File size: 22,931 Bytes
c6919c4 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "39ea4bed",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\"\n",
"\n",
"\n",
"from IPython.display import Audio\n",
"import nltk # we'll use this to split into sentences\n",
"import numpy as np\n",
"\n",
"from bark.generation import (\n",
" generate_text_semantic,\n",
" preload_models,\n",
")\n",
"from bark.api import semantic_to_waveform\n",
"from bark import generate_audio, SAMPLE_RATE"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "776964b6",
"metadata": {},
"outputs": [],
"source": [
"preload_models()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1d03f4d2",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "74a025a4",
"metadata": {},
"source": [
"# Simple Long-Form Generation\n",
"We split longer text into sentences using `nltk` and generate the sentences one by one."
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "57b06e2a",
"metadata": {},
"outputs": [],
"source": [
"script = \"\"\"\n",
"Hey, have you heard about this new text-to-audio model called \"Bark\"? \n",
"Apparently, it's the most realistic and natural-sounding text-to-audio model \n",
"out there right now. People are saying it sounds just like a real person speaking. \n",
"I think it uses advanced machine learning algorithms to analyze and understand the \n",
"nuances of human speech, and then replicates those nuances in its own speech output. \n",
"It's pretty impressive, and I bet it could be used for things like audiobooks or podcasts. \n",
"In fact, I heard that some publishers are already starting to use Bark to create audiobooks. \n",
"It would be like having your own personal voiceover artist. I really think Bark is going to \n",
"be a game-changer in the world of text-to-audio technology.\n",
"\"\"\".replace(\"\\n\", \" \").strip()"
]
},
{
"cell_type": "code",
"execution_count": 34,
"id": "f747f804",
"metadata": {},
"outputs": [],
"source": [
"sentences = nltk.sent_tokenize(script)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"id": "17400a9b",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 43.03it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 17/17 [00:06<00:00, 2.45it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:04<00:00, 22.73it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 33/33 [00:13<00:00, 2.52it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 66.30it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 11/11 [00:04<00:00, 2.46it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:04<00:00, 20.99it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 35/35 [00:14<00:00, 2.46it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:03<00:00, 25.63it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 29/29 [00:11<00:00, 2.50it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:04<00:00, 23.90it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 30/30 [00:12<00:00, 2.46it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 53.24it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 14/14 [00:05<00:00, 2.51it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 50.63it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 15/15 [00:05<00:00, 2.57it/s]\n"
]
}
],
"source": [
"SPEAKER = \"v2/en_speaker_6\"\n",
"silence = np.zeros(int(0.25 * SAMPLE_RATE)) # quarter second of silence\n",
"\n",
"pieces = []\n",
"for sentence in sentences:\n",
" audio_array = generate_audio(sentence, history_prompt=SPEAKER)\n",
" pieces += [audio_array, silence.copy()]\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "04cf77f9",
"metadata": {},
"outputs": [],
"source": [
"Audio(np.concatenate(pieces), rate=SAMPLE_RATE)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ac2d4625",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "6d13249b",
"metadata": {},
"source": [
"# $ \\\\ $"
]
},
{
"cell_type": "markdown",
"id": "cdfc8bf5",
"metadata": {},
"source": [
"# Advanced Long-Form Generation\n",
"Somtimes Bark will hallucinate a little extra audio at the end of the prompt.\n",
"We can solve this issue by lowering the threshold for bark to stop generating text. \n",
"We use the `min_eos_p` kwarg in `generate_text_semantic`"
]
},
{
"cell_type": "code",
"execution_count": 37,
"id": "62807fd0",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 38.05it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 18/18 [00:07<00:00, 2.46it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:03<00:00, 32.28it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 21/21 [00:08<00:00, 2.54it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 55.78it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 14/14 [00:05<00:00, 2.57it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:06<00:00, 14.73it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 35/35 [00:14<00:00, 2.47it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 40.29it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 18/18 [00:07<00:00, 2.56it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:03<00:00, 32.92it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 20/20 [00:08<00:00, 2.47it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 68.87it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 12/12 [00:04<00:00, 2.62it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 47.64it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 15/15 [00:06<00:00, 2.46it/s]\n"
]
}
],
"source": [
"GEN_TEMP = 0.6\n",
"SPEAKER = \"v2/en_speaker_6\"\n",
"silence = np.zeros(int(0.25 * SAMPLE_RATE)) # quarter second of silence\n",
"\n",
"pieces = []\n",
"for sentence in sentences:\n",
" semantic_tokens = generate_text_semantic(\n",
