Update app.py

app.py

@@ -9,9 +9,12 @@ import time
 import random
 import os
 import zipfile
-import gradio as gr
 import ffmpeg
-
+from gtts import gTTS
+#from io import BytesIO
+from collections import Counter
+from PIL import Image, ImageDraw, ImageFont
+import numpy as np
 
 nltk.download('maxent_ne_chunker') #Chunker
 nltk.download('stopwords') #Stop Words List (Mainly Roman Languages)
@@ -29,7 +32,7 @@ nltk.download('opinion_lexicon') #Sentiment words
 nltk.download('averaged_perceptron_tagger') #Parts of Speech Tagging
 
 
-spacy.cli.download("en_core_web_sm")
+#spacy.cli.download("en_core_web_sm")
 
 nlp = spacy.load('en_core_web_sm')
 translator = Translator()
@@ -183,7 +186,47 @@ def merge_lines(roman_file, w4w_file, full_mean_file, macaronic_file):
     return "\n".join(merged_lines)
 
 def TTSforListeningPractice(text):
-	return "not finished"
+    language = "en"
+    speech = gTTS(text=text, lang=language, slow="False")
+    speech.save("CurrentTTSFile.mp3")
+    #file = BytesIO()
+    #speech.write_to_fp(file)
+    #file.seek(0)
+    return "CurrentTTSFile.mp3" #file
+
+def AutoChorusInvestigator(sentences):
+    sentences = sentences.splitlines()
+    # Use Counter to count the number of occurrences of each sentence
+    sentence_counts = Counter(sentences)
+
+    # Identify duplicate sentences
+    duplicates = [s for s, count in sentence_counts.items() if count > 1]
+
+    FinalOutput = ""
+    if len(duplicates) == 0:
+        FinalOutput += "No duplicate sentences found in the file."
+    else:
+        FinalOutput += "The following sentences appear more than once in the file:"
+        for sentence in duplicates:
+            FinalOutput += "\n" + sentence
+    return FinalOutput
+
+def AutoChorusPerWordScheduler(sentences):
+    words = set(sentences.split(" "))
+    wordsoneattime =[]
+    practicestring = ""
+
+    FinalOutput = "This is supposed to output the words in repetition format (i.e. schedule for repitition) \nCurrent Idea = 1 new word every min and 1 old word every second" + "\n\nWords: \n"
+    for word in words:
+        wordsoneattime.append(word)
+        for i in range(0, 59):
+            practicestring += word + " "
+            practicestring += random.choice(wordsoneattime) + " "    
+        FinalOutput += word + "\n "
+        practicestring += "\n"
+
+    FinalOutput += practicestring
+    return FinalOutput
 
 def group_words(inlist):
     inlisttoks = inlist.split(" ")
@@ -221,7 +264,8 @@ def split_verbs_nouns(text):
     
     verbs_nouns = []
     other_words = []
-    
+    pos_string = []
+
     for token in doc:
         if token.pos_ in ["VERB", "NOUN"]:
             verbs_nouns.append(token.text)
@@ -230,11 +274,13 @@ def split_verbs_nouns(text):
             other_words.append(token.text)
         else:
             other_words.append(token.text)
-    
+        pos_string.append(token.pos_)
+
     verbs_nouns_text = " ".join(verbs_nouns)
     other_words_text = " ".join(other_words)
+    pos_string_text = " ".join(pos_string)
     
-    return verbs_nouns_text, other_words_text
+    return pos_string_text, verbs_nouns_text, other_words_text
 
 def split_srt_file(text): #file_path):
     # Open the SRT file and read its contents
@@ -327,6 +373,73 @@ def VideotoSegment(video_file, subtitle_file):
     # Return the ZIP archive for download
     return 'segmented_files.zip'
 
