Update app.py
Browse files
app.py
CHANGED
@@ -95,11 +95,11 @@ iface = gr.Interface(
|
|
95 |
fn=chatbot,
|
96 |
inputs=gr.Audio(type="filepath"),
|
97 |
outputs=[
|
98 |
-
gr.Textbox(label="Chat History"), # Display chat history
|
99 |
gr.Audio(type="filepath", label="Response Audio"),
|
100 |
],
|
101 |
live=True,
|
102 |
-
title="
|
103 |
description="Upload your audio, and the chatbot will transcribe and respond to it with a synthesized response.",
|
104 |
theme="default",
|
105 |
css='''
|
@@ -109,27 +109,37 @@ iface = gr.Interface(
|
|
109 |
background-position: center;
|
110 |
background-repeat: no-repeat;
|
111 |
color: white;
|
112 |
-
font-family:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
113 |
}
|
114 |
-
# .gradio-container {
|
115 |
-
# background-color: rgba(0, 0, 0, 0.6);
|
116 |
-
# padding: 20px;
|
117 |
-
# border-radius: 8px;
|
118 |
-
# box-shadow: 0 4px 8px rgba(0, 0, 0, 0.2);
|
119 |
-
# }
|
120 |
-
# h1, h2, p, .gradio-label {
|
121 |
-
# color: #FFD700; /* Gold color for labels and titles */
|
122 |
-
# }
|
123 |
-
# .gradio-button {
|
124 |
-
# background-color: #FFD700;
|
125 |
-
# color: black;
|
126 |
-
# border-radius: 4px;
|
127 |
-
# font-weight: bold;
|
128 |
-
# }
|
129 |
-
# .gradio-input {
|
130 |
-
# background-color: rgba(255, 255, 255, 0.9);
|
131 |
-
# border-radius: 4px;
|
132 |
-
# }
|
133 |
'''
|
134 |
)
|
135 |
|
@@ -152,6 +162,7 @@ if __name__ == "__main__":
|
|
152 |
# import gradio as gr
|
153 |
# from groq import Groq
|
154 |
# from datetime import datetime
|
|
|
155 |
|
156 |
# # Load a smaller Whisper model for faster processing
|
157 |
# try:
|
@@ -186,12 +197,13 @@ if __name__ == "__main__":
|
|
186 |
# print(f"Error during LLM response retrieval: {e}")
|
187 |
# return "Sorry, there was an error retrieving the response. Please try again."
|
188 |
|
189 |
-
# # Function to convert text to speech using gTTS
|
190 |
# def text_to_speech(text):
|
191 |
# try:
|
192 |
# tts = gTTS(text)
|
193 |
-
#
|
194 |
-
#
|
|
|
195 |
# return output_audio
|
196 |
# except Exception as e:
|
197 |
# print(f"Error generating TTS: {e}")
|
@@ -245,37 +257,37 @@ if __name__ == "__main__":
|
|
245 |
# gr.Audio(type="filepath", label="Response Audio"),
|
246 |
# ],
|
247 |
# live=True,
|
248 |
-
# title="
|
249 |
# description="Upload your audio, and the chatbot will transcribe and respond to it with a synthesized response.",
|
