File size: 2,210 Bytes
891d755 bf5a004 6480da6 8162cb8 6480da6 8162cb8 6480da6 8162cb8 bf5a004 8162cb8 |
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 |
import gradio as gr
def dub_video(video_url):
# यहाँ आप बैकएंड फंक्शन को कॉल करें, जो वीडियो डाउनलोड करे, ऑडियो निकाले, हिंदी में डब करे और डब्ड वीडियो रिटर्न करे
# उदाहरण के लिए: processed_video_path = backend_dubbing_function(video_url, "hindi")
# return processed_video_path
return "Processed video path will be returned here (replace with actual function call)"
demo = gr.Interface(
fn=dub_video,
inputs=gr.Textbox(label="Enter video URL"),
outputs=gr.Video(label="Hindi Dubbed Video"),
title="Video Dubbing AI (Hindi)",
description="Enter a video URL to get it dubbed in Hindi."
)
demo.launch()
from pytube import YouTube
video_url = "https://www.youtube.com/watch?v=YOUR_VIDEO_ID"
yt = YouTube(video_url)
stream = yt.streams.filter(only_audio=True).first()
stream.download(filename="video_audio.mp4")
from moviepy.editor import VideoFileClip
video = VideoFileClip("video_audio.mp4")
audio = video.audio
audio.write_audiofile("output_audio.wav")
from transformers import WhisperProcessor, WhisperForConditionalGeneration
import torch
from datasets import load_dataset
# Load model and processor
processor = WhisperProcessor.from_pretrained("openai/whisper-small")
model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-small")
# Optional: Use GPU if available
device = "cuda" if torch.cuda.is_available() else "cpu"
model = model.to(device)
# Load sample audio (here using a dummy dataset, aap apni audio file bhi use kar sakte hain)
ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
sample = ds[0]["audio"]
# Prepare audio input
input_features = processor(sample["array"], sampling_rate=sample["sampling_rate"], return_tensors="pt").input_features
input_features = input_features.to(device)
# Generate transcription
predicted_ids = model.generate(input_features)
# Decode transcription
transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
print(transcription)
|