astoeckl

import markdown
from IPython.core.display import HTML

art = createarticle_from_video('https://www.youtube.com/watch?v=oaNwxtLKyk0')
HTML(markdown.markdown(art))

astoeckl

from pytube import YouTube
import whisper
import openai
openai.api_key = YOUROPENAIKEY
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", use_auth_token=YOUR_TOKEN)

def createarticle_from_video(url):
    output = ''

astoeckl

from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", use_auth_token=YOUR_TOKEN)
pipe = pipe.to("gpu")

image = pipe(titeltext).images[0]
image.save("news.jpg")

astoeckl

import openai
openai.api_key = YOUROPENAIKEY

newstext = result["text"]

prompt = "Newstext:\n" + newstext + "\nTitle:\n *"

response = openai.Completion.create(
        engine="text-davinci-002",
        prompt=str(prompt),

astoeckl

import whisper

model = whisper.load_model("base")
result = model.transcribe("bbc.mp4")
print(result["text"])

astoeckl

from pytube import YouTube

stream = YouTube('https://www.youtube.com/watch?v=oaNwxtLKyk0').streams.filter(only_audio=True).first()
stream.download('',"bbc.mp4")

astoeckl

import openai
openai.api_key = "XXX-YOURKEY"

doc_per_cluster = 3

for i in range(no_clusters):
    print(f"Cluster {i} Topic:", end=" ")
    
    docs = "\n".join(df[df.Cluster == i].Text.map(lambda x: x[:1000]).sample(doc_per_cluster, random_state=42).values)
    response = openai.Completion.create(

astoeckl

import seaborn as sns
from sklearn.manifold import TSNE
import matplotlib
import matplotlib.pyplot as plt
plt.rcParams['figure.figsize'] = (15, 8) 

tsne = TSNE(n_components=2, perplexity=15, random_state=42, init='random', learning_rate=200)
vis_dims2 = tsne.fit_transform(matrix)

x = [x for x,y in vis_dims2]

astoeckl

from sklearn.cluster import KMeans
from tqdm.notebook import tqdm
from sklearn.metrics import silhouette_score

X = matrix
cluster_results_km = pd.DataFrame({'K': range(6, 25), 'SIL': np.nan})
cluster_results_km.set_index('K', inplace=True)
for k in tqdm(cluster_results_km.index):
    km_model = KMeans(n_clusters = k, init ='k-means++', random_state = 42)
    y = km_model.fit_predict(X)

astoeckl

import openai
import numpy as np

openai.api_key = "XXX-YOUkey"

from tenacity import retry, wait_random_exponential, stop_after_attempt

@retry(wait=wait_random_exponential(min=1, max=20), stop=stop_after_attempt(6))
def get_embedding(text, engine="davinci-similarity"):