Spaces:
Build error
Build error
File size: 11,728 Bytes
bcb84e7 6249bc9 bcb84e7 6249bc9 595153d bcb84e7 6249bc9 595153d 6249bc9 595153d bcb84e7 6249bc9 25733b9 6249bc9 595153d bcb84e7 595153d bcb84e7 25733b9 bcb84e7 595153d 6249bc9 595153d 6249bc9 595153d 6249bc9 595153d 6249bc9 595153d 02fcd9e 595153d 6249bc9 595153d 6249bc9 595153d d5c9693 6249bc9 595153d 6249bc9 82c7c76 6249bc9 bcb84e7 595153d 6249bc9 595153d 6249bc9 595153d 6249bc9 02fcd9e 6249bc9 |
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 |
import gradio as gr
from typing import Any
import torch
from transformers import pipeline
from diffusers import StableDiffusionPipeline
from TTS.api import TTS
import whisper
import utils
from youtubeaudioextractor import PytubeAudioExtractor
from transcriber import SpanishTranscriber, WhisperTranscriber
from textprocessor import TextProcessor
from videocreator import VideoCreator
spanish_transcribe_model = "juancopi81/whisper-medium-es"
languages = {"Spanish": "es", "English": "en"}
device = "cuda" if torch.cuda.is_available() else "cpu"
device_dict = {"cuda": 0, "cpu": -1}
dtype = torch.float16 if device == "cuda" else torch.float32
# Detect if code is running in Colab
is_colab = utils.is_google_colab()
colab_instruction = "" if is_colab else """
<p>You can skip the queue using Colab:
<a href="">
<img data-canonical-src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg"></a></p>"""
device_print = "GPU 🔥" if torch.cuda.is_available() else "CPU 🥶"
# Initialize components
audio_extractor = PytubeAudioExtractor()
es_transcription_pipe = pipeline(
task="automatic-speech-recognition",
model=spanish_transcribe_model,
chunk_length_s=30,
device=device_dict[device],
)
es_transcription_pipe.model.config.forced_decoder_ids = es_transcription_pipe.tokenizer.get_decoder_prompt_ids(language="es",
task="transcribe")
es_audio_transcriber = SpanishTranscriber(es_transcription_pipe)
en_transcription_pipe = whisper.load_model("base")
en_audio_transcriber = WhisperTranscriber(en_transcription_pipe)
openai_model = "text-davinci-003"
text_processor = TextProcessor(openai_model)
image_model_id = "runwayml/stable-diffusion-v1-5"
image_pipeline = StableDiffusionPipeline.from_pretrained(image_model_id,
torch_dtype=dtype,
revision="fp16")
image_pipeline = image_pipeline.to(device)
es_vo_model_name = TTS.list_models()[22]
en_vo_model_name = TTS.list_models()[8]
# Init TTS
es_tts = TTS(es_vo_model_name)
en_tts = TTS(en_vo_model_name)
def datapipeline(url: str,
video_language: str,
summary_language: str,
video_styles: str) -> Any:
audio_path_file = audio_extractor.extract(url)
print(f"Audio file created at: {audio_path_file}")
# Select transcriber
if video_language == "Spanish":
audio_transcriber = es_audio_transcriber
elif video_language == "English":
audio_transcriber = en_audio_transcriber
else:
return "Language not supported"
if summary_language == "Spanish":
video_creator = VideoCreator(es_tts, image_pipeline)
elif summary_language == "English":
video_creator = VideoCreator(en_tts, image_pipeline)
else:
return "Language not supported"
transcribed_text = audio_transcriber.transcribe(audio_path_file)
print("Audio transcription ready!")
