Added Azure Viva-vocal Project

Natural Language Processing/Azure_Review_analyzer/Readme.md

@@ -0,0 +1,118 @@
+# 🌟 ViveVocal: Azure Customer Review Analysis 🌟
+
+[![GitHub issues](https://img.shields.io/github/issues/priyans877/VIvaVocal-Azure-Customer-Review-Analysis-)](https://github.com/priyans877/VIvaVocal-Azure-Customer-Review-Analysis-/issues)
+[![GitHub forks](https://img.shields.io/github/forks/priyans877/VIvaVocal-Azure-Customer-Review-Analysis-)](https://github.com/priyans877/VIvaVocal-Azure-Customer-Review-Analysis-/network)
+[![GitHub stars](https://img.shields.io/github/stars/priyans877/VIvaVocal-Azure-Customer-Review-Analysis-)](https://github.com/priyans877/VIvaVocal-Azure-Customer-Review-Analysis-/stargazers)
+[![GitHub license](https://img.shields.io/github/license/priyans877/VIvaVocal-Azure-Customer-Review-Analysis-)](https://github.com/priyans877/VIvaVocal-Azure-Customer-Review-Analysis-/blob/main/LICENSE)
+
+## 🚀 Project Overview
+**ViveVocal** is an AI-driven platform that transforms customer feedback into valuable insights using **Azure Speech Services** for speech-to-text conversion and **Azure Language Services** for sentiment analysis, language detection, key phrase extraction, and entity recognition. This project aims to help businesses better understand and act on customer feedback by providing real-time insights from reviews submitted through voice, file uploads, or text.
+
+---
+
+### 🌟 Key Features
+- 🗣️ **Speech Input**: Converts spoken feedback into text using Azure Speech Services.
+- 📁 **File Upload**: Analyzes audio or text file uploads.
+- ⌨️ **Text Input**: Direct text review analysis.
+
+- 🎭 **Sentiment Analysis**: Detects the emotional tone (positive, negative, neutral).
+
+- 🌍 **Language Detection**: Automatically detects the language of the review.
+
+- 🔑 **Key Phrase Extraction**: Extracts important topics and key phrases.
+
+- 🏷️ **Entity Recognition**: Identifies and links key entities like products, services, locations, and competitors to relevant sources.
+
+---
+
+### 🔑 Why It's a Game Changer
+By analyzing **key phrases** and **entities**, businesses can:
+- 🎯 **Address specific customer concerns**.
+- 📊 **Spot emerging trends**.
+- 🚀 **Respond proactively** based on real-time feedback.
+
+Understanding not only the **emotional tone** but also **how entities (products, brands, services) impact customer opinions** provides businesses with a unique edge in improving customer satisfaction and making data-driven decisions.
+
+---
+
+## ⚙️ How It Works
+1. **Speech-to-Text**: Converts audio feedback into text using **Azure Speech Services**.
+2. **Text Processing**: Processes the text using **Azure Language Services** for:
+   - Sentiment analysis.
+   - Language detection.
+   - Key phrase extraction.
+   - Entity detection.
+3. **Output**: Provides the sentiment, key phrases, detected language, and links to relevant entities.
+
+---
+
+## 🛠️ Installation
+'''
+### 1. Clone the Repository
+```bash
+git clone https://github.com/priyans877/VIvaVocal-Azure-Customer-Review-Analysis-.git
+cd VIvaVocal-Azure-Customer-Review-Analysis-
+```
+---
+
+### 2. Install Dependencies
+--bash
+pip install -r requirements.txt
+
+---
+
+### 3. Set Up Azure Services
+Create an Azure Speech Services resource for speech-to-text conversion.
+Set up Azure Language Services for sentiment analysis, language detection, key phrase extraction, and entity recognition.
+Update your configuration files with the Azure API keys.
+🚀 Usage
+
+### Run the Application:
+
+```bash
+
+streamlit run app.py
+```
+
+### Provide Reviews in One of Three Ways:
+
+- 🗣️ Speak into the microphone.
+- 📁 Upload a file (audio or text).
+- ⌨️ Type your review.
+
+---
+
+
+### Analyze the Output:
+
+- View the sentiment (positive, neutral, negative).
+- Key phrases and entities are displayed for further insights.
+- Get language detection results and entity links for additional context.
+
+---
+### 💻 Technology Stack
+
+- **Azure Speech Services**: Converts speech to text.
+- **Azure Language Services**: Provides sentiment analysis, key phrase extraction, and entity detection.
+- **Python**: Main programming language.
+- **Streamlit**: Front-end for the web interface.
+
+---
+
+### 🤝 Contributing
+
+We welcome contributions! To get started:
+
+### Fork the repository.
+- Create a new branch for your feature.
+- Submit a pull request.
+- Feel free to open issues for suggestions or bug reports.
+
+### 📄 License
+This project is licensed under the MIT License. See the LICENSE file for more details.
+
+### 🎓 Acknowledgements
+Special thanks to ICT Academy and Infosys for providing the training that made this project possible.
+
+### 🌐 Connect
+If you have any questions or feedback, feel free to contact us or open an issue in the GitHub repository!

