Spaces:
Sleeping
Sleeping
File size: 6,104 Bytes
deb7eb8 4e21277 deb7eb8 4e21277 deb7eb8 4e21277 6335b41 deb7eb8 4e21277 deb7eb8 53e054f deb7eb8 2d3e3b7 2b61740 |
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 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 |
import streamlit as st
from streamlit_lottie import st_lottie
from utils import write_vtt, write_srt
from flores200_codes import flores_codes
import ffmpeg
import requests
from typing import Iterator
from io import StringIO
import numpy as np
import pathlib
import os
st.set_page_config(page_title="Captions", page_icon=":movie_camera:", layout="wide")
# Sema Translator
Public_Url = 'https://lewiskimaru-helloworld.hf.space' #endpoint
# Define a function that we can use to load lottie files from a link.
@st.cache(allow_output_mutation=True)
def load_lottieurl(url: str):
r = requests.get(url)
if r.status_code != 200:
return None
return r.json()
APP_DIR = pathlib.Path(__file__).parent.absolute()
LOCAL_DIR = APP_DIR / "local_transcript"
LOCAL_DIR.mkdir(exist_ok=True)
save_dir = LOCAL_DIR / "output"
save_dir.mkdir(exist_ok=True)
col1, col2 = st.columns([1, 3])
with col1:
lottie = load_lottieurl("https://assets6.lottiefiles.com/packages/lf20_cjnxwrkt.json")
st_lottie(lottie)
with col2:
st.write("""
## Sema Captions
##### ➠ Upload a video file and a transcript as .srt or .vtt file and get a video with subtitles.""")
def getSubs(segments: Iterator[dict], format: str, maxLineWidth: int) -> str:
segmentStream = StringIO()
if format == 'vtt':
write_vtt(segments, file=segmentStream, maxLineWidth=maxLineWidth)
elif format == 'srt':
write_srt(segments, file=segmentStream, maxLineWidth=maxLineWidth)
else:
raise Exception("Unknown format " + format)
segmentStream.seek(0)
return segmentStream.read()
def split_video_audio(uploaded_file):
with open(f"{save_dir}/input.mp4", "wb") as f:
f.write(uploaded_file.read())
audio = ffmpeg.input(f"{save_dir}/input.mp4")
audio = ffmpeg.output(audio, f"{save_dir}/output.wav", acodec="pcm_s16le", ac=1, ar="16k")
ffmpeg.run(audio, overwrite_output=True)
def translate(userinput, target_lang, source_lang=None):
if source_lang:
url = f"{Public_Url}/translate_enter/"
data = {
"userinput": userinput,
"source_lang": source_lang,
"target_lang": target_lang,
}
response = requests.post(url, json=data)
result = response.json()
print(type(result))
source_lange = source_lang
translation = result['translated_text']
else:
url = f"{Public_Url}/translate_detect/"
data = {
"userinput": userinput,
"target_lang": target_lang,
}
response = requests.post(url, json=data)
result = response.json()
source_lange = result['source_language']
translation = result['translated_text']
return source_lange, translation
def main():
uploaded_video = st.file_uploader("Upload Video File", type=["mp4", "avi", "mov", "mkv"])
# get the name of the input_file
if uploaded_video is not None:
filename = uploaded_video.name[:-4]
else:
filename = None
transcript_file = st.file_uploader("Upload Transcript File", type=["srt", "vtt"])
if transcript_file is not None:
transcript_name = transcript_file.name
else:
transcript_name = None
if uploaded_video is not None and transcript_file is not None:
if transcript_name[-3:] == "vtt":
with open("uploaded_transcript.vtt", "wb") as f:
f.writelines(transcript_file)
f.close()
with open(os.path.join(os.getcwd(), "uploaded_transcript.vtt"), "rb") as f:
vtt_file = f.read()
if st.button("Generate Video with Subtitles"):
with st.spinner("Generating Subtitled Video"):
split_video_audio(uploaded_video)
video_file = ffmpeg.input(f"{save_dir}/input.mp4")
audio_file = ffmpeg.input(f"{save_dir}/output.wav")
ffmpeg.concat(video_file.filter("subtitles", "uploaded_transcript.vtt"), audio_file, v=1, a=1).output("final.mp4").global_args('-report').run(quiet=True, overwrite_output=True)
video_with_subs = open("final.mp4", "rb")
col3, col4 = st.columns(2)
with col3:
st.video(uploaded_video)
with col4:
st.video(video_with_subs)
st.download_button(label="Download Video with Subtitles",
data=video_with_subs,
file_name=f"{filename}_with_subs.mp4")
elif transcript_name[-3:] == "srt":
with open("uploaded_transcript.srt", "wb") as f:
f.writelines(transcript_file)
f.close()
with open(os.path.join(os.getcwd(), "uploaded_transcript.srt"), "rb") as f:
srt_file = f.read()
if st.button("Generate Video with Subtitles"):
with st.spinner("Generating Subtitled Video"):
split_video_audio(uploaded_video)
video_file = ffmpeg.input(f"{save_dir}/input.mp4")
audio_file = ffmpeg.input(f"{save_dir}/output.wav")
ffmpeg.concat(video_file.filter("subtitles", "uploaded_transcript.srt"), audio_file, v=1, a=1).output("final.mp4").run(quiet=True, overwrite_output=True)
video_with_subs = open("final.mp4", "rb")
col3, col4 = st.columns(2)
with col3:
st.video(uploaded_video)
with col4:
st.video(video_with_subs)
st.download_button(label="Download Video with Subtitles",
data=video_with_subs,
file_name=f"{filename}_with_subs.mp4")
else:
st.error("Please upload a .srt or .vtt file")
else:
st.info("Please upload a video file and a transcript file ")
if __name__ == "__main__":
main()
st.markdown("###### ")
st.markdown("###### Powered by [sema © 2024](https://www.sema.wiki)")
|