ***\n",
"#@markdown Loads the story summarization module\n",
"extras_enable_summarize = True #@param {type:\"boolean\"}\n",
"summarization_model = \"slauw87/bart_summarisation\" #@param [ \"slauw87/bart_summarisation\", \"Qiliang/bart-large-cnn-samsum-ChatGPT_v3\", \"Qiliang/bart-large-cnn-samsum-ElectrifAi_v10\", \"distilbart-xsum-12-3\" ]\n",
"#@markdown * slauw87/bart_summarisation - general purpose summarization model\n",
"#@markdown * Qiliang/bart-large-cnn-samsum-ChatGPT_v3 - summarization model optimized for chats\n",
"#@markdown * Qiliang/bart-large-cnn-samsum-ElectrifAi_v10 - nice results so far, but still being evaluated\n",
"#@markdown * distilbart-xsum-12-3 - faster, but pretty basic alternative\n",
"#@markdown ***\n",
"#@markdown Enables Silero text-to-speech module\n",
"extras_enable_silero_tts = True #@param {type:\"boolean\"}\n",
"#@markdown Enables Microsoft Edge text-to-speech module\n",
"extras_enable_edge_tts = True #@param {type:\"boolean\"}\n",
"#@markdown Enables RVC module\n",
"extras_enable_rvc = False #@param {type:\"boolean\"}\n",
"#@markdown ***\n",
"#@markdown Enables Whisper speech recognition module\n",
"extras_enable_whisper_stt = True #@param {type:\"boolean\"}\n",
"whisper_model = \"base.en\" #@param [ \"tiny.en\", \"base.en\", \"small.en\", \"medium.en\", \"tiny\", \"base\", \"small\", \"medium\", \"large\" ]\n",
"#@markdown There are five model sizes, four with English-only versions, offering speed and accuracy tradeoffs.\n",
"#@markdown The .en models for English-only applications tend to perform better, especially for the tiny.en and base.en models.\n",
"#@markdown ***\n",
"#@markdown Enables SD picture generation\n",
"extras_enable_sd = True #@param {type:\"boolean\"}\n",
"sd_model = \"ckpt/anything-v4.5-vae-swapped\" #@param [ \"ckpt/anything-v4.5-vae-swapped\", \"hakurei/waifu-diffusion\", \"philz1337/clarity\", \"prompthero/openjourney\", \"ckpt/sd15\", \"stabilityai/stable-diffusion-2-1-base\" ]\n",
"#@markdown * ckpt/anything-v4.5-vae-swapped - anime style model\n",
"#@markdown * hakurei/waifu-diffusion - anime style model\n",
"#@markdown * philz1337/clarity - realistic style model\n",
"#@markdown * prompthero/openjourney - midjourney style model\n",
"#@markdown * ckpt/sd15 - base SD 1.5\n",
"#@markdown * stabilityai/stable-diffusion-2-1-base - base SD 2.1\n",
"#@markdown ***\n",
"#@markdown Enables ChromaDB module\n",
"extras_enable_chromadb = True #@param {type:\"boolean\"}\n",
"\n",
"import subprocess\n",
"import secrets\n",
"\n",
"# ---\n",
"# SillyTavern extras\n",
"extras_url = '(disabled)'\n",
"params = []\n",
"if use_cpu:\n",
" params.append('--cpu')\n",
"if use_sd_cpu:\n",
" params.append('--sd-cpu')\n",
"if secure:\n",
" params.append('--secure')\n",
"params.append('--share')\n",
"modules = []\n",
"\n",
"if extras_enable_caption:\n",
" modules.append('caption')\n",
"if extras_enable_summarize:\n",
" modules.append('summarize')\n",
"if extras_enable_classify:\n",
" modules.append('classify')\n",
"if extras_enable_sd:\n",
" modules.append('sd')\n",
"if extras_enable_silero_tts:\n",
" modules.append('silero-tts')\n",
"if extras_enable_edge_tts:\n",
" modules.append('edge-tts')\n",
"if extras_enable_chromadb:\n",
" modules.append('chromadb')\n",
"if extras_enable_whisper_stt:\n",
" modules.append('whisper-stt')\n",
" params.append(f'--stt-whisper-model-path={whisper_model}')\n",
"if extras_enable_rvc:\n",
" modules.append('rvc')\n",
" params.append('--max-content-length=2000')\n",
" params.append('--rvc-save-file')\n",
"\n",
"\n",
"if extras_enable_websearch:\n",
" print(\"Enabling WebSearch module\")\n",
" modules.append('websearch')\n",
" !apt update\n",
" !apt install -y chromium-chromedriver\n",
"\n",
"params.append(f'--classification-model={classification_model}')\n",
"params.append(f'--summarization-model={summarization_model}')\n",
"params.append(f'--captioning-model={captioning_model}')\n",
"params.append(f'--sd-model={sd_model}')\n",
"params.append(f'--enable-modules={\",\".join(modules)}')\n",
"\n",
"\n",
"%cd /\n",
"!git clone https://github.com/SillyTavern/SillyTavern-extras\n",
"%cd /SillyTavern-extras\n",
"!git clone https://github.com/Cohee1207/tts_samples\n",
"!npm install -g localtunnel\n",
"%pip install -r requirements.txt\n",
"!wget https://github.com/cloudflare/cloudflared/releases/download/2023.5.0/cloudflared-linux-amd64 -O /tmp/cloudflared-linux-amd64\n",
"!chmod +x /tmp/cloudflared-linux-amd64\n",
"\n",
"if extras_enable_rvc:\n",
" print(\"Installing RVC requirements\")\n",
" %pip install -r requirements-rvc.txt\n",
"\n",
"# Generate a random API key\n",
"api_key = secrets.token_hex(5)\n",
"\n",
"# Write the API key to api_key.txt\n",
"with open('./api_key.txt', 'w') as f:\n",
" f.write(api_key)\n",
"print(f\"API Key generated: {api_key}\")\n",
"\n",
"cmd = f\"python server.py {' '.join(params)}\"\n",
"print(cmd)\n",
"extras_process = subprocess.Popen(\n",
" cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, cwd='/SillyTavern-extras', shell=True)\n",
"print('processId:', extras_process.pid)\n",
"while True:\n",
" line = extras_process.stdout.readline().decode().strip()\n",
" if line != None and line != '':\n",
" print(line)\n"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"private_outputs": true,
"provenance": []
},
"gpuClass": "standard",
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|