Spaces:
Sleeping
Sleeping
File size: 44,441 Bytes
cfd3735 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 |
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Voice Assistant\n",
"\n",
"This chain creates a clone of ChatGPT with a few modifications to make it a voice assistant. \n",
"It uses the `pyttsx3` and `speech_recognition` libraries to convert text to speech and speech to text respectively. The prompt template is also changed to make it more suitable for voice assistant use."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"from langchain import OpenAI, ConversationChain, LLMChain, PromptTemplate\n",
"from langchain.memory import ConversationBufferWindowMemory\n",
"\n",
"\n",
"template = \"\"\"Assistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"{history}\n",
"Human: {human_input}\n",
"Assistant:\"\"\"\n",
"\n",
"prompt = PromptTemplate(\n",
" input_variables=[\"history\", \"human_input\"], \n",
" template=template\n",
")\n",
"\n",
"\n",
"chatgpt_chain = LLMChain(\n",
" llm=OpenAI(temperature=0), \n",
" prompt=prompt, \n",
" verbose=True, \n",
" memory=ConversationBufferWindowMemory(k=2),\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"import speech_recognition as sr\n",
"import pyttsx3\n",
"engine = pyttsx3.init()\n",
"\n",
"\n",
"def listen():\n",
" r = sr.Recognizer()\n",
" with sr.Microphone() as source:\n",
" print('Calibrating...')\n",
" r.adjust_for_ambient_noise(source, duration=5)\n",
" # optional parameters to adjust microphone sensitivity\n",
" # r.energy_threshold = 200\n",
" # r.pause_threshold=0.5 \n",
" \n",
" print('Okay, go!')\n",
" while(1):\n",
" text = ''\n",
" print('listening now...')\n",
" try:\n",
" audio = r.listen(source, timeout=5, phrase_time_limit=30)\n",
" print('Recognizing...')\n",
" # whisper model options are found here: https://github.com/openai/whisper#available-models-and-languages\n",
" # other speech recognition models are also available.\n",
" text = r.recognize_whisper(audio, model='medium.en', show_dict=True, )['text']\n",
" except Exception as e:\n",
" unrecognized_speech_text = f'Sorry, I didn\\'t catch that. Exception was: {e}s'\n",
" text = unrecognized_speech_text\n",
" print(text)\n",
"\n",
" \n",
" response_text = chatgpt_chain.predict(human_input=text)\n",
" print(response_text)\n",
" engine.say(response_text)\n",
" engine.runAndWait()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Calibrating...\n",
"Okay, go!\n",
"listening now...\n",
"Recognizing...\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\jaden\\AppData\\Roaming\\Python\\Python310\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" Hello, Assistant. What's going on?\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"\n",
"Human: Hello, Assistant. What's going on?\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" Hi there! It's great to hear from you. I'm doing well. How can I help you today?\n",
"listening now...\n",
"Recognizing...\n",
" That's cool. Isn't that neat? Yeah, I'm doing great.\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Hello, Assistant. What's going on?\n",
"AI: Hi there! It's great to hear from you. I'm doing well. How can I help you today?\n",
"Human: That's cool. Isn't that neat? Yeah, I'm doing great.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" That's great to hear! What can I do for you today?\n",
"listening now...\n",
"Recognizing...\n",
" Thank you.\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Hello, Assistant. What's going on?\n",
"AI: Hi there! It's great to hear from you. I'm doing well. How can I help you today?\n",
"Human: That's cool. Isn't that neat? Yeah, I'm doing great.\n",
"AI: That's great to hear! What can I do for you today?\n",
"Human: Thank you.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" You're welcome! Is there anything else I can help you with?\n",
"listening now...\n",
"Recognizing...\n",
" I'd like to learn more about neural networks.\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: That's cool. Isn't that neat? Yeah, I'm doing great.\n",
"AI: That's great to hear! What can I do for you today?\n",
"Human: Thank you.\n",
"AI: You're welcome! Is there anything else I can help you with?\n",
