File size: 10,868 Bytes
bc8b865 27f9093 bc8b865 27f9093 bc8b865 27f9093 bc8b865 1aff08b bc8b865 27f9093 bc8b865 27f9093 bc8b865 27f9093 bc8b865 1aff08b bc8b865 1aff08b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 |
# import whisper
# import os
# from gtts import gTTS
# import gradio as gr
# from groq import Groq
# from datetime import datetime
# import tempfile
# # Load a smaller Whisper model for faster processing
# try:
# model = whisper.load_model("tiny")
# except Exception as e:
# print(f"Error loading Whisper model: {e}")
# model = None
# # Set up Groq API client using environment variable
# GROQ_API_TOKEN = os.getenv("GROQ_API")
# if not GROQ_API_TOKEN:
# raise ValueError("Groq API token is missing. Set 'GROQ_API' in your environment variables.")
# client = Groq(api_key=GROQ_API_TOKEN)
# # Initialize the chat history
# chat_history = []
# # Function to get the LLM response from Groq with timeout handling
# def get_llm_response(user_input, role="detailed responder"):
# prompt = f"As an expert, provide a detailed and knowledgeable response: {user_input}" if role == "expert" else \
# f"As a good assistant, provide a clear, concise, and helpful response: {user_input}" if role == "good assistant" else \
# f"Provide a thorough and detailed response: {user_input}"
# try:
# chat_completion = client.chat.completions.create(
# messages=[{"role": "user", "content": user_input}],
# model="llama3-8b-8192", # Replace with your desired model
# timeout=20 # Increased timeout to 20 seconds
# )
# return chat_completion.choices[0].message.content
# except Exception as e:
# print(f"Error during LLM response retrieval: {e}")
# return "Sorry, there was an error retrieving the response. Please try again."
# # Function to convert text to speech using gTTS and handle temporary files
# def text_to_speech(text):
# try:
# tts = gTTS(text)
# with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as temp_file:
# output_audio = temp_file.name
# tts.save(output_audio)
# return output_audio
# except Exception as e:
# print(f"Error generating TTS: {e}")
# return None
# # Main chatbot function to handle audio input and output with chat history
# def chatbot(audio):
# if not model:
# return "Error: Whisper model is not available.", None, chat_history
# if not audio:
# return "No audio provided. Please upload a valid audio file.", None, chat_history
# try:
# # Step 1: Transcribe the audio using Whisper
# result = model.transcribe(audio)
# user_text = result.get("text", "")
# if not user_text.strip():
# return "Could not understand the audio. Please try speaking more clearly.", None, chat_history
# # Get current timestamp
# timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
# # Display transcription in chat history
# chat_history.append((timestamp, "User", user_text))
# # Step 2: Get LLM response from Groq
# response_text = get_llm_response(user_text)
# # Step 3: Convert the response text to speech
# output_audio = text_to_speech(response_text)
# # Append the latest interaction to the chat history
# chat_history.append((timestamp, "Chatbot", response_text))
# # Format the chat history for display with timestamps and clear labels
# formatted_history = "\n".join([f"[{time}] {speaker}: {text}" for time, speaker, text in chat_history])
# return formatted_history, output_audio, chat_history
# except Exception as e:
# print(f"Error in chatbot function: {e}")
# return "Sorry, there was an error processing your request.", None, chat_history
# # Gradio interface for real-time interaction with chat history display
# iface = gr.Interface(
# fn=chatbot,
# inputs=gr.Audio(type="filepath"),
# outputs=[
# gr.Textbox(label="Chat History", lines=10, interactive=False), # Display chat history
# gr.Audio(type="filepath", label="Response Audio"),
# ],
# live=True,
# title="Voice to Voice Chatbot",
# description="Upload your audio, and the chatbot will transcribe and respond to it with a synthesized response.",
# theme="default",
# css='''
# body {
# background-image: url("https://huggingface.co/spaces/abdullahzunorain/voice-to-voice-Chatbot/resolve/main/BG_1.jpg");
# background-size: cover;
# background-position: center;
# background-repeat: no-repeat;
# color: white;
# font-family: 'Helvetica Neue', sans-serif;
# }
# .gradio-container {
# background-color: rgba(0, 0, 0, 0.7);
# padding: 20px;
# border-radius: 10px;
# box-shadow: 0 4px 20px rgba(0, 0, 0, 0.5);
# }
# h1, h2, p, .gradio-label {
# color: #FFD700; /* Gold color for labels and titles */
# text-align: center;
# }
# .gradio-button {
# background-color: #FFD700;
# color: black;
# border-radius: 5px;
# font-weight: bold;
# transition: background-color 0.3s, transform 0.2s;
# }
# .gradio-button:hover {
# background-color: #FFC107; /* Lighter gold on hover */
# transform: scale(1.05);
# }
# .gradio-input {
# background-color: rgba(255, 255, 255, 0.9);
# border-radius: 4px;
# border: 2px solid #FFD700; /* Gold border */
# }
# .gradio-audio {
# border: 2px solid #FFD700; /* Gold border for audio */
# }
# '''
# )
# # Launch the Gradio app
# if __name__ == "__main__":
# iface.launch()
import whisper
import os
from gtts import gTTS
import gradio as gr
from groq import Groq
from datetime import datetime
import tempfile
# Load a smaller Whisper model for faster processing
try:
model = whisper.load_model("tiny")
except Exception as e:
print(f"Error loading Whisper model: {e}")
model = None
# Set up Groq API client using environment variable
GROQ_API_TOKEN = os.getenv("GROQ_API")
if not GROQ_API_TOKEN:
raise ValueError("Groq API token is missing. Set 'GROQ_API' in your environment variables.")