250 |
# theme="default",
|
251 |
-
# css='''
|
252 |
# body {
|
253 |
-
# background-image: url("https://huggingface.co/spaces/abdullahzunorain/voice-to-voice-Chatbot/
|
254 |
# background-size: cover;
|
255 |
# background-position: center;
|
256 |
# background-repeat: no-repeat;
|
257 |
# color: white;
|
258 |
# font-family: Arial, sans-serif;
|
259 |
# }
|
260 |
-
# .gradio-container {
|
261 |
-
#
|
262 |
-
#
|
263 |
-
#
|
264 |
-
#
|
265 |
-
# }
|
266 |
-
# h1, h2, p, .gradio-label {
|
267 |
-
#
|
268 |
-
# }
|
269 |
-
# .gradio-button {
|
270 |
-
#
|
271 |
-
#
|
272 |
-
#
|
273 |
-
#
|
274 |
-
# }
|
275 |
-
# .gradio-input {
|
276 |
-
#
|
277 |
-
#
|
278 |
-
# }
|
279 |
# '''
|
280 |
# )
|
281 |
|
@@ -284,119 +296,3 @@ if __name__ == "__main__":
|
|
284 |
# iface.launch()
|
285 |
|
286 |
|
287 |
-
|
288 |
-
|
289 |
-
|
290 |
-
# ---------------------------------------------------------------------------------------------------------------------------------------------------------------
|
291 |
-
|
292 |
-
|
293 |
-
|
294 |
-
|
295 |
-
# import whisper
|
296 |
-
# import os
|
297 |
-
# from gtts import gTTS
|
298 |
-
# import gradio as gr
|
299 |
-
# from groq import Groq
|
300 |
-
# from datetime import datetime # Import datetime to handle timestamps
|
301 |
-
|
302 |
-
# # Load a smaller Whisper model for faster processing
|
303 |
-
# try:
|
304 |
-
# model = whisper.load_model("tiny")
|
305 |
-
# except Exception as e:
|
306 |
-
# print(f"Error loading Whisper model: {e}")
|
307 |
-
# model = None
|
308 |
-
|
309 |
-
# # Set up Groq API client using environment variable
|
310 |
-
# GROQ_API_TOKEN = os.getenv("GROQ_API")
|
311 |
-
# if not GROQ_API_TOKEN:
|
312 |
-
# raise ValueError("Groq API token is missing. Set 'GROQ_API' in your environment variables.")
|
313 |
-
# client = Groq(api_key=GROQ_API_TOKEN)
|
314 |
-
|
315 |
-
# # Initialize the chat history
|
316 |
-
# chat_history = []
|
317 |
-
|
318 |
-
# # Function to get the LLM response from Groq with timeout handling
|
319 |
-
# def get_llm_response(user_input, role="detailed responder"):
|
320 |
-
# prompt = f"As an expert, provide a detailed and knowledgeable response: {user_input}" if role == "expert" else \
|
321 |
-
# f"As a good assistant, provide a clear, concise, and helpful response: {user_input}" if role == "good assistant" else \