" sentence,\n",
" history_prompt=SPEAKER,\n",
" temp=GEN_TEMP,\n",
" min_eos_p=0.05, # this controls how likely the generation is to end\n",
" )\n",
"\n",
" audio_array = semantic_to_waveform(semantic_tokens, history_prompt=SPEAKER,)\n",
" pieces += [audio_array, silence.copy()]\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "133fec46",
"metadata": {},
"outputs": [],
"source": [
"Audio(np.concatenate(pieces), rate=SAMPLE_RATE)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6eee9f5a",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "be8e125e",
"metadata": {},
"source": [
"# $ \\\\ $"
]
},
{
"cell_type": "markdown",
"id": "03a16c1b",
"metadata": {},
"source": [
"# Make a Long-Form Dialog with Bark"
]
},
{
"cell_type": "markdown",
"id": "06c5eff8",
"metadata": {},
"source": [
"### Step 1: Format a script and speaker lookup"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "5238b297",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['Samantha: Hey, have you heard about this new text-to-audio model called \"Bark\"?',\n",
" \"John: No, I haven't. What's so special about it?\",\n",
" \"Samantha: Well, apparently it's the most realistic and natural-sounding text-to-audio model out there right now. People are saying it sounds just like a real person speaking.\",\n",
" 'John: Wow, that sounds amazing. How does it work?',\n",
" 'Samantha: I think it uses advanced machine learning algorithms to analyze and understand the nuances of human speech, and then replicates those nuances in its own speech output.',\n",
" \"John: That's pretty impressive. Do you think it could be used for things like audiobooks or podcasts?\",\n",
" 'Samantha: Definitely! In fact, I heard that some publishers are already starting to use Bark to create audiobooks. And I bet it would be great for podcasts too.',\n",
" 'John: I can imagine. It would be like having your own personal voiceover artist.',\n",
" 'Samantha: Exactly! I think Bark is going to be a game-changer in the world of text-to-audio technology.']"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"speaker_lookup = {\"Samantha\": \"v2/en_speaker_9\", \"John\": \"v2/en_speaker_2\"}\n",
"\n",
"# Script generated by chat GPT\n",
"script = \"\"\"\n",
"Samantha: Hey, have you heard about this new text-to-audio model called \"Bark\"?\n",
"\n",
"John: No, I haven't. What's so special about it?\n",
"\n",
"Samantha: Well, apparently it's the most realistic and natural-sounding text-to-audio model out there right now. People are saying it sounds just like a real person speaking.\n",
"\n",
"John: Wow, that sounds amazing. How does it work?\n",
"\n",
"Samantha: I think it uses advanced machine learning algorithms to analyze and understand the nuances of human speech, and then replicates those nuances in its own speech output.\n",
"\n",
"John: That's pretty impressive. Do you think it could be used for things like audiobooks or podcasts?\n",
"\n",
"Samantha: Definitely! In fact, I heard that some publishers are already starting to use Bark to create audiobooks. And I bet it would be great for podcasts too.\n",
"\n",
"John: I can imagine. It would be like having your own personal voiceover artist.\n",
"\n",
"Samantha: Exactly! I think Bark is going to be a game-changer in the world of text-to-audio technology.\"\"\"\n",
"script = script.strip().split(\"\\n\")\n",
"script = [s.strip() for s in script if s]\n",
"script"
]
},
{
"cell_type": "markdown",
"id": "ee547efd",
"metadata": {},
"source": [
"### Step 2: Generate the audio for every speaker turn"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "203e5081",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 34.03it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 22/22 [00:08<00:00, 2.55it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 71.58it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 11/11 [00:04<00:00, 2.65it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:04<00:00, 22.75it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 33/33 [00:13<00:00, 2.53it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 70.76it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 11/11 [00:04<00:00, 2.63it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:04<00:00, 20.46it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 36/36 [00:14<00:00, 2.47it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:04<00:00, 20.18it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 37/37 [00:14<00:00, 2.51it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:04<00:00, 23.04it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 32/32 [00:12<00:00, 2.48it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 54.64it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 14/14 [00:05<00:00, 2.58it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████| 100/100 [00:03<00:00, 31.71it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████| 24/24 [00:09<00:00, 2.56it/s]\n"
]
}
],
"source": [
"pieces = []\n",
"silence = np.zeros(int(0.5*SAMPLE_RATE))\n",
"for line in script:\n",
" speaker, text = line.split(\": \")\n",
" audio_array = generate_audio(text, history_prompt=speaker_lookup[speaker], )\n",
" pieces += [audio_array, silence.copy()]"
]
},
{
"cell_type": "markdown",
"id": "7c54bada",
"metadata": {},
"source": [
"### Step 3: Concatenate all of the audio and play it"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "27a56842",
"metadata": {},
"outputs": [],
"source": [
"Audio(np.concatenate(pieces), rate=SAMPLE_RATE)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a1bc5877",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.10.11"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|