Update app.py
Browse files
app.py
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
import gradio as gr
|
2 |
-
|
3 |
from share_btn import community_icon_html, loading_icon_html, share_js
|
4 |
|
5 |
caption = gr.Blocks.load(name="spaces/SRDdev/Image-Caption")
|
@@ -8,7 +8,10 @@ audio_gen = gr.Blocks.load(name="spaces/haoheliu/audioldm-text-to-audio-generati
|
|
8 |
def infer(image_input):
|
9 |
cap = caption(image_input, fn_index=0)
|
10 |
sound = audio_gen(cap, 5, 2.5, 45, 3, fn_index=0)
|
11 |
-
|
|
|
|
|
|
|
12 |
|
13 |
title = """
|
14 |
<div style="text-align: center; max-width: 700px; margin: 0 auto;">
|
@@ -47,7 +50,7 @@ with gr.Blocks(css="style.css") as demo:
|
|
47 |
|
48 |
input_img = gr.Image(type="filepath", elem_id="input-img")
|
49 |
caption_output = gr.Textbox(label="Caption", lines=1, visible=False, elem_id="text-caption")
|
50 |
-
sound_output = gr.
|
51 |
|
52 |
generate = gr.Button("Generate SFX from Image")
|
53 |
|
|
|
1 |
import gradio as gr
|
2 |
+
from moviepy.editor import *
|
3 |
from share_btn import community_icon_html, loading_icon_html, share_js
|
4 |
|
5 |
caption = gr.Blocks.load(name="spaces/SRDdev/Image-Caption")
|
|
|
8 |
def infer(image_input):
|
9 |
cap = caption(image_input, fn_index=0)
|
10 |
sound = audio_gen(cap, 5, 2.5, 45, 3, fn_index=0)
|
11 |
+
FILETOCONVERT = AudioFileClip(sound)
|
12 |
+
FILETOCONVERT.write_audiofile("audio.wav")
|
13 |
+
FILETOCONVERT.close()
|
14 |
+
return gr.Textbox.update(value=cap, visible=True), "audio.wav", gr.Group.update(visible=True)
|
15 |
|
16 |
title = """
|
17 |
<div style="text-align: center; max-width: 700px; margin: 0 auto;">
|
|
|
50 |
|
51 |
input_img = gr.Image(type="filepath", elem_id="input-img")
|
52 |
caption_output = gr.Textbox(label="Caption", lines=1, visible=False, elem_id="text-caption")
|
53 |
+
sound_output = gr.Audio(label="Result", elem_id="sound-output")
|
54 |
|
55 |
generate = gr.Button("Generate SFX from Image")
|
56 |
|