Create app.py

app.py

@@ -0,0 +1,116 @@
+# Import libraries
+from transformers import pipeline
+from numpy import random
+import gradio as gr
+import re
+import torch
+from torch import autocast
+import os
+
+# Array with song cover art styles
+image_input_styles = ["Random", "Pencil sketch", "Oil painting", "Pop art", "Piet Mondriaan"]
+
+# Get image type for image input
+"""
+The default setting for the art style dropdown is "Random". The below function determines which style is chosen
+If set to "Random", copy the art style array and remove "Random" to prevent "Random" from being a chosen art style
+"""
+def get_image_input(title, given_input_style):
+    if given_input_style == 'Random':
+      image_input_styles_new = image_input_styles.copy()
+      image_input_styles_new.pop(0)
+      random_choice = random.randint(len(image_input_styles_new)-1)
+      final_style = image_input_styles_new[random_choice]
+    else:
+      final_style = given_input_style
+    image_input = 'Cover for ' + title.lower() + ' in style of ' + final_style 
+    return image_input, final_style
+
+# Available models for generate lyrics pipeline
+# checkpoint = 'wvangils/GPT-Medium-Beatles-Lyrics-finetuned-newlyrics'
+# checkpoint = 'wvangils/GPT-Neo-125m-Beatles-Lyrics-finetuned-newlyrics'
+checkpoint = 'wvangils/BLOOM-560m-Beatles-Lyrics-finetuned'
+
+# Setup all the pipelines we need
+title_generator = pipeline('summarization', model='czearing/story-to-title')
+lyrics_generator = pipeline("text-generation", model=checkpoint)
+
+# For the image generator we use stable diffusion from an existing HuggingFace space, Gradio accelerated backend
+stable_diffusion = gr.Blocks.load(name="spaces/stabilityai/stable-diffusion-1")
+
+# Create 4 images for the given prompt and receive the first one
+# This function uses an existing HuggingFace space where the number of created images cannot be modified
+def get_image(prompt):
+    gallery_dir = stable_diffusion(prompt, fn_index=2)
+    images = [os.path.join(gallery_dir, img) for img in os.listdir(gallery_dir)]
+    return [images[0]]
+
+# Lyrics generation
+def generate_beatles(input_prompt, temperature, top_p, given_input_style):
+    # Create generator for different models
+    generated_lyrics = lyrics_generator(input_prompt
+                              , max_length = 100
+                              , num_return_sequences = 1
+                              , return_full_text = True
+                              , temperature = temperature    
+                              , top_p = top_p    # Default 1.0
+                              , no_repeat_ngram_size = 3   # Default = 0
+                              , repetition_penalty = 1.0   # Default = 1.0
+                              )[0]["generated_text"]
+
+    # Put lyrics in the right form
+    lyrics_sentences = re.sub('\n', '. ', generated_lyrics)
+
+    # Create a title based on the generated lyrics
+    title = title_generator(lyrics_sentences, min_length=1, max_length=10, repetition_penalty=2.5)[0]['summary_text']
+
+    # Create an image based on the generated title
+    image_input, image_style = get_image_input(title, given_input_style)
+
+    # Generate the image
+    image = get_image(image_input)
+    return (title, generated_lyrics, image, image_style)
+    
+# Create textboxes for input and output
+input_box = gr.Textbox(label="Write the start of a song here", placeholder="Write the start of a new song here", value="Looking out of my window", lines=2, max_lines=5)
+gen_lyrics = gr.Textbox(label="Song lyrics", lines=15)
+gen_title = gr.Textbox(label="Proposed songtitle", lines=1)
+gen_image = gr.Gallery(label="Proposed song cover").style(grid=1, height="auto")
+gen_image_style = gr.Textbox(label="Image style", lines=1)
+
+# Layout and text around the app
+title='Beatles lyrics generator'
+description="<p style='text-align: center'>We've fine-tuned multiple language models on lyrics from The Beatles to generate Beatles-like text. Below are the results we obtained fine-tuning a GPT Neo model. After generation a title is generated using <a href='https://huggingface.co/czearing/story-to-title' target='_blank'>this model</a>. On top we use the generated title to suggest an album cover using <a href='https://huggingface.co/CompVis/stable-diffusion-v1-4' target='_blank'>Stable Diffusion 1.4</a>. Give it a try!</p>"
+article="""<p style='text-align: left'>These text generation models that output Beatles-like text were created by data scientists working for <a href='https://cmotions.nl/' target="_blank">Cmotions.</a>  
+        We tried several text generation models that we were able to load in Colab: a general <a href='https://huggingface.co/gpt2-medium' target='_blank'>GPT2-medium</a> model, the Eleuther AI small-sized GPT model <a href='https://huggingface.co/EleutherAI/gpt-neo-125M' target='_blank'>GPT-Neo</a> and the new kid on the block build by the <a href='https://bigscience.notion.site/BLOOM-BigScience-176B-Model-ad073ca07cdf479398d5f95d88e218c4' target='_blank'>Bigscience</a> initiative <a href='https://huggingface.co/bigscience/bloom-560m' target='_blank'>BLOOM 560m</a>. 
+        Further we've put together a <a href='https://huggingface.co/datasets/cmotions/Beatles_lyrics' target='_blank'> Huggingface dataset</a> containing all known lyrics created by The Beatles. Currently we are fine-tuning models and are evaluating the results. Once finished we will publish a blog at this <a href='https://www.theanalyticslab.nl/blogs/' target='_blank'>location </a> with all the steps we took including a Python notebook using Huggingface.
+        The default output contains 100 tokens and has a repetition penalty of 1.0. 
+         </p>"""
+css = """
+        .gr-button-primary {
+          text-indent: -9999px;
+          line-height: 0;
+        }  
+        .gr-button-primary:after {
+          content: "Beatlify!";
+          text-indent: 0;
+          display: block;
+          line-height: initial;
+        }
+""" 
+
+# Let users select their own temperature and top-p
+temperature = gr.Slider(minimum=0.1, maximum=1.0, step=0.1, label="Change the temperature \r\n (higher temperature = more creative in lyrics generation, but posibbly less Beatly)", value=0.7, show_label=True)  #high = sensitive for low probability tokens
+top_p = gr.Slider(minimum=0.1, maximum=1.0, step=0.1, label="Change top probability of the next word \n (higher top probability = more words to choose from for the next word, but possibly less Beatly)", value=0.5, show_label=True)
+given_input_style = gr.Dropdown(choices=image_input_styles, value="Random", label="Choose the art style for the lyrics cover", show_label=True)
+
+# Use generate Beatles function in demo-app Gradio
+gr.Interface(fn=generate_beatles
+             , inputs=[input_box, temperature, top_p, given_input_style]
+             , outputs=[gen_title, gen_lyrics, gen_image, gen_image_style]
+             , title=title
+             , css=css
+             , description=description
+             , article=article
+             , allow_flagging='never'
+             ).launch()