"Human: I'd like to learn more about neural networks.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" Sure! Neural networks are a type of artificial intelligence that use a network of interconnected nodes to process data and make decisions. They are used in a variety of applications, from image recognition to natural language processing. Neural networks are often used to solve complex problems that are too difficult for traditional algorithms.\n",
"listening now...\n",
"Recognizing...\n",
" Tell me a fun fact about neural networks.\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Thank you.\n",
"AI: You're welcome! Is there anything else I can help you with?\n",
"Human: I'd like to learn more about neural networks.\n",
"AI: Sure! Neural networks are a type of artificial intelligence that use a network of interconnected nodes to process data and make decisions. They are used in a variety of applications, from image recognition to natural language processing. Neural networks are often used to solve complex problems that are too difficult for traditional algorithms.\n",
"Human: Tell me a fun fact about neural networks.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" Neural networks are inspired by the way the human brain works. They are composed of interconnected nodes that process data and make decisions, just like neurons in the brain. Neural networks can learn from their mistakes and improve their performance over time, just like humans do.\n",
"listening now...\n",
"Recognizing...\n",
" Tell me about a brand new discovered bird species.\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: I'd like to learn more about neural networks.\n",
"AI: Sure! Neural networks are a type of artificial intelligence that use a network of interconnected nodes to process data and make decisions. They are used in a variety of applications, from image recognition to natural language processing. Neural networks are often used to solve complex problems that are too difficult for traditional algorithms.\n",
"Human: Tell me a fun fact about neural networks.\n",
"AI: Neural networks are inspired by the way the human brain works. They are composed of interconnected nodes that process data and make decisions, just like neurons in the brain. Neural networks can learn from their mistakes and improve their performance over time, just like humans do.\n",
"Human: Tell me about a brand new discovered bird species.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" A new species of bird was recently discovered in the Amazon rainforest. The species, called the Spix's Macaw, is a small, blue parrot that is believed to be extinct in the wild. It is the first new species of bird to be discovered in the Amazon in over 100 years.\n",
"listening now...\n",
"Recognizing...\n",
" Tell me a children's story about the importance of honesty and trust.\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Tell me a fun fact about neural networks.\n",
"AI: Neural networks are inspired by the way the human brain works. They are composed of interconnected nodes that process data and make decisions, just like neurons in the brain. Neural networks can learn from their mistakes and improve their performance over time, just like humans do.\n",
"Human: Tell me about a brand new discovered bird species.\n",
"AI: A new species of bird was recently discovered in the Amazon rainforest. The species, called the Spix's Macaw, is a small, blue parrot that is believed to be extinct in the wild. It is the first new species of bird to be discovered in the Amazon in over 100 years.\n",
"Human: Tell me a children's story about the importance of honesty and trust.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" Once upon a time, there was a young boy named Jack who lived in a small village. Jack was always honest and trustworthy, and his friends and family knew they could always count on him. One day, Jack was walking through the forest when he stumbled upon a magical tree. The tree told Jack that if he was honest and trustworthy, he would be rewarded with a special gift. Jack was so excited, and he promised to always be honest and trustworthy. Sure enough, the tree rewarded Jack with a beautiful golden apple. From that day forward, Jack was always honest and trustworthy, and he was rewarded with many more magical gifts. The moral of the story is that honesty and trust are the most important things in life.\n",
"listening now...\n",
"Recognizing...\n",