+def text_to_dropdown(text, id=None): #TextCompFormat
+    lines = text.strip().split("\n")
+    html = "<select"
+    if id:
+        html += f' id="{id}"'
+    html += "> \n"
+    for line in lines:
+        html += f"    <option>{line}</option>\n"
+    html += "</select> \n"
+    return html
+
+def text_to_links(text): #TextCompFormat
+    lines = text.strip().split("\n")
+    html = ""
+    for line in lines:
+        if line.startswith("http"):
+            html += f'<a href="{line}">{line}</a><br> \n'
+        else:
+            html += line + "Not a link <br> \n"
+    return html
+
+HTMLCompMode = gr.Dropdown(choices=["Dropdown", "Links"], value="Dropdown")
+
+def TextCompFormat(text, HTMLCompMode):
+    FinalOutput = ""
+    if HTMLCompMode == "Dropdown":
+        FinalOutput = text_to_dropdown(text)
+    if HTMLCompMode == "Links":
+        FinalOutput = text_to_links(text)
+    return FinalOutput
+
+def create_collapsiblebutton(button_id, button_caption, div_content):
+    button_html = f'<button id="{button_id}" class="accordionbtn">{button_caption}</button>'
+    div_html = f'<div id="{button_id}Div" class="panel">\n{div_content}\n    </div>'
+    return button_html + "\n    " + div_html
+
+#---------------
+
+def removeTonalMarks(string):
+    tonalMarks = "āēīōūǖáéíóúǘǎěǐǒǔǚàèìòùǜ"
+    nonTonalMarks = "aeiouuaeiouuaeiouuaeiou"
+    noTonalMarksStr = ""
+    for char in string:
+        index = tonalMarks.find(char)
+        if index != -1:
+            noTonalMarksStr += nonTonalMarks[index]
+        else:
+            noTonalMarksStr += char
+    return noTonalMarksStr
+
+
+def add_text_to_image(input_image, text, output_image_path="output.png", border_size=2):
+    imagearr = np.asarray(input_image) #Image.open(input_image_path)
+    width, height = imagearr.shape[:2] #width, height = image.size
+    img = Image.fromarray(imagearr)
+    draw = ImageDraw.Draw(img)
+    font = ImageFont.truetype("ShortBaby.ttf", 36) #ShortBaby-Mg2w.ttf
+    text_width, text_height = draw.textbbox((0, 0), text, font=font)[2:] #draw.textsize(text, font)
+    # calculate the x, y coordinates of the text box
+    x = (width - text_width) / 2
+    y = (height - text_height) / 2
+    # put the text on the image with a border
+    for dx, dy in [(0, 0), (border_size, border_size), (-border_size, -border_size), (border_size, -border_size), (-border_size, border_size)]:
+        draw.text((x + dx, y + dy), text, font=font, fill=(255, 255, 255))
+    draw.text((x, y), text, font=font, fill=(0, 0, 0))
+    img.save(output_image_path, "PNG")
+    return "output.png"
 
 # Define the Gradio interface inputs and outputs for video split
 spvvideo_file_input = gr.File(label='Video File')
@@ -338,6 +451,7 @@ groupinput_text = gr.inputs.Textbox(lines=2, label="Enter a list of words")
 groupoutput_text = gr.outputs.Textbox(label="Grouped words")
 
