├── Generate_English_Subtitles_Video_with_OpenAI_Whisper.ipynb
├── LICENSE
├── README.md
└── app.py
/LICENSE:
--------------------------------------------------------------------------------
1 | MIT License
2 |
3 | Copyright (c) 2022 amrrs
4 |
5 | Permission is hereby granted, free of charge, to any person obtaining a copy
6 | of this software and associated documentation files (the "Software"), to deal
7 | in the Software without restriction, including without limitation the rights
8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 |
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 |
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # subtitle-embedded-video-generator
2 |
3 | Powered by OpenAI Whisper & Gradio
4 |
5 |
6 |
7 | 
8 |
9 |
10 |
11 | If you just want a Gradio App, refer this [app.py](app.py)
12 |
13 |
14 | # Demo
15 |
16 | 
17 |
--------------------------------------------------------------------------------
/app.py:
--------------------------------------------------------------------------------
1 |
2 | import gradio as gr
3 | import os
4 | import sys
5 | import subprocess
6 | #from moviepy.editor import VideoFileClip
7 |
8 | import whisper
9 | from whisper.utils import write_vtt
10 |
11 | model = whisper.load_model("medium")
12 |
13 | def video2mp3(video_file, output_ext="mp3"):
14 | filename, ext = os.path.splitext(video_file)
15 | subprocess.call(["ffmpeg", "-y", "-i", video_file, f"{filename}.{output_ext}"],
16 | stdout=subprocess.DEVNULL,
17 | stderr=subprocess.STDOUT)
18 | return f"{filename}.{output_ext}"
19 |
20 |
21 | def translate(input_video):
22 |
23 | audio_file = video2mp3(input_video)
24 |
25 | options = dict(beam_size=5, best_of=5)
26 | translate_options = dict(task="translate", **options)
27 | result = model.transcribe(audio_file,**translate_options)
28 |
29 | output_dir = '/content/'
30 | audio_path = audio_file.split(".")[0]
31 |
32 | with open(os.path.join(output_dir, audio_path + ".vtt"), "w") as vtt:
33 | write_vtt(result["segments"], file=vtt)
34 |
35 | subtitle = audio_path + ".vtt"
36 | output_video = audio_path + "_subtitled.mp4"
37 |
38 | os.system(f"ffmpeg -i {input_video} -vf subtitles={subtitle} {output_video}")
39 |
40 | return output_video
41 |
42 |
43 |
44 | title = "Add Text/Caption to your YouTube Shorts - MultiLingual"
45 |
46 | block = gr.Blocks()
47 |
48 | with block:
49 |
50 | with gr.Group():
51 | with gr.Box():
52 |
53 |
54 |
55 | with gr.Row().style():
56 |
57 | inp_video = gr.Video(
58 | label="Input Video",
59 | type="filepath",
60 | mirror_webcam = False
61 | )
62 | op_video = gr.Video()
63 | btn = gr.Button("Generate Subtitle Video")
64 |
65 |
66 |
67 |
68 |
69 |
70 | btn.click(translate, inputs=[inp_video], outputs=[op_video])
71 |
72 | gr.HTML('''
73 |
77 | ''')
78 |
79 | block.launch(debug = True)
80 |
--------------------------------------------------------------------------------