" Wow, Assistant, that was a really good story. Congratulations!\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Tell me about a brand new discovered bird species.\n",
"AI: A new species of bird was recently discovered in the Amazon rainforest. The species, called the Spix's Macaw, is a small, blue parrot that is believed to be extinct in the wild. It is the first new species of bird to be discovered in the Amazon in over 100 years.\n",
"Human: Tell me a children's story about the importance of honesty and trust.\n",
"AI: Once upon a time, there was a young boy named Jack who lived in a small village. Jack was always honest and trustworthy, and his friends and family knew they could always count on him. One day, Jack was walking through the forest when he stumbled upon a magical tree. The tree told Jack that if he was honest and trustworthy, he would be rewarded with a special gift. Jack was so excited, and he promised to always be honest and trustworthy. Sure enough, the tree rewarded Jack with a beautiful golden apple. From that day forward, Jack was always honest and trustworthy, and he was rewarded with many more magical gifts. The moral of the story is that honesty and trust are the most important things in life.\n",
"Human: Wow, Assistant, that was a really good story. Congratulations!\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" Thank you! I'm glad you enjoyed it.\n",
"listening now...\n",
"Recognizing...\n",
" Thank you.\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Tell me a children's story about the importance of honesty and trust.\n",
"AI: Once upon a time, there was a young boy named Jack who lived in a small village. Jack was always honest and trustworthy, and his friends and family knew they could always count on him. One day, Jack was walking through the forest when he stumbled upon a magical tree. The tree told Jack that if he was honest and trustworthy, he would be rewarded with a special gift. Jack was so excited, and he promised to always be honest and trustworthy. Sure enough, the tree rewarded Jack with a beautiful golden apple. From that day forward, Jack was always honest and trustworthy, and he was rewarded with many more magical gifts. The moral of the story is that honesty and trust are the most important things in life.\n",
"Human: Wow, Assistant, that was a really good story. Congratulations!\n",
"AI: Thank you! I'm glad you enjoyed it.\n",
"Human: Thank you.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" You're welcome!\n",
"listening now...\n",
"Recognizing...\n",
" Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way? Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way?\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Wow, Assistant, that was a really good story. Congratulations!\n",
"AI: Thank you! I'm glad you enjoyed it.\n",
"Human: Thank you.\n",
"AI: You're welcome!\n",
"Human: Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way? Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way?\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" Yes, there are several online brands that offer photo editing and other creative tools without the need to download any software. Adobe Photoshop Express, Pixlr, and Fotor are some of the most popular online photo editing tools. Freq is an online music production platform that allows users to create and share music without downloading any software.\n",
"listening now...\n",
"Recognizing...\n",
" Our whole process of awesome is free.\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Thank you.\n",
"AI: You're welcome!\n",
"Human: Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way? Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way?\n",
"AI: Yes, there are several online brands that offer photo editing and other creative tools without the need to download any software. Adobe Photoshop Express, Pixlr, and Fotor are some of the most popular online photo editing tools. Freq is an online music production platform that allows users to create and share music without downloading any software.\n",
"Human: Our whole process of awesome is free.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" That's great! It's always nice to have access to free tools and resources.\n",
"listening now...\n",
"Recognizing...\n",
" No, I meant to ask, are those options that you mentioned free? No, I meant to ask, are those options that you mentioned free?\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way? Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way?\n",