|
322 |
-
# f"Provide a thorough and detailed response: {user_input}"
|
323 |
-
|
324 |
-
# try:
|
325 |
-
# chat_completion = client.chat.completions.create(
|
326 |
-
# messages=[{"role": "user", "content": user_input}],
|
327 |
-
# model="llama3-8b-8192", # Replace with your desired model
|
328 |
-
# timeout=20 # Increased timeout to 20 seconds
|
329 |
-
# )
|
330 |
-
# return chat_completion.choices[0].message.content
|
331 |
-
# except Exception as e:
|
332 |
-
# print(f"Error during LLM response retrieval: {e}")
|
333 |
-
# return "Sorry, there was an error retrieving the response. Please try again."
|
334 |
-
|
335 |
-
# # Function to convert text to speech using gTTS
|
336 |
-
# def text_to_speech(text):
|
337 |
-
# try:
|
338 |
-
# tts = gTTS(text)
|
339 |
-
# output_audio = "output_audio.mp3"
|
340 |
-
# tts.save(output_audio)
|
341 |
-
# return output_audio
|
342 |
-
# except Exception as e:
|
343 |
-
# print(f"Error generating TTS: {e}")
|
344 |
-
# return None
|
345 |
-
|
346 |
-
# # Main chatbot function to handle audio input and output with chat history
|
347 |
-
# def chatbot(audio):
|
348 |
-
# if not model:
|
349 |
-
# return "Error: Whisper model is not available.", None, chat_history
|
350 |
-
|
351 |
-
# if not audio:
|
352 |
-
# return "No audio provided. Please upload a valid audio file.", None, chat_history
|
353 |
-
|
354 |
-
# try:
|
355 |
-
# # Step 1: Transcribe the audio using Whisper
|
356 |
-
# result = model.transcribe(audio)
|
357 |
-
# user_text = result.get("text", "")
|
358 |
-
# if not user_text.strip():
|
359 |
-
# return "Could not understand the audio. Please try speaking more clearly.", None, chat_history
|
360 |
-
|
361 |
-
# # Get current timestamp
|
362 |
-
# timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
363 |
-
|
364 |
-
# # Display transcription in chat history
|
365 |
-
# chat_history.append((timestamp, "User", user_text))
|
366 |
-
|
367 |
-
# # Step 2: Get LLM response from Groq
|
368 |
-
# response_text = get_llm_response(user_text)
|
369 |
-
|
370 |
-
# # Step 3: Convert the response text to speech
|
371 |
-
# output_audio = text_to_speech(response_text)
|
372 |
-
|
373 |
-
# # Append the latest interaction to the chat history
|
374 |
-
# chat_history.append((timestamp, "Chatbot", response_text))
|
375 |
-
|
376 |
-
# # Format the chat history for display with timestamps and clear labels
|
377 |
-
# formatted_history = "\n".join([f"[{time}] {speaker}: {text}" for time, speaker, text in chat_history])
|
378 |
-
|
379 |
-
# return formatted_history, output_audio, chat_history
|
380 |
-
|
381 |
-
# except Exception as e:
|
382 |
-
# print(f"Error in chatbot function: {e}")
|
383 |
-
# return "Sorry, there was an error processing your request.", None, chat_history
|
384 |
-
|
385 |
-
# # Gradio interface for real-time interaction with chat history display
|
386 |
-
# iface = gr.Interface(
|
387 |
-
# fn=chatbot,
|
388 |
-
# inputs=gr.Audio(type="filepath"),
|
389 |
-
# outputs=[
|
390 |
-
# gr.Textbox(label="Chat History"), # Display chat history
|
391 |
-
# gr.Audio(type="filepath", label="Response Audio"),
|
392 |
-
# ],
|
393 |
-
# live=True,
|
394 |
-
# title="Audio Chatbot with Groq API",
|
395 |
-
# description="Upload your audio, and the chatbot will transcribe and respond to it with a synthesized response.",
|
396 |
-
# theme="default"
|
397 |
-
# )
|
398 |
-
|
399 |
-
# # Launch the Gradio app
|
400 |
-
# if __name__ == "__main__":
|
401 |
-
# iface.launch()
|
402 |
-
|
|
|
95 |
fn=chatbot,
|
96 |
inputs=gr.Audio(type="filepath"),
|
97 |
outputs=[
|
98 |
+
gr.Textbox(label="Chat History", lines=10, interactive=False), # Display chat history
|
99 |
gr.Audio(type="filepath", label="Response Audio"),
