Upload 8 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+wake_detect.wav filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,3 @@
+# .gitignore
+venv
+__pycache__

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Ashutosh
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

Procfile

@@ -0,0 +1 @@
+web: gunicorn app:app

README.md

@@ -1,12 +1,72 @@
----
-title: VoiceAssistance
-emoji: 📈
-colorFrom: gray
-colorTo: yellow
-sdk: gradio
-sdk_version: 3.41.1
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+<h1 align="center">Bard Voice Assistant Web Application😃</h1>
+
+
+
+
+
+
+
+
+https://github.com/Ghost-Ashu/Bard-Voice-Assistant/assets/41056892/af6bd22c-4b81-4ad3-9784-d64e2e11bceb
+
+
+
+
+
+<p align="center">
+  <strong>A Flask web application that provides a user interface to interact with a chatbot.</strong>
+</p>
+
+<p align="center">
+  <a href="#installation">Installation</a> •
+  <a href="#usage">Usage</a> •
+  <a href="#license">License</a>
+</p>
+
+## Installation
+
+<ol>
+  <li>Clone the repository:
+    <pre><code>git clone https://github.com/your-username/your-repository.git
+    cd your-repository</code></pre>
+  </li>
+  
+  <li>Create a virtual environment (optional but recommended):
+    <pre><code>python3 -m venv venv
+    source venv/bin/activate</code></pre>
+  </li>
+  
+  <li>Install the dependencies:
+    <pre><code>pip install -r requirements.txt</code></pre>
+  </li>
+  
+  <li>Obtain a Bard Token:
+    <ul>
+      <li>Sign up on the <a href="https://www.bard.ai/">Bard</a> website to get an API token.</li>
+      <li>Replace the <code>token</code> variable in <code>app.py</code> with your token.</li>
+    </ul>
+  </li>
+  
+  <li>Download Whisper models:
+    <ul>
+      <li>Download the <code>tiny</code> and <code>base</code> models from the <a href="https://github.com/snakers4/whisper">Whisper</a> repository.</li>
+      <li>Place the models in the same directory as <code>app.py</code>.</li>
+    </ul>
+  </li>
+  
+  <li>Run the application:
+    <pre><code>python app.py</code></pre>
+  </li>
+  
+  <li>Open your web browser and visit <code>http://localhost:5000</code> to access the chatbot interface.</li>
+</ol>
+
+## Usage
+
+- Enter text input: Type your message in the input field and press Enter or click the "Send" button. The chatbot will respond accordingly.
+- Speech input: Click the "Listen" button and speak your prompt to the chatbot. It will transcribe your speech, send it to the chatbot, and provide a spoken response.
+- Speech output: Enter your prompt in the input field and click the "Speak" button. The chatbot's response will be spoken aloud.
+
+## License
+
+This project is licensed under the <a href="LICENSE">MIT License</a>.

app.py

@@ -0,0 +1,89 @@
+from flask import Flask, render_template, request, jsonify
+from Bard import Chatbot
+import pyttsx3
+import speech_recognition as sr
+import whisper
+
+app = Flask(__name__, static_folder='static', template_folder='templates')
+
+# Paste your Bard Token (check README.md for where to find yours)
+token = "<ADD YOUR BARD SESSION TOKEN>"
+# Initialize Google Bard API
+chatbot = Chatbot(token)
+# Initialize speech recognition
+r = sr.Recognizer()
+# Initialize Whisper model
+tiny_model = whisper.load_model('tiny')
+base_model = whisper.load_model('base')
+
+# Initialize pyttsx3 for text-to-speech
+engine = pyttsx3.init()
+# Get the current speech rate
+rate = engine.getProperty('rate')
+# Decrease speech rate by 50 words per minute (Change as desired)
+engine.setProperty('rate', rate - 50)
+
+
+def prompt_bard(prompt):
+    response = chatbot.ask(prompt)
+    return response['content']
+
+
+def speak(text):
+    engine.say(text)
+    engine.runAndWait()
+
+
+def listen_for_prompt():
+    with sr.Microphone() as source:
+        try:
+            print("Speak your prompt to Bard.\n")
+            # Record prompt
+            audio = r.listen(source)
+            with open("prompt.wav", "wb") as f:
+                f.write(audio.get_wav_data())
+            # Transcribe prompt using whisper base model
+            result = base_model.transcribe('prompt.wav')
+            prompt_text = result['text']
+            print("Sending to Bard:", prompt_text, '\n')
+            # If prompt is empty, return empty response
+            if len(prompt_text.strip()) == 0:
+                return ""
+            return prompt_text
+        except Exception as e:
+            print("Error transcribing audio: ", e)
+            return ""
+
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+
+@app.route('/ask', methods=['POST'])
+def ask():
+    prompt = request.form['prompt']
+    response = prompt_bard(prompt)
+    return jsonify({'response': response})
+
+
+@app.route('/speak', methods=['POST'])
+def speak_prompt():
+    prompt = request.form['prompt']
+    speak(prompt)
+    return jsonify({'status': 'success'})
+
+
+@app.route('/listen', methods=['POST'])
+def listen_prompt():
+    prompt = listen_for_prompt()
+    if prompt:
+        response = prompt_bard(prompt)
+        speak(response)
+        return jsonify({'response': response})
+    else:
+        return jsonify({'response': 'No prompt recorded.'})
+
+
+if __name__ == '__main__':
+    app.run(debug=True)

requirements.txt

@@ -0,0 +1,44 @@
+blinker==1.6.2
+certifi==2023.5.7
+charset-normalizer==3.1.0
+click==8.1.3
+colorama==0.4.6
+comtypes==1.2.0
+ffmpeg-python==0.2.0
+filelock==3.12.2
+Flask==2.3.2
+future==0.18.3
+GoogleBard==0.0.7
+gunicorn==20.1.0
+heroku==0.1.4
+idna==3.4
+itsdangerous==2.1.2
+Jinja2==3.1.2
+llvmlite==0.40.1rc1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+mdurl==0.1.2
+more-itertools==9.1.0
+mpmath==1.3.0
+networkx==3.1
+numba==0.57.0
+numpy==1.24.3
+openai-whisper==20230314
+prompt-toolkit==3.0.38
+Pygments==2.15.1
+pypiwin32==223
+python-dateutil==1.5
+pyttsx3==2.90
+pywin32==306
+regex==2023.6.3
+requests==2.31.0
+rich==13.4.2
+SpeechRecognition==3.10.0
+sympy==1.12
+tiktoken==0.3.1
+torch==2.0.1
+tqdm==4.65.0
+typing_extensions==4.6.3
+urllib3==2.0.3
+wcwidth==0.2.6
+Werkzeug==2.3.6

wake_detect.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cccf3ffdc78f000d45dc15c2f3a18801f81c71e7689c58b9ec1a59d5f347ddce
+size 2785324