File size: 1,284 Bytes
a2a46d0 aa0a69d 3482efe b94d057 b405478 3482efe b94d057 51dfe6b dc1d260 c9ccf46 dc1d260 3482efe a2a46d0 dc1d260 3482efe |
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 |
import whisper
import gradio as gr
from transformers import pipeline
# Force the model to run on CPU
device = "cpu"
print("Running on CPU")
# Load the tiny Whisper model
model = whisper.load_model("base")
# Load the text summarization model from Hugging Face
summarizer = pipeline(task="summarization", model="facebook/bart-large-cnn")
# Function to transcribe and summarize the audio file
def transcribe_and_summarize(audio):
# Step 1: Transcribe the audio using Whisper
transcription_result = whisper_model.transcribe(audio)
transcription = transcription_result['text']
# Step 2: Summarize the transcription
summary = summarizer(transcription, min_length=10, max_length=100)
summary_text = summary[0]['summary_text']
return transcription, summary_text
# Create the Gradio interface
demo = gr.Interface(
fn=transcribe, # The function to be called for transcription
inputs=gr.Audio(type="filepath", label="Upload your audio file"), # Input audio field
outputs=gr.Textbox(label="Transcription"), # Output transcription
title="Whisper Speech-to-Text", # Title of the interface
description="Record audio using your microphone and get a transcription using the Whisper model."
)
# Launch the Gradio interface
demo.launch()
|