Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,9 +1,12 @@
|
|
|
|
|
|
|
|
| 1 |
from transformers import pipeline, BlipForConditionalGeneration, BlipProcessor
|
| 2 |
import torchaudio
|
| 3 |
from torchaudio.transforms import Resample
|
| 4 |
import torch
|
| 5 |
import gradio as gr
|
| 6 |
-
|
|
|
|
| 7 |
|
| 8 |
# Initialize TTS model from Hugging Face
|
| 9 |
tts_model_name = "Kamonwan/blip-image-captioning-new"
|
|
@@ -14,8 +17,6 @@ model_id = "Kamonwan/blip-image-captioning-new"
|
|
| 14 |
blip_model = BlipForConditionalGeneration.from_pretrained(model_id)
|
| 15 |
blip_processor = BlipProcessor.from_pretrained(model_id)
|
| 16 |
|
| 17 |
-
app = Flask(__name__)
|
| 18 |
-
|
| 19 |
def generate_caption(image):
|
| 20 |
# Generate caption from image using Blip model
|
| 21 |
inputs = blip_processor(images=image, return_tensors="pt")
|
|
@@ -38,35 +39,7 @@ def generate_caption_api():
|
|
| 38 |
|
| 39 |
@app.route('/')
|
| 40 |
def index():
|
| 41 |
-
return
|
| 42 |
-
<!DOCTYPE html>
|
| 43 |
-
<html lang="en">
|
| 44 |
-
<head>
|
| 45 |
-
<meta charset="UTF-8">
|
| 46 |
-
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
| 47 |
-
<title>Gradio Interface</title>
|
| 48 |
-
</head>
|
| 49 |
-
<body>
|
| 50 |
-
<h1>Gradio Interface</h1>
|
| 51 |
-
{{ gr_interface|safe }}
|
| 52 |
-
</body>
|
| 53 |
-
</html>
|
| 54 |
-
""", gr_interface=demo.get_interface())
|
| 55 |
|
| 56 |
if __name__ == '__main__':
|
| 57 |
-
demo = gr.Interface(
|
| 58 |
-
fn=generate_caption,
|
| 59 |
-
inputs=gr.Image(),
|
| 60 |
-
outputs=[
|
| 61 |
-
gr.Textbox(label="Generated caption"),
|
| 62 |
-
gr.Button("Convert to Audio"),
|
| 63 |
-
gr.Audio(type="filepath", label="Generated Audio")
|
| 64 |
-
],
|
| 65 |
-
live=True
|
| 66 |
-
)
|
| 67 |
-
|
| 68 |
-
# Start Gradio interface
|
| 69 |
-
demo.launch(share=True)
|
| 70 |
-
|
| 71 |
-
# Start Flask app
|
| 72 |
app.run(host='0.0.0.0', port=5000)
|
|
|
|
| 1 |
+
# app.py
|
| 2 |
+
from flask import Flask, render_template, request, jsonify
|
| 3 |
from transformers import pipeline, BlipForConditionalGeneration, BlipProcessor
|
| 4 |
import torchaudio
|
| 5 |
from torchaudio.transforms import Resample
|
| 6 |
import torch
|
| 7 |
import gradio as gr
|
| 8 |
+
|
| 9 |
+
app = Flask(__name__)
|
| 10 |
|
| 11 |
# Initialize TTS model from Hugging Face
|
| 12 |
tts_model_name = "Kamonwan/blip-image-captioning-new"
|
|
|
|
| 17 |
blip_model = BlipForConditionalGeneration.from_pretrained(model_id)
|
| 18 |
blip_processor = BlipProcessor.from_pretrained(model_id)
|
| 19 |
|
|
|
|
|
|
|
| 20 |
def generate_caption(image):
|
| 21 |
# Generate caption from image using Blip model
|
| 22 |
inputs = blip_processor(images=image, return_tensors="pt")
|
|
|
|
| 39 |
|
| 40 |
@app.route('/')
|
| 41 |
def index():
|
| 42 |
+
return render_template("index.html")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
if __name__ == '__main__':
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
app.run(host='0.0.0.0', port=5000)
|