Spaces:
Sleeping
Sleeping
File size: 1,513 Bytes
80c5382 c3f535c 2336f67 9706c54 c3f535c 1ef5127 2336f67 |
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 |
# Import libraries
import whisper
import os
from gtts import gTTS
import gradio as gr
from groq import Groq
# Load Whisper model for transcription
model = whisper.load_model("base")
GROQ_API_KEY= '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'
client= Groq(api_key=GROQ_API_KEY)
# Function to get the LLM response from Groq
def get_llm_response(user_input):
chat_completion = client.chat.completions.create(
messages=[{"role": "user", "content": user_input}],
model="llama3-8b-8192", # Replace with your desired model
)
return chat_completion.choices[0].message.content
# Function to convert text to speech using gTTS
def text_to_speech(text, output_audio="output_audio.mp3"):
tts = gTTS(text)
tts.save(output_audio)
return output_audio
# Main chatbot function to handle audio input and output
def chatbot(audio):
# Step 1: Transcribe the audio using Whisper
result = model.transcribe(audio)
user_text = result["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)
return response_text, output_audio
# Gradio interface for real-time interaction
iface = gr.Interface(
fn=chatbot,
inputs=gr.Audio(type="filepath"), # Input from mic or file
outputs=[gr.Textbox(), gr.Audio(type="filepath")], # Output: response text and audio
live=True
)
# Launch the Gradio app
iface.launch()
|