|
100 |
],
|
101 |
live=True,
|
102 |
+
title="Voice to Voice Chatbot",
|
103 |
description="Upload your audio, and the chatbot will transcribe and respond to it with a synthesized response.",
|
104 |
theme="default",
|
105 |
css='''
|
|
|
109 |
background-position: center;
|
110 |
background-repeat: no-repeat;
|
111 |
color: white;
|
112 |
+
font-family: 'Helvetica Neue', sans-serif;
|
113 |
+
}
|
114 |
+
.gradio-container {
|
115 |
+
background-color: rgba(0, 0, 0, 0.7);
|
116 |
+
padding: 20px;
|
117 |
+
border-radius: 10px;
|
118 |
+
box-shadow: 0 4px 20px rgba(0, 0, 0, 0.5);
|
119 |
+
}
|
120 |
+
h1, h2, p, .gradio-label {
|
121 |
+
color: #FFD700; /* Gold color for labels and titles */
|
122 |
+
text-align: center;
|
123 |
+
}
|
124 |
+
.gradio-button {
|
125 |
+
background-color: #FFD700;
|
126 |
+
color: black;
|
127 |
+
border-radius: 5px;
|
128 |
+
font-weight: bold;
|
129 |
+
transition: background-color 0.3s, transform 0.2s;
|
130 |
+
}
|
131 |
+
.gradio-button:hover {
|
132 |
+
background-color: #FFC107; /* Lighter gold on hover */
|
133 |
+
transform: scale(1.05);
|
134 |
+
}
|
135 |
+
.gradio-input {
|
136 |
+
background-color: rgba(255, 255, 255, 0.9);
|
137 |
+
border-radius: 4px;
|
138 |
+
border: 2px solid #FFD700; /* Gold border */
|
139 |
+
}
|
140 |
+
.gradio-audio {
|
141 |
+
border: 2px solid #FFD700; /* Gold border for audio */
|
142 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
143 |
'''
|
144 |
)
|
145 |
|
|
|
162 |
# import gradio as gr
|
163 |
# from groq import Groq
|
164 |
# from datetime import datetime
|
165 |
+
# import tempfile
|
166 |
|
167 |
# # Load a smaller Whisper model for faster processing
|
168 |
# try:
|
|
|
197 |
# print(f"Error during LLM response retrieval: {e}")
|
198 |
# return "Sorry, there was an error retrieving the response. Please try again."
|
199 |
|
200 |
+
# # Function to convert text to speech using gTTS and handle temporary files
|
201 |
# def text_to_speech(text):
|
202 |
# try:
|
203 |
# tts = gTTS(text)
|
204 |
+
# with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as temp_file:
|
205 |
+
# output_audio = temp_file.name
|
206 |
+
# tts.save(output_audio)
|
207 |
# return output_audio
|
208 |
# except Exception as e:
|
209 |
# print(f"Error generating TTS: {e}")
|
|
|
257 |
# gr.Audio(type="filepath", label="Response Audio"),
|
258 |
# ],
|
259 |
# live=True,
|
260 |
+
# title="Voice to Voice Chatbot",
|
261 |
# description="Upload your audio, and the chatbot will transcribe and respond to it with a synthesized response.",
|
262 |
# theme="default",
|
263 |
+
# css='''
|
264 |
# body {
|
265 |
+
# background-image: url("https://huggingface.co/spaces/abdullahzunorain/voice-to-voice-Chatbot/resolve/main/BG_1.jpg");
|
266 |
# background-size: cover;
|
267 |
# background-position: center;
|
268 |
# background-repeat: no-repeat;
|
269 |
# color: white;
|
270 |
# font-family: Arial, sans-serif;
|
271 |
# }
|
272 |
+
# # .gradio-container {
|
273 |
+
# # background-color: rgba(0, 0, 0, 0.6);
|
274 |
+
# # padding: 20px;
|
275 |
+
# # border-radius: 8px;
|
276 |
+
# # box-shadow: 0 4px 8px rgba(0, 0, 0, 0.2);
|
277 |
+
# # }
|
278 |
+
# # h1, h2, p, .gradio-label {
|
279 |
+
# # color: #FFD700; /* Gold color for labels and titles */
|
280 |
+
# # }
|
281 |
+
# # .gradio-button {
|
282 |
+
# # background-color: #FFD700;
|
283 |
+
# # color: black;
|
284 |
+
# # border-radius: 4px;
|
285 |
+
# # font-weight: bold;
|
286 |
+
# # }
|
287 |
+
# # .gradio-input {
|
288 |
+
# # background-color: rgba(255, 255, 255, 0.9);
|
289 |
+
# # border-radius: 4px;
|
290 |
+
# # }
|
291 |
# '''
|
292 |
# )
|
293 |
|
|
|
296 |
# iface.launch()
|
297 |
|
298 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|