Update app.py

app.py

@@ -32,38 +32,40 @@ embeddings_dataset_english = load_dataset("Matthijs/cmu-arctic-xvectors", split=
 speaker_embedding_english = torch.tensor(embeddings_dataset_english[7306]["xvector"]).unsqueeze(0)
 
 """### **English Text-To-Image:**
-convert the starter of the English poetry to an image.
+Convert the starter of the English poetry to an image.
 """
 
 pipe_image = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4")
 
 """### **Translator from Arabic to English:**
-The text-to-image model dosn't support Arabic, therefore we need to translate the starter of the Arabic poetry to English in order to generate image.
+The text-to-image model doesn't support Arabic, therefore we need to translate the starter of the Arabic poetry to English in order to generate image.
 """
 
 pipe_translator = pipeline("translation", model="Helsinki-NLP/opus-mt-ar-en")
 
 """### **Primary Function:**
-This function will recives 2 inputs from the gradio interface, and excute the thollowing function and retrun 3 outputs:
-1. The generted poem.
-2. The aduio.
+This function will receive 2 inputs from the Gradio interface, and execute the following functions and return 3 outputs:
+1. The generated poem.
+2. The audio.
 3. The image.
 """
 
 # Generate poem based on language and convert it to audio and image
 def generate_poem(selected_language, text):
-    if selected_language == "English":
-        poem = generate_poem_english(text) #retrun the generated poem from the generate_poem_english function
-        sampling_rate, audio_data = text_to_speech_english(poem) #return the audio from the text_to_speech_english function
-        # image = generate_image_from_poem(text) #return the image from the generate_image_from_poem function
-    elif selected_language == "Arabic":
-        poem = generate_poem_arabic(text) #retrun the generated poem from the generate_poem_arabic function
-        sampling_rate, audio_data = text_to_speech_arabic(poem) #return the audio from the text_to_speech_arabic function
-        translated_text = translate_arabic_to_english(text) #return the translated poem from arabic to englsih, using translate_arabic_to_english function
-        # image = generate_image_from_poem(translated_text) #return the image from the generate_image_from_poem function
-
-    return poem, (sampling_rate, audio_data)
-    # , image
+    try:
+        if selected_language == "English":
+            poem = generate_poem_english(text) # Return the generated poem from the generate_poem_english function
+            sampling_rate, audio_data = text_to_speech_english(poem) # Return the audio from the text_to_speech_english function
+            image = generate_image_from_poem(text) # Return the image from the generate_image_from_poem function
+        elif selected_language == "Arabic":
+            poem = generate_poem_arabic(text) # Return the generated poem from the generate_poem_arabic function
+            sampling_rate, audio_data = text_to_speech_arabic(poem) # Return the audio from the text_to_speech_arabic function
+            translated_text = translate_arabic_to_english(text) # Return the translated poem from Arabic to English
+            image = generate_image_from_poem(translated_text) # Return the image from the generate_image_from_poem function
+
+        return poem, (sampling_rate, audio_data), image
+    except Exception as e:
+        return f"Error: {str(e)}", None, None
 
 """### **Poem Generation Function:**
 This function is responsible for generating a poem (text) in Arabic or English, based on the provided text.
@@ -71,20 +73,24 @@ This function is responsible for generating a poem (text) in Arabic or English,
 
 # Poem generation for Arabic
 def generate_poem_arabic(text):
+    temp = 1.0
+    topk = 50
+    topp = 0.9
+    penalty = 1.2
     generated_text = pipe_ar(text, max_length=96, do_sample=True, temperature=temp, top_k=topk, top_p=topp, repetition_penalty=penalty,
-                             min_length = 64, no_repeat_ngram_size = 3, return_full_text=True,
+                             min_length=64, no_repeat_ngram_size=3, return_full_text=True,
                              num_beams=5, num_return_sequences=1)[0]["generated_text"]
-    clean_text = generated_text.replace("-", "") #To get rid of the dashs generated by the model.
+    clean_text = generated_text.replace("-", "") # To get rid of the dashes generated by the model.
     return clean_text
 