 with gr.Blocks() as lliface:
+  gr.HTML("<p>Audio = best long form attention mechanism AS it is ANTICIPATION (Awareness of something before it happens like knowing song Lyrics) FOCUSED - Attention (Focused Repitition) + Exposure (Random Repitition) </p>")
   with gr.Tab("Welcome"):
     gr.HTML("""<h1> Spaces Test - Still Undercontruction </h1> <p> You only learn when you convert things you dont know to known --> Normally Repetition is the only reliable method for everybody </p>  
     <p> Knowledge is a Language but productive knowledge is find replace as well </p> <p>LingQ is good option for per word state management</p> <p> Arrows app json creator for easy knowledge graphing and spacy POS graph? </p> 
@@ -347,49 +461,48 @@ with gr.Blocks() as lliface:
     <p> ChatGPT Turns Learning into a read only what you dont know ask only what you dont know feedback loop --> All you have to do is keep track of what prompts you have asked in the past</p>
     <p> Spell multiple words simultaneously for simultaneous access </p>
     """)
-    with gr.Tab("Unique word ID"):
+    with gr.Tab("Unique word ID - use in Infranodus"):
       gr.Interface(fn=unique_word_count, inputs="text", outputs="text", title="Wordcounter")
-      gr.Interface(fn=SepHypandSynExpansion, inputs="text", outputs=["text", "text"], title="Word suggestions")
+      gr.Interface(fn=SepHypandSynExpansion, inputs="text", outputs=["text", "text"], title="Word suggestions - Analyse the unique words in infranodus")
       gr.Interface(fn=WikiSearch, inputs="text", outputs="text", title="Unique word suggestions(wiki articles)")
     with gr.Tab("Automating related information linking"):
       gr.HTML("Questions - Tacking and suggesting questions to ask = new education")  
-  with gr.Tab("Spelling and Chunks"):
-    gr.Text("Merged Spelling Practice Placeholder - Spell multiple words simultaneously for simultaneous access")  
-    gr.HTML("<p> Spelling is the end goal, you already know many letter orders called words so you need leverage them to remember random sequences")
-    with gr.Tab("Spelling Simplification - Use a dual language list"):
-        gr.Interface(fn=create_dictionary, inputs="text", outputs="text", title="Sort Text by first two letters")
-    with gr.Tab("Chunks"): 
-        gr.Interface(fn=FrontRevSentChunk, inputs=[ChunkModeDrop, "checkbox", "text", langdest], outputs="text")
-        gr.Interface(fn=keep_nouns_verbs, inputs=["text"], outputs="text", title="Noun and Verbs only (Plus punctuation)")
   with gr.Tab("Timing Practice - Repitition"):
     gr.HTML("<p>Run from it, Dread it, Repitition is inevitable - Thanos</p> <p>Next Milestone is Turning this interface handsfree</p>")  
     with gr.Tab("Gradio Version"):
-      gr.Interface(fn=group_words, inputs=groupinput_text, outputs=groupoutput_text, title="Word Grouping and Rotation", description="Group a list of words into sets of 10 and rotate them every 60 seconds.").queue()          
+      gr.Interface(fn=group_words, inputs=groupinput_text, outputs=groupoutput_text, title="Word Grouping and Rotation", description="Group a list of words into sets of 10 and rotate them every 60 seconds.") #.queue()          
     with gr.Tab("HTML Version"):
       gr.HTML("""<iframe height="1200" style="width: 100%;" scrolling="no" title="Memorisation Aid" src="https://codepen.io/kwabs22/embed/preview/GRXKQgj?default-tab=result&editable=true" frameborder="no" loading="lazy" allowtransparency="true" allowfullscreen="true">
   See the Pen <a href="https://codepen.io/kwabs22/pen/GRXKQgj">
   Memorisation Aid</a> by kwabs22 (<a href="https://codepen.io/kwabs22">@kwabs22</a>)
   on <a href="https://codepen.io">CodePen</a>.
 </iframe>""")
-  with gr.Tab("Knowledge Ideas"):
-      gr.HTML("""<p>Good knowledge = ability to answer questions --> find Questions you cant answer and look for hidden answer within them </p>
-      <p>My One Word Theory = We only use more words than needed when we have to or are bored --> Headings exist because title is not sufficient, subheadings exist because headings are not sufficient, Book Text exists because subheadings are not sufficient</p>
