Update app.py
Browse files
app.py
CHANGED
@@ -1,64 +1,64 @@
|
|
|
|
|
|
1 |
import gradio as gr
|
2 |
-
from
|
|
|
|
|
3 |
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
|
|
8 |
|
|
|
|
|
|
|
|
|
9 |
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
system_message,
|
14 |
-
max_tokens,
|
15 |
-
temperature,
|
16 |
-
top_p,
|
17 |
-
):
|
18 |
-
messages = [{"role": "system", "content": system_message}]
|
19 |
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
|
|
|
|
|
|
25 |
|
26 |
-
|
|
|
|
|
|
|
27 |
|
28 |
-
|
|
|
|
|
29 |
|
30 |
-
|
31 |
-
|
32 |
-
max_tokens=max_tokens,
|
33 |
-
stream=True,
|
34 |
-
temperature=temperature,
|
35 |
-
top_p=top_p,
|
36 |
-
):
|
37 |
-
token = message.choices[0].delta.content
|
38 |
|
39 |
-
|
40 |
-
|
41 |
|
|
|
42 |
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
gr.Textbox(
|
50 |
-
gr.
|
51 |
-
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
52 |
-
gr.Slider(
|
53 |
-
minimum=0.1,
|
54 |
-
maximum=1.0,
|
55 |
-
value=0.95,
|
56 |
-
step=0.05,
|
57 |
-
label="Top-p (nucleus sampling)",
|
58 |
-
),
|
59 |
],
|
|
|
|
|
60 |
)
|
61 |
|
|
|
|
|
62 |
|
63 |
-
if __name__ == "__main__":
|
64 |
-
demo.launch()
|
|
|
1 |
+
import whisper
|
2 |
+
import openai
|
3 |
import gradio as gr
|
4 |
+
from gtts import gTTS
|
5 |
+
from moviepy.editor import VideoFileClip
|
6 |
+
import os
|
7 |
|
8 |
+
def transcribe_video(video_path):
|
9 |
+
# Extract audio from video file
|
10 |
+
video = VideoFileClip(video_path)
|
11 |
+
audio_path = "temp_audio.wav"
|
12 |
+
video.audio.write_audiofile(audio_path, codec='pcm_s16le')
|
13 |
|
14 |
+
# Load Whisper model and transcribe audio
|
15 |
+
model = whisper.load_model("base")
|
16 |
+
result = model.transcribe(audio_path)
|
17 |
+
transcription = result["text"]
|
18 |
|
19 |
+
# Remove temporary audio file
|
20 |
+
os.remove(audio_path)
|
21 |
+
return transcription
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
|
23 |
+
def summarize_text(text):
|
24 |
+
response = openai.Completion.create(
|
25 |
+
engine="text-davinci-003",
|
26 |
+
prompt=f"Summarize the following text:\n\n{text}",
|
27 |
+
max_tokens=150
|
28 |
+
)
|
29 |
+
summary = response.choices[0].text.strip()
|
30 |
+
return summary
|
31 |
|
32 |
+
def text_to_speech(text, language="en"):
|
33 |
+
tts = gTTS(text=text, lang=language)
|
34 |
+
tts.save("summary_audio.mp3")
|
35 |
+
return "summary_audio.mp3"
|
36 |
|
37 |
+
def process_video(video):
|
38 |
+
# Transcribe the video
|
39 |
+
transcription = transcribe_video(video)
|
40 |
|
41 |
+
# Summarize the transcription
|
42 |
+
summary = summarize_text(transcription)
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
|
44 |
+
# Convert summary to speech
|
45 |
+
audio_file = text_to_speech(summary)
|
46 |
|
47 |
+
return transcription, summary, audio_file
|
48 |
|
49 |
+
# Create Gradio interface
|
50 |
+
iface = gr.Interface(
|
51 |
+
fn=process_video,
|
52 |
+
inputs=gr.Video(label="Upload Video"),
|
53 |
+
outputs=[
|
54 |
+
gr.Textbox(label="Transcription"),
|
55 |
+
gr.Textbox(label="Summary"),
|
56 |
+
gr.Audio(label="Summary Audio")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
],
|
58 |
+
title="Video Transcription and Summarization",
|
59 |
+
description="Upload a video file to transcribe and summarize its content."
|
60 |
)
|
61 |
|
62 |
+
# Launch the interface
|
63 |
+
iface.launch()
|
64 |
|
|
|
|