json_scenes = text_processor.get_json_scenes(transcribed_text,
summary_language)
print("Scenes ready")
video = video_creator.create_video(json_scenes, video_styles)
print("Video at", video)
return video, video
css = """
a {
color: inherit;
text-decoration: underline;
}
.gradio-container {
font-family: 'IBM Plex Sans', sans-serif;
}
.gr-button {
color: white;
border-color: #000000;
background: #000000;
}
input[type='range'] {
accent-color: #000000;
}
.dark input[type='range'] {
accent-color: #dfdfdf;
}
.container {
max-width: 730px;
margin: auto;
padding-top: 1.5rem;
}
#gallery {
min-height: 22rem;
margin-bottom: 15px;
margin-left: auto;
margin-right: auto;
border-bottom-right-radius: .5rem !important;
border-bottom-left-radius: .5rem !important;
}
#gallery>div>.h-full {
min-height: 20rem;
}
.details:hover {
text-decoration: underline;
}
.gr-button {
white-space: nowrap;
}
.gr-button:focus {
border-color: rgb(147 197 253 / var(--tw-border-opacity));
outline: none;
box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000);
--tw-border-opacity: 1;
--tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color);
--tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color);
--tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity));
--tw-ring-opacity: .5;
}
#advanced-btn {
font-size: .7rem !important;
line-height: 19px;
margin-top: 12px;
margin-bottom: 12px;
padding: 2px 8px;
border-radius: 14px !important;
}
#advanced-options {
margin-bottom: 20px;
}
.footer {
margin-bottom: 45px;
margin-top: 35px;
text-align: center;
border-bottom: 1px solid #e5e5e5;
}
.footer>p {
font-size: .8rem;
display: inline-block;
padding: 0 10px;
transform: translateY(10px);
background: white;
}
.dark .footer {
border-color: #303030;
}
.dark .footer>p {
background: #0b0f19;
}
.acknowledgments h4{
margin: 1.25em 0 .25em 0;
font-weight: bold;
font-size: 115%;
}
#container-advanced-btns{
display: flex;
flex-wrap: wrap;
justify-content: space-between;
align-items: center;
}
.animate-spin {
animation: spin 1s linear infinite;
}
@keyframes spin {
from {
transform: rotate(0deg);
}
to {
transform: rotate(360deg);
}
}
#share-btn-container {
display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem;
}
#share-btn {
all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important;
}
#share-btn * {
all: unset;
}
.gr-form{
flex: 1 1 50%; border-top-right-radius: 0; border-bottom-right-radius: 0;
}
#prompt-container{
gap: 0;
}
#generated_id{
min-height: 700px
}
#setting_id{
margin-bottom: 12px;
text-align: center;
font-weight: 900;
}
"""
block = gr.Blocks(css=css)
with block as demo:
gr.HTML(
f"""
<div style="text-align: center; max-width: 650px; margin: 0 auto;">
<div
style="
display: inline-flex;
align-items: center;
gap: 0.8rem;
font-size: 1.75rem;
"
>
<h1 style="font-weight: 900; margin-bottom: 7px;">
YouTube to Illustraded Summary
</h1>
</div>
<p style="margin-bottom: 10px; font-size: 94%">
Enter the URL of a YouTube video (in Spanish) and you'll recive a video with an illustraded summary.
It works for audio books, history lessons, etc. Try it out with a short video (less than 4 minutes).
</p>
<p style="margin-bottom: 10px; font-size: 94%">
Running on <b>{device_print}</b>
</p>
</div>
"""
)
with gr.Group():
with gr.Box():
with gr.Row(elem_id="setting_id").style(mobile_collapse=False, equal_height=True):
gr.HTML("<h1>Setting</h1>")
with gr.Row():
with gr.Column():
video_language = gr.Radio(choices=["Spanish", "English"],
label="Language of your input video:",
value="Spanish")
with gr.Column():
summary_language = gr.Radio(choices=["Spanish", "English"],
label="Language of your output video:",
value="Spanish")
with gr.Row():
video_styles = gr.Textbox(label="(OPTIONAL) Enter the styles for your ouput video",
value="",
placeholder="illustration, highly detailed, digital painting, concept art, matte, art by wlop and artgerm and greg rutkowski and alphonse mucha, masterpiece")
with gr.Group():
with gr.Box():
with gr.Row().style(mobile_collapse=False, equal_height=True):
url = gr.Textbox(
label="Enter the URL of the YouTubeVideo",
show_label=False,
max_lines=1,
placeholder="YouTube URL"
).style(
border=(True, False, True, True),
rounded=(True, False, False, True),
container=False,
)
btn = gr.Button("Run").style(
margin=False,
rounded=(False, True, True, False),
)
video_output = gr.Video()
file_output = gr.File()
btn.click(datapipeline,
inputs=[url,
video_language,
summary_language,
video_styles],
outputs=[video_output, file_output])
gr.Examples(
examples=[["https://www.youtube.com/watch?v=c0i5016pB2Y", "English", "Spanish", "oil on painting"],
["https://www.youtube.com/watch?v=Hk5evm1NgzA", "Spanish", "English", "dramatic lighting, cinematic, matte painting"],
["https://www.youtube.com/watch?v=sRmmQBBln9Q", "Spanish", "Spanish", "Hyper real, 4k"],
["https://www.youtube.com/watch?v=qz4Wc48KITA", "Spanish", "English", "detailed art by kay nielsen and walter crane, illustration style, watercolor"]],
inputs=[url, video_language, summary_language, video_styles]
)
gr.HTML(
"""
<div class="footer">
<p>This demos is part of the Whisper Sprint (Dec. 2022).</a>
</p>
</div>
"""
)
gr.Markdown('''
[](https://twitter.com/juancopi81)
''')
if not is_colab:
demo.queue(concurrency_count=1)
demo.launch(debug=is_colab, share=is_colab) |