"AI: Yes, there are several online brands that offer photo editing and other creative tools without the need to download any software. Adobe Photoshop Express, Pixlr, and Fotor are some of the most popular online photo editing tools. Freq is an online music production platform that allows users to create and share music without downloading any software.\n",
"Human: Our whole process of awesome is free.\n",
"AI: That's great! It's always nice to have access to free tools and resources.\n",
"Human: No, I meant to ask, are those options that you mentioned free? No, I meant to ask, are those options that you mentioned free?\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" Yes, the online brands I mentioned are all free to use. Adobe Photoshop Express, Pixlr, and Fotor are all free to use, and Freq is a free music production platform.\n",
"listening now...\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[6], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m listen(\u001b[39mNone\u001b[39;49;00m)\n",
"Cell \u001b[1;32mIn[5], line 20\u001b[0m, in \u001b[0;36mlisten\u001b[1;34m(command_queue)\u001b[0m\n\u001b[0;32m 18\u001b[0m \u001b[39mprint\u001b[39m(\u001b[39m'\u001b[39m\u001b[39mlistening now...\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[0;32m 19\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m---> 20\u001b[0m audio \u001b[39m=\u001b[39m r\u001b[39m.\u001b[39;49mlisten(source, timeout\u001b[39m=\u001b[39;49m\u001b[39m5\u001b[39;49m, phrase_time_limit\u001b[39m=\u001b[39;49m\u001b[39m30\u001b[39;49m)\n\u001b[0;32m 21\u001b[0m \u001b[39m# audio = r.record(source,duration = 5)\u001b[39;00m\n\u001b[0;32m 22\u001b[0m \u001b[39mprint\u001b[39m(\u001b[39m'\u001b[39m\u001b[39mRecognizing...\u001b[39m\u001b[39m'\u001b[39m)\n",
"File \u001b[1;32mc:\\ProgramData\\miniconda3\\envs\\lang\\lib\\site-packages\\speech_recognition\\__init__.py:523\u001b[0m, in \u001b[0;36mRecognizer.listen\u001b[1;34m(self, source, timeout, phrase_time_limit, snowboy_configuration)\u001b[0m\n\u001b[0;32m 520\u001b[0m \u001b[39mif\u001b[39;00m phrase_time_limit \u001b[39mand\u001b[39;00m elapsed_time \u001b[39m-\u001b[39m phrase_start_time \u001b[39m>\u001b[39m phrase_time_limit:\n\u001b[0;32m 521\u001b[0m \u001b[39mbreak\u001b[39;00m\n\u001b[1;32m--> 523\u001b[0m buffer \u001b[39m=\u001b[39m source\u001b[39m.\u001b[39;49mstream\u001b[39m.\u001b[39;49mread(source\u001b[39m.\u001b[39;49mCHUNK)\n\u001b[0;32m 524\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mlen\u001b[39m(buffer) \u001b[39m==\u001b[39m \u001b[39m0\u001b[39m: \u001b[39mbreak\u001b[39;00m \u001b[39m# reached end of the stream\u001b[39;00m\n\u001b[0;32m 525\u001b[0m frames\u001b[39m.\u001b[39mappend(buffer)\n",
"File \u001b[1;32mc:\\ProgramData\\miniconda3\\envs\\lang\\lib\\site-packages\\speech_recognition\\__init__.py:199\u001b[0m, in \u001b[0;36mMicrophone.MicrophoneStream.read\u001b[1;34m(self, size)\u001b[0m\n\u001b[0;32m 198\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mread\u001b[39m(\u001b[39mself\u001b[39m, size):\n\u001b[1;32m--> 199\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mpyaudio_stream\u001b[39m.\u001b[39;49mread(size, exception_on_overflow\u001b[39m=\u001b[39;49m\u001b[39mFalse\u001b[39;49;00m)\n",
"File \u001b[1;32mc:\\ProgramData\\miniconda3\\envs\\lang\\lib\\site-packages\\pyaudio\\__init__.py:570\u001b[0m, in \u001b[0;36mPyAudio.Stream.read\u001b[1;34m(self, num_frames, exception_on_overflow)\u001b[0m\n\u001b[0;32m 567\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_is_input:\n\u001b[0;32m 568\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mIOError\u001b[39;00m(\u001b[39m\"\u001b[39m\u001b[39mNot input stream\u001b[39m\u001b[39m\"\u001b[39m,\n\u001b[0;32m 569\u001b[0m paCanNotReadFromAnOutputOnlyStream)\n\u001b[1;32m--> 570\u001b[0m \u001b[39mreturn\u001b[39;00m pa\u001b[39m.\u001b[39;49mread_stream(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_stream, num_frames,\n\u001b[0;32m 571\u001b[0m exception_on_overflow)\n",
"\u001b[1;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"listen(None)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "lang",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.10"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
|