-      <p>Big Picture = Expand the Heading and the subheadings and compare them to each other</p>
-      <p>Application of Knowledge = App Version of the text (eg. Jupyter Notebooks) is what you create and learn first</p>
-	  """)    
-  with gr.Tab("Beginner - Songs - Chorus"):
-      gr.HTML("Essentially if the sounds are repeated or long notes they are easy to remember")
-      gr.Interface(fn=TTSforListeningPractice, inputs="text", outputs="text", title="Placeholder - paste chorus here and use TTS or make notes to save here")
-  with gr.Tab("Transcribe - RASMUS Whisper"):
-    gr.HTML("""<p>If this tab doesnt work use the link below ⬇️</p> <a href="https://huggingface.co/spaces/RASMUS/Whisper-youtube-crosslingual-subtitles">https://huggingface.co/spaces/RASMUS/Whisper-youtube-crosslingual-subtitles</a>""")
-    gr.Interface.load("spaces/RASMUS/Whisper-youtube-crosslingual-subtitles", title="Subtitles")
+  with gr.Tab("Beginner - Listening and Reading"):
+    with gr.Tab("Listening - Songs - Chorus"):
+        gr.HTML("Anticipation of the item to remember is how you learn lyrics that is why songs are easy as if you heard it 10 times already your capacity to anticipate the words is great <br><br> This is where TTS helps as you are ignoring all words except the words just before the actual <hr>")
+        gr.HTML("<p>Fastest way to learn words = is to have your own sound reference --> probably why babies learn fast as they make random noise</p> <p>If you know the flow of the song you can remember the spelling easier</p><p>Essentially if the sounds are repeated or long notes they are easy to remember</p>")
+        gr.HTML("""<hr><a href="https://translate.google.com/?hl=en&tab=TT"> --Google Translate-- </a><br>""")
+        gr.Interface(fn=AutoChorusInvestigator, inputs="text", outputs="text", description="Paste Full Lyrics to try find only chorus lines")
+        gr.Interface(fn=AutoChorusPerWordScheduler, inputs="text", outputs="text", description="Create order of repitition for tts practice")
+        gr.Interface(fn=TTSforListeningPractice, inputs="text", outputs="file", title="Placeholder - paste chorus here and use TTS or make notes to save here")
+    with gr.Tab("Reading - Caption images (SD/Dalle-E)"):
+        gr.HTML("Predictable to identify the parts of picture being described --> The description moves in one direction from one side of the image to the other side is easiest <hr>")
+        gr.HTML("Image = instant comprehension like Stable Diffusion --> Audiovisual experience is the most optimal reading experience <br> Manga with summary descriptions for the chapters = Most aligned visual to audio experience")
+        gr.HTML("""<a href="https://huggingface.co/spaces/pharma/CLIP-Interrogator"> --Huggingface CLIP-Interrogator Space-- </a><br> """)
+        gr.Interface(fn=removeTonalMarks, inputs="text", outputs="text", description="For text with characters use this function to remove any conflicting characters (if error below)")
+        gr.Interface(fn=add_text_to_image , inputs=["image", "text"], outputs="image", description="Create Annotated images (Can create using stable diffusion and use the prompt)")
+  #with gr.Tab("Transcribe - RASMUS Whisper"):
+    #gr.Interface.load("spaces/RASMUS/Whisper-youtube-crosslingual-subtitles", title="Subtitles")
   with gr.Tab("Advanced - LingQ Addons ideas"):
-    gr.HTML("Extra functions needed - Persitent Sentence translation, UNWFWO, POS tagging and Word Count per user of words in their account. Macaronic Text is also another way to practice only the important information")
+    gr.HTML("LingQ Companion Idea - i.e. Full Translation Read along, and eventually Videoplayer watch along like RAMUS whisper space <br><br>Extra functions needed - Persitent Sentence translation, UNWFWO, POS tagging and Word Count per user of words in their account. Macaronic Text is also another way to practice only the important information")
+    gr.HTML("""<hr> <p>For Transcripts to any video on youtube use the link below ⬇️</p> <a href="https://huggingface.co/spaces/RASMUS/Whisper-youtube-crosslingual-subtitles">https://huggingface.co/spaces/RASMUS/Whisper-youtube-crosslingual-subtitles</a>""")