Natural Language Processing/Azure_Review_analyzer/main.py

@@ -0,0 +1,88 @@
+import streamlit as st
+import os
+from speech_recognition import main
+from text_sentimet import  text_analysis
+# Main layout
+
+# Set the page configuration
+st.set_page_config(page_title="Priyanshu-Choubey", layout="wide")
+st.markdown(
+    """
+    <style>
+    [data-testid="stSidebar"][aria-expanded="true"] > div:first-child{
+        width: 400px;
+    }
+    [data-testid="stSidebar"][aria-expanded="false"] > div:first-child{
+        width: 400px;
+        margin-left: -400px;
+    }
+
+    """,
+    unsafe_allow_html=True,
+)
+
+
+
+# Page header
+st.title("ViveVocal : Analyzing emotional Tone in Real-Time Speech")
+
+
+st.header("""Choose how you'd like to proceed furthur:""", divider='rainbow')
+
+# Option to select input method
+input_method = st.radio("How would you like to provide input?", 
+                        ('None','Voice Input', 'Select Pre-stored File','By entering text'),index=0)
+
+# If user selects 'Voice Input'
+if input_method == 'Voice Input':
+    main()
+
+
+
+# If user selects 'Select Pre-stored File'
+elif input_method == 'Select Pre-stored File':
+    st.info("You chose to use a pre-stored text file.")
+
+    #provide your directory which contain a reviews folder
+    file_directory = 'speech_text/'
+    if not os.path.exists(file_directory):
+        st.warning(f"The directory `{file_directory}` does not exist. Please ensure the folder is created.")
+    else:
+        files = [f for f in os.listdir(file_directory) if f.endswith('.txt')]
+        if len(files) > 0:
+            selected_file = st.selectbox("Choose a file", files)
+
+            # Display the content of the selected file
+            if selected_file:
+                file_path = os.path.join(file_directory, selected_file)
+                with open(file_path, 'r') as file:
+                    content = file.read()
+                    st.text_area("File Content", content, height=200)
+                    if st.button(" Summarize Review"):
+                        text_analysis(1,content)    
+        else:
+            st.warning(f"No .txt files found in the `{file_directory}` directory.")
+
+elif input_method=="By entering text":
+    st.info("You chose to input text manually.")
+
+    # Text input box
+    user_input = st.text_input("Enter your text here:")
+
+    if user_input:
+        # Display the manually entered text in a beautiful box
+        st.markdown(f"""
+        <div style="
+            background-color: #f0f0f5;
+            padding: 15px;
+            border-radius: 10px;
+            box-shadow: 2px 2px 12px rgba(0,0,0,0.1);
+            font-size: 16px;
+            font-family: Arial, sans-serif;
+            color: #333;
+            text-align: center;
+        ">
+            {user_input}
+        </div>
+        """, unsafe_allow_html=True)
+    text_analysis(2,user_input)

