Update app.py

app.py

@@ -5,19 +5,17 @@ import ffmpeg
 from typing import List
 from moviepy.editor import VideoFileClip
 import nltk
-from huggingface_hub import InferenceClient
 from sklearn.feature_extraction.text import TfidfVectorizer
 from langchain import HuggingFaceHub, PromptTemplate, LLMChain
 import gradio as gr
 from pytube import YouTube
 import requests
 import logging
-
+import os
 nltk.download('punkt')
 nltk.download('stopwords')
 
 
-
 class VideoAnalytics:
     """
     Class for performing analytics on videos including transcription, summarization, topic generation,
@@ -42,8 +40,10 @@ class VideoAnalytics:
       # API URL for accessing the Hugging Face model
       self.API_URL = "https://api-inference.huggingface.co/models/openai/whisper-large-v3"
 
+
+      hf_token = os.getenv('HF_TOKEN')
       # Placeholder for Hugging Face API token
-      self.hf_token = "HF_TOKEN"  # Replace this with the actual Hugging Face API token
+      self.hf_token = hf_token # Replace this with the actual Hugging Face API token
 
       # Set headers for API requests with Hugging Face token
       self.headers = {"Authorization": f"Bearer {self.hf_token}"}
@@ -85,6 +85,8 @@ class VideoAnalytics:
 
           # Send audio data to the Hugging Face model for transcription
           output = query(audio_file)
+
+          print(output)
           # Update the transcribed_text attribute with the transcription result
           self.transcribed_text = output["text"]
           # Update the translation text into english_text
@@ -374,6 +376,10 @@ class VideoAnalytics:
             # Log any errors that occur during initialization of YouTube object
             logging.error(f"Error downloading video: {e}")
             return ""
+    def save_audio_with_gtts(self,text, filename):
+        tts = gTTS(text=text, lang='en')
+        tts.save(filename)
+        return filename
 
     def main(self, video: str = None, input_path: str = None) -> tuple:
         """
@@ -387,31 +393,38 @@ class VideoAnalytics:
             tuple: Summary, important sentences, and topics.
         """
         try:
-          video = VideoFileClip(input_path)
-          duration = video.duration
-          video.close()
-
-          if round(duration) < 600:
             # Download the video if input_path is provided, otherwise use the provided video path
-            if input_path:
-              input_path = self.Download(input_path)
+          if input_path:
+            input_path = self.Download(input_path)
+            video_ = VideoFileClip(input_path)
+            duration = video_.duration
+            video_.close()
+            if round(duration) <= 600:
               text = self.transcribe_video(input_path)
-            elif video:
+            else:
+              return "Video Duration Above 10 Minutes,Try Below 10 Minutes Video","",""
+          elif video:
+            video_ = VideoFileClip(video)
+            duration = video_.duration
+            video_.close()
+            if round(duration) <= 600:
               text = self.transcribe_video(video)
               input_path = video
-
-            # Generate summary, important sentences, and topics
-            summary = self.generate_video_summary()
-            self.write_text_files(summary,"Summary")
-            important_sentences = self.extract_video_important_sentence()
-            self.write_text_files(important_sentences,"Important_Sentence")
-            topics = self.generate_topics()
-            self.write_text_files(topics,"Topics")
-
-            # Return the generated summary, important sentences, and topics
-            return summary,important_sentences,topics
-          else:
-            return "Video Duration Above 10 Minutes,Try Below 10 Minutes Video","",""
+            else:
+              return "Video Duration Above 10 Minutes,Try Below 10 Minutes Video","",""
+          # Generate summary, important sentences, and topics
+          summary = self.generate_video_summary()
+          self.write_text_files(summary,"Summary")
+          summary_voice = save_audio_with_gtts(summary,"summary.mp3")
+          important_sentences = self.extract_video_important_sentence()
+          self.write_text_files(important_sentences,"Important_Sentence")
+          important_sentences_voice = save_audio_with_gtts(important_sentences,"important_sentences.mp3")
+          topics = self.generate_topics()
+          self.write_text_files(topics,"Topics")
+          topics_voice = save_audio_with_gtts(topics,"topics.mp3")
+
+          # Return the generated summary, important sentences, and topics
+          return summary,important_sentences,topics,summary_voice,important_sentences_voice,topics_voice
 
         except Exception as e:
             # Log any errors that occur during video analytics
@@ -432,28 +445,34 @@ class VideoAnalytics:
                   summary = gr.Textbox(show_label=False,lines=10)
               with gr.Row():
                   summary_download = gr.DownloadButton(label="Download",value="Summary.txt",visible=True,size='lg',elem_classes="download_button")
+              with gr.Row():
+                  summary_audio = gr.Audio(show_label= False,elem_classes='audio_class')
             with gr.Tab("Important Sentences"):
               with gr.Row():
                   Important_Sentences = gr.Textbox(show_label=False,lines=10)
               with gr.Row():
                   sentence_download = gr.DownloadButton(label="Download",value="Important_Sentence.txt",visible=True,size='lg',elem_classes="download_button")
+              with gr.Row():
+                  important_sentence_audio = gr.Audio(show_label = False,elem_classes='audio_class')
             with gr.Tab("Topics"):
               with gr.Row():
                   Topics = gr.Textbox(show_label=False,lines=10)
               with gr.Row():
                   topics_download = gr.DownloadButton(label="Download",value="Topics.txt",visible=True,size='lg',elem_classes="download_button")
+              with gr.Row():
+                  topics_audio = gr.Audio(show_label=False,elem_classes='audio_class')
             with gr.Tab("Video QA"):
               with gr.Row():
                 with gr.Column(scale=0.70):
                   question = gr.Textbox(show_label=False,placeholder="Ask Your Questions...")
                 with gr.Column(scale=0.30):
-                  model = gr.Dropdown(["OpenAI", "Mixtral"], label="Models")
+                  model = gr.Dropdown(["OpenAI", "Mixtral"],show_label=False,value="model")
               with gr.Row():
                   result = gr.Textbox(label='Answer',lines=10)
-              submit_btn.click(self.main,[video,yt_link],[summary,Important_Sentences,Topics])
+              submit_btn.click(self.main,[video,yt_link],[summary,Important_Sentences,Topics,summary_audio,important_sentence_audio,topics_audio])
               question.submit(self.video_qa,[question,model],result)
         demo.launch()
-
+        
 if __name__ == "__main__":
   video_analytics = VideoAnalytics()
   video_analytics.gradio_interface()