Spaces:
Runtime error
Runtime error
File size: 3,495 Bytes
79d2f90 975b4c6 79d2f90 975b4c6 79d2f90 |
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 |
# from transformers import pipeline, BlipForConditionalGeneration, BlipProcessor, AutoTokenizer, AutoModelForSeq2SeqLM
# import torchaudio
# from torchaudio.transforms import Resample
# import torch
# from flask import Flask, request, jsonify
# # from PLI import Image
# # import pytesseract
# # import gradio as gr
# app = Flask(__name__)
# # Initialize TTS model from Hugging Face
# tts_model_name = "suno/bark"
# tts = pipeline(task="text-to-speech", model=tts_model_name)
# # Initialize Blip model for image captioning
# model_id = "dblasko/blip-dalle3-img2prompt"
# blip_model = BlipForConditionalGeneration.from_pretrained(model_id)
# blip_processor = BlipProcessor.from_pretrained(model_id)
# @app.route('/generate_caption_and_audio', methods=['POST'])
# def generate_caption ():
# try:
# # Get image file from the request
# image = request.files['image']
# # Generate caption from image using Blip model
# inputs = blip_processor(images=image, return_tensors="pt")
# pixel_values = inputs.pixel_values
# generated_ids = blip_model.generate(pixel_values=pixel_values, max_length=50)
# generated_caption = blip_processor.batch_decode(generated_ids, skip_special_tokens=True, temperature=0.8, top_k=40, top_p=0.9)[0]
# # Use TTS model to convert generated caption to audio
# audio_output = tts(generated_caption)
# audio_path = "generated_audio_resampled.wav"
# torchaudio.save(audio_path, torch.tensor(audio_output[0]), audio_output["sampling_rate"])
# return jsonify({'generate_caption': generate_caption, 'audio_path': audio_path})
# except Exception as e:
# return jsonify({'error': str(e)})
# if __name__ == '__main__':
# app.run(debug=True)
from flask import Flask, request, jsonify
from transformers import pipeline, BlipForConditionalGeneration, BlipProcessor
import torchaudio
from torchaudio.transforms import Resample
import torch
from io import BytesIO
app = Flask(__name__)
# Initialize TTS model from Hugging Face
tts_model_name = "suno/bark"
tts = pipeline(task="text-to-speech", model=tts_model_name)
# Initialize Blip model for image captioning
model_id = "dblasko/blip-dalle3-img2prompt"
blip_model = BlipForConditionalGeneration.from_pretrained(model_id)
blip_processor = BlipProcessor.from_pretrained(model_id)
def generate_caption(image):
# Generate caption from image using Blip model
inputs = blip_processor(images=image, return_tensors="pt")
pixel_values = inputs.pixel_values
generated_ids = blip_model.generate(pixel_values=pixel_values, max_length=50)
generated_caption = blip_processor.batch_decode(generated_ids, skip_special_tokens=True, temperature=0.8, top_k=40, top_p=0.9)[0]
# Use TTS model to convert generated caption to audio
audio_output = tts(generated_caption)
audio_path = "generated_audio_resampled.wav"
torchaudio.save(audio_path, torch.tensor(audio_output[0]), audio_output["sampling_rate"])
return generated_caption, audio_path
@app.route('/upload', methods=['POST'])
def upload_image():
if 'image' not in request.files:
return jsonify({'error': 'No image provided'}), 400
image_file = request.files['image'].read()
generated_caption, audio_path = generate_caption(image_file)
return jsonify({'generated_caption': generated_caption, 'audio_url': audio_path}), 200
if __name__ == '__main__':
app.run(host='0.0.0.0', port=5000, debug=True)
|