+    #gr.HTML("<p>If Space not loaded its because of offline devopment errors please message for edit</p> <hr>")
     with gr.Tab("Merged Subtitles"):
-        gr.HTML("SRT Contents to W4W Split SRT for Google Translate")
-        gr.Interface(fn=split_srt_file, inputs="text", outputs="text")
-        gr.HTML("Text for w4w creation in G Translate")
-        gr.Interface(fn=splittext, inputs="text", outputs="text")
+        gr.HTML("Step 1 - Word for Word Translation Creation in both Directions (Paste Google Translation here)")
+        gr.Interface(fn=split_srt_file, inputs="text", outputs="text", description="SRT Contents to W4W Split SRT for Google Translate")
+        gr.HTML("Step 2 - Pronounciation (Roman) to Subtitle Format --> GTranslate returns unformatted string")
+        gr.Interface(fn=splittext, inputs="text", outputs="text", description="Text for w4w creation in G Translate")
+        gr.HTML("Step 3 - Merge into one file")
         with gr.Row():
             RomanFile = gr.File(label="Paste Roman")
             W4WFile = gr.File(label="Paste Word 4 Word")
@@ -404,9 +517,25 @@ with gr.Blocks() as lliface:
     with gr.Tab("Split video to segments"):
         gr.Interface(VideotoSegment, inputs=[spvvideo_file_input, spvsubtitle_file_input], outputs=spvdownload_output)
     with gr.Tab("Sentence to Format"):
-        gr.Interface(fn=split_verbs_nouns , inputs="text", outputs=["text", "text"], title="Comprehension reading and Sentence Format Creator")
+        gr.Interface(fn=split_verbs_nouns , inputs="text", outputs=["text", "text", "text"], title="Comprehension reading and Sentence Format Creator")
         gr.Text("Text to Closed Class + Adjectives + Punctuation or Noun Verb + Punctuation ")
-  with gr.Tab("Dictionary from text"):
-    gr.Interface(fn=create_dictionary, inputs="text", outputs="text", title="Two Letter Dictionary")
+  with gr.Tab("Spelling and Chunks"):
+    gr.Text("Merged Spelling Practice Placeholder - Spell multiple words simultaneously for simultaneous access")  
+    gr.HTML("<p> Spelling is the end goal, you already know many letter orders called words so you need leverage them to remember random sequences")
+    with gr.Tab("Spelling Simplification - Use a dual language list"):
+        gr.Interface(fn=create_dictionary, inputs="text", outputs="text", title="Sort Text by first two letters")
+    with gr.Tab("Chunks"): 
+        gr.Interface(fn=FrontRevSentChunk, inputs=[ChunkModeDrop, "checkbox", "text", langdest], outputs="text")
+        gr.Interface(fn=keep_nouns_verbs, inputs=["text"], outputs="text", title="Noun and Verbs only (Plus punctuation)")
+  with gr.Tab("Knowledge Ideas - Notetaking"):
+      gr.HTML("""<p>Good knowledge = ability to answer questions --> find Questions you cant answer and look for hidden answer within them </p>
+      <p>My One Word Theory = We only use more words than needed when we have to or are bored --> Headings exist because title is not sufficient, subheadings exist because headings are not sufficient, Book Text exists because subheadings are not sufficient</p>
+      <p>Big Picture = Expand the Heading and the subheadings and compare them to each other</p>
+      <p>Application of Knowledge = App Version of the text (eg. Jupyter Notebooks) is what you create and learn first</p>
+	  """)
+      gr.Interface(fn=TextCompFormat, inputs=["textarea", HTMLCompMode], outputs="text", description="Convert Text to HTML Dropdown or Links which you paste in any html file")    
+      gr.Interface(fn=create_collapsiblebutton, inputs=["textbox", "textbox", "textarea"], outputs="textarea", description="Button and Div HTML Generator, Generate the HTML for a button and the corresponding div element.")
+  with gr.Tab("Automated Reading Assitant"):
+      gr.HTML("Tree and Branches approach to learning = familiarity with keywords/headings/summaries before reading the whole text <hr> Productivity/Work revolves around repitition which can be found looking for plurals and grouping terms eg. Headings and Hyper/Hyponyms Analysis")        
   
-lliface.launch()
+lliface.queue().launch()