client = Groq(api_key=GROQ_API_TOKEN)
# Initialize the chat history
chat_history = []
# Function to get the LLM response from Groq with timeout handling
def get_llm_response(user_input, role="detailed responder"):
prompt = f"As an expert, provide a detailed and knowledgeable response: {user_input}" if role == "expert" else \
f"As a good assistant, provide a clear, concise, and helpful response: {user_input}" if role == "good assistant" else \
f"Provide a thorough and detailed response: {user_input}"
try:
chat_completion = client.chat.completions.create(
messages=[{"role": "user", "content": user_input}],
model="llama3-8b-8192", # Replace with your desired model
timeout=20 # Increased timeout to 20 seconds
)
return chat_completion.choices[0].message.content
except Exception as e:
print(f"Error during LLM response retrieval: {e}")
return "Sorry, there was an error retrieving the response. Please try again."
# Function to convert text to speech using gTTS and handle temporary files
def text_to_speech(text):
try:
tts = gTTS(text)
with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as temp_file:
output_audio = temp_file.name
tts.save(output_audio)
return output_audio
except Exception as e:
print(f"Error generating TTS: {e}")
return None
# Main chatbot function to handle audio input and output with chat history
def chatbot(audio):
if not model:
return "Error: Whisper model is not available.", None, chat_history
if not audio:
return "No audio provided. Please upload a valid audio file.", None, chat_history
try:
# Step 1: Transcribe the audio using Whisper
result = model.transcribe(audio)
user_text = result.get("text", "")
if not user_text.strip():
return "Could not understand the audio. Please try speaking more clearly.", None, chat_history
# Get current timestamp
timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
# Display transcription in chat history
chat_history.append((timestamp, "User", user_text))
# Step 2: Get LLM response from Groq
response_text = get_llm_response(user_text)
# Step 3: Convert the response text to speech
output_audio = text_to_speech(response_text)
# Append the latest interaction to the chat history
chat_history.append((timestamp, "Chatbot", response_text))
# Format the chat history for display with timestamps and clear labels
formatted_history = "\n".join([f"[{time}] {speaker}: {text}" for time, speaker, text in chat_history])
return formatted_history, output_audio, chat_history
except Exception as e:
print(f"Error in chatbot function: {e}")
return "Sorry, there was an error processing your request.", None, chat_history
# Gradio interface for real-time interaction with chat history display
iface = gr.Interface(
fn=chatbot,
inputs=gr.Audio(type="filepath"),
outputs=[
gr.Textbox(label="Chat History"), # Display chat history
gr.Audio(type="filepath", label="Response Audio"),
],
live=True,
title="Voice to Voice Chatbot",
description="Upload your audio, and the chatbot will transcribe and respond to it with a synthesized response.",
theme="default",
css='''
body {
background-image: url("https://huggingface.co/spaces/abdullahzunorain/voice-to-voice-Chatbot/resolve/main/BG_1.jpg");
background-size: cover;
background-position: center;
background-repeat: no-repeat;
color: white;
font-family: Arial, sans-serif;
}
# .gradio-container {
# background-color: rgba(0, 0, 0, 0.6);
# padding: 20px;
# border-radius: 8px;
# box-shadow: 0 4px 8px rgba(0, 0, 0, 0.2);
# }
# h1, h2, p, .gradio-label {
# color: #FFD700; /* Gold color for labels and titles */
# }
# .gradio-button {
# background-color: #FFD700;
# color: black;
# border-radius: 4px;
# font-weight: bold;
# }
# .gradio-input {
# background-color: rgba(255, 255, 255, 0.9);
# border-radius: 4px;
# }
'''
)
# Launch the Gradio app
if __name__ == "__main__":
iface.launch()
|