Natural Language Processing/Azure_Review_analyzer/requirements.txt

@@ -0,0 +1,3 @@
+pip install azure-ai-textanalytics==5.3.0
+pip install python-dotenv
+pip install playsound==1.2.2

Natural Language Processing/Azure_Review_analyzer/speech_recognition.py

@@ -0,0 +1,120 @@
+from datetime import datetime
+import os
+from text_sentimet import text_analysis
+import streamlit as st 
+
+
+# Import namespaces
+import azure.cognitiveservices.speech as speech_sdk
+from playsound import playsound
+
+
+def main():
+    try:
+        global command1
+        global speech_config
+
+        # Get Configuration Settings
+
+        ai_key = "b32f134094a2432fa1293380952bfa61"
+        ai_region = "eastus"
+
+        # Configure speech service
+        speech_config = speech_sdk.SpeechConfig(ai_key, ai_region)
+        st.subheader(f'Ready to use speech service in: {speech_config.region}',divider='rainbow')
+        #print('Ready to use speech service in ', speech_config.region)
+        st.divider()
+
+        if st.button(" Start by giving voice input Text"):
+            command1 = TranscribeCommand()
+
+            drictory="speech_text"
+            #maintatinig the file count in directory 
+            fileslist=os.listdir("speech_text")
+            lenfl=len(fileslist)
+            # print(fileslist)
+            # print(lenfl)
+
+            if command1 != '':
+                with open(f"speech_text/review_{lenfl+1}.txt","x") as f:
+                    #print("int the open funtion")
+                    f.write(f"{command1}") 
+                    st.subheader(f"Your speaked text is saved in File name : {f"reveiw_{lenfl+1}.txt"}")
+                    f.close()     
+                text_analysis()
+            else:
+                st.warning("I cant hear any specific command kindly speak Again by Using button")
+
+    except Exception as ex:
+        st.warning(ex)
+
+def TranscribeCommand():
+    command = ''
+
+
+    # Configure speech recognition
+    audio_config = speech_sdk.AudioConfig(use_default_microphone=True)
+    speech_recognizer = speech_sdk.SpeechRecognizer(speech_config, audio_config)
+    st.subheader('Speak now...' ,divider='rainbow')
+
+
+    # Process speech input
+    speech = speech_recognizer.recognize_once_async().get()
+    if speech.reason == speech_sdk.ResultReason.RecognizedSpeech:
+        command = speech.text
+        spoken_text = st.text_area("Simulated Voice Ouput",placeholder=f"{command}")
+        if spoken_text:
+            st.markdown(f"""
+            <div style="
+                background-color: #f0f0f5;
+                padding: 8px;
+                border-radius: 13px;
+                box-shadow: 2px 2px 12px rgba(0,0,0,0.1);
+                font-size: 30px;
+                font-family: Arial, sans-serif;
+                color: #80ff00;
+                text-align: center;
+            ">
+                {spoken_text}
+            </div>
+            """, unsafe_allow_html=True)
+
+
+
+
+
+
+    else:
+        print(speech.reason)
+        if speech.reason == speech_sdk.ResultReason.Canceled:
+            cancellation = speech.cancellation_details
+            print(cancellation.reason)
+            print(cancellation.error_details)
+
+    # Return the command
+    return command
+
+
+
+if __name__ == "__main__":
+    main()
+
+# def TellTime():
+#     now = datetime.now()
+#     response_text = 'The time is {}:{:02d}'.format(now.hour,now.minute)
+
+
+#     # Configure speech synthesis
+#     speech_config.speech_synthesis_voice_name = "en-GB-RyanNeural"
+#     speech_synthesizer = speech_sdk.SpeechSynthesizer(speech_config)
+
+
+#     # Synthesize spoken output
+#     speak = speech_synthesizer.speak_text_async(response_text).get()
+#     if speak.reason != speech_sdk.ResultReason.SynthesizingAudioCompleted:
+#         print(speak.reason)
+
+
+#     # Print the response
+#     print(response_text)
+