 # Poem generation for English
 def generate_poem_english(text):
-    generated_text = pipe_en(text, do_sample=True, max_length=100, top_k=0, top_p=0.9, temperature=1.0, num_return_sequences=3,)[0]['generated_text']
-    clean_text = generated_text.replace("</s>", "") #To get rid of the </s> generated by the model.
+    generated_text = pipe_en(text, do_sample=True, max_length=100, top_k=50, top_p=0.9, temperature=1.0, num_return_sequences=3)[0]['generated_text']
+    clean_text = generated_text.replace("</s>", "") # To get rid of the </s> generated by the model.
     return clean_text
 
-"""### **ِAduio Function:**
-This function is responsible for generating an audio in Arabic or English, based on the provided text.
+"""### **Audio Function:**
+This function is responsible for generating audio in Arabic or English, based on the provided text.
 """
 
 # Text-to-speech conversion for Arabic
@@ -105,16 +111,16 @@ def text_to_speech_english(text):
 This function is responsible for generating an image based on the provided text.
 """
 
-#Image Function
+# Image generation function
 def generate_image_from_poem(poem_text):
     image = pipe_image(poem_text).images[0]
     return image
 
 """### **Translation Function:**
-This function is responsible for translating the Arabic input to English, to be used for the image function, which accept only english inputs.
+This function is responsible for translating Arabic input to English, to be used for the image function, which accepts only English inputs.
 """
 
-#Translation Function from Arabic to English
+# Translation function from Arabic to English
 def translate_arabic_to_english(text):
     translated_text = pipe_translator(text)[0]['translation_text']
     return translated_text
@@ -166,7 +172,7 @@ Provide 4 predefined inputs to demonstrate how the interface works.
 """
 
 examples = [
-    #First parameter is for the dropdown menu, and the second parameter is for the starter of the poem
+    # First parameter is for the dropdown menu, and the second parameter is for the starter of the poem
     ["English", "The shining sun rises over the calm ocean"],
     ["Arabic", "الورود تتفتح في الربيع"],
     ["English", "The night sky is filled with stars and dreams"],
@@ -174,22 +180,23 @@ examples = [
 ]
 
 """### **Gradio Interface:**
-Creating a Gradio interface to generate a poem, reading the poem, and generate an image based on that poem.
+Creating a Gradio interface to generate a poem, read the poem, and generate an image based on that poem.
 """
 
 my_model = gr.Interface(
-    fn=generate_poem,  #The primary function that will recives the inputs (language and the starter of the poem)
+    fn=generate_poem,  # The primary function that will receive the inputs (language and the starter of the poem)
     inputs=[
-        gr.Dropdown(["English", "Arabic"], label="Select Language"), #Dropdown menu to select the language, either "English" or "Arabic" for the poem
-        gr.Textbox(label="Enter a sentence")], #Textbox where the user will input a sentence or phrase to generate the poem (starter of the peom)
+        gr.Dropdown(["English", "Arabic"], label="Select Language"), # Dropdown menu to select the language, either "English" or "Arabic"
+        gr.Textbox(label="Enter a sentence")  # Textbox where the user will input a sentence or phrase to generate the poem
+    ],
 
     outputs=[
-        gr.Textbox(label="Generated Poem", lines=10), # Textbox to display the generated poem
-        gr.Audio(label="Generated Audio", type="numpy") #Audio output for the generated poem
-        # gr.Image(label="Generated Image")
-        ], #Display an image generated from the starter of the peom
+        gr.Textbox(label="Generated Poem", lines=10),  # Textbox to display the generated poem
+        gr.Audio(label="Generated Audio", type="numpy"),  # Audio output for the generated poem
+        gr.Image(label="Generated Image")  # Image output for the generated image
+    ],
 
-    examples=examples,  #Predefined examples to guide the user how to use the interface
-    css=custom_css  #Applying CSS Custeom
+    examples=examples,  # Predefined examples to guide the user
+    css=custom_css  # Applying custom CSS
 )
-my_model.launch()
+my_model.launch()