Spaces:
Runtime error
Runtime error
File size: 1,592 Bytes
c412199 dde51c5 c412199 dde51c5 c412199 dde51c5 |
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 |
!pip install gradio groq openai-whisper gtts
import os
import gradio as gr
from groq import Groq
import whisper
from gtts import gTTS
import tempfile
# Set up Groq API key
os.environ['GROQ_API_KEY'] = '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' # Replace with your valid key
groq_client = Groq(api_key=os.environ.get('GROQ_API_KEY'))
# Load Whisper model
whisper_model = whisper.load_model("base")
def process_audio(audio_file):
try:
# Transcribe audio using Whisper
result = whisper_model.transcribe(audio_file)
user_text = result['text']
# Generate response using Llama 8b model with Groq API
chat_completion = groq_client.chat.completions.create(
messages=[
{
"role": "user",
"content": user_text,
}
],
model="llama3-8b-8192",
)
response_text = chat_completion.choices[0].message.content
# Convert response text to speech using gTTS
tts = gTTS(text=response_text, lang='en')
# Saving to a temporary file
audio_file = tempfile.NamedTemporaryFile(delete=False, suffix='.mp3')
tts.save(audio_file.name)
return response_text, audio_file.name
except Exception as e:
print("Error:", e)
return str(e), None
# Create Gradio interface
iface = gr.Interface(
fn=process_audio,
inputs=gr.Audio(type="filepath"),
outputs=[gr.Textbox(label="Response"), gr.Audio(label="Response Audio")],
live=True
)
iface.launch()
|