File size: 10,376 Bytes
f89c8ce 9392609 f89c8ce 04676e1 f89c8ce 8eab835 4b6f416 9392609 cc01dfc 8d4309d 9392609 8d4309d cc01dfc 9392609 8d4309d 4b6f416 9392609 4b6f416 aaf4dac f89c8ce 4b6f416 aaf4dac 4b6f416 8d4309d 9392609 aaf4dac 9392609 8d4309d 9392609 4b6f416 9392609 8d4309d 4b6f416 9392609 aaf4dac 9392609 aaf4dac 9392609 4b6f416 aaf4dac 4b6f416 aaf4dac 4b6f416 aaf4dac 8d4309d aaf4dac 9392609 aaf4dac 9392609 aaf4dac 9392609 aaf4dac 9392609 aaf4dac 9392609 aaf4dac 9392609 4b6f416 8d4309d 9392609 8d4309d 9392609 aaf4dac 8d4309d 4b6f416 9392609 4b6f416 9392609 8d4309d 9392609 8d4309d 9392609 8d4309d 9392609 8d4309d 9392609 aaf4dac 9392609 8d4309d 9392609 8d4309d 9392609 8d4309d 9392609 8d4309d aaf4dac 8d4309d aaf4dac 9392609 4b6f416 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 |
import streamlit as st
from moviepy.editor import VideoFileClip, AudioFileClip, TextClip, CompositeVideoClip, concatenate_audioclips
import whisper
from translate import Translator
from gtts import gTTS
import tempfile
import os
import numpy as np
from datetime import timedelta
import shutil
from pathlib import Path
# Set page configuration
st.set_page_config(
page_title="Tamil Movie Dubber",
page_icon="🎬",
layout="wide"
)
# Custom CSS
st.markdown("""
<style>
.stButton>button {
width: 100%;
border-radius: 5px;
height: 3em;
background-color: #FF4B4B;
color: white;
}
.stProgress .st-bo {
background-color: #FF4B4B;
}
</style>
""", unsafe_allow_html=True)
# Tamil voice configurations
TAMIL_VOICES = {
'Female 1': {'name': 'ta-IN-PallaviNeural', 'style': 'normal'},
'Female 2': {'name': 'ta-IN-PallaviNeural', 'style': 'formal'},
'Male 1': {'name': 'ta-IN-ValluvarNeural', 'style': 'normal'},
'Male 2': {'name': 'ta-IN-ValluvarNeural', 'style': 'formal'}
}
class TamilTextProcessor:
@staticmethod
def normalize_tamil_text(text):
"""Normalize Tamil text for better pronunciation"""
tamil_numerals = {'௦': '0', '௧': '1', '௨': '2', '௩': '3', '௪': '4',
'௫': '5', '௬': '6', '௭': '7', '௮': '8', '௯': '9'}
for tamil_num, eng_num in tamil_numerals.items():
text = text.replace(tamil_num, eng_num)
return text
@staticmethod
def process_for_tts(text):
"""Process Tamil text for TTS"""
text = ''.join(char for char in text if ord(char) < 65535)
text = ' '.join(text.split())
return text
@st.cache_resource
def load_whisper_model():
"""Load Whisper model with caching"""
return whisper.load_model("base")
class VideoProcessor:
def __init__(self):
self.temp_dir = Path(tempfile.mkdtemp())
self.whisper_model = load_whisper_model()
def create_temp_path(self, suffix):
"""Create a temporary file path"""
return str(self.temp_dir / f"temp_{os.urandom(4).hex()}{suffix}")
def cleanup(self):
"""Clean up temporary directory"""
try:
shutil.rmtree(self.temp_dir)
except Exception as e:
st.warning(f"Cleanup warning: {e}")
def transcribe_video(self, video_path):
"""Transcribe video audio using Whisper"""
try:
with VideoFileClip(video_path) as video:
# Extract audio to temporary file
audio_path = self.create_temp_path(".wav")
video.audio.write_audiofile(audio_path, fps=16000, verbose=False, logger=None)
# Transcribe using Whisper
result = self.whisper_model.transcribe(audio_path)
return result["segments"], video.duration
except Exception as e:
raise Exception(f"Transcription error: {str(e)}")
def translate_segments(self, segments):
"""Translate segments to Tamil"""
translator = Translator(to_lang='ta')
translated_segments = []
for segment in segments:
try:
translated_text = translator.translate(segment["text"])
translated_text = TamilTextProcessor.normalize_tamil_text(translated_text)
translated_text = TamilTextProcessor.process_for_tts(translated_text)
translated_segments.append({
"text": translated_text,
"start": segment["start"],
"end": segment["end"],
"duration": segment["end"] - segment["start"]
})
except Exception as e:
st.warning(f"Translation warning for segment: {str(e)}")
# Keep original text if translation fails
translated_segments.append({
"text": segment["text"],
"start": segment["start"],
"end": segment["end"],
"duration": segment["end"] - segment["start"]
})
return translated_segments
def generate_tamil_audio(self, text):
"""Generate Tamil audio using gTTS"""
try:
audio_path = self.create_temp_path(".mp3")
tts = gTTS(text=text, lang='ta', slow=False)
tts.save(audio_path)
return audio_path
except Exception as e:
raise Exception(f"Audio generation error: {str(e)}")
def create_subtitle_clip(self, txt, fontsize, color, size):
"""Create a subtitle clip"""
return TextClip(
txt=txt,
fontsize=fontsize,
color=color,
bg_color='rgba(0,0,0,0.5)',
size=size,
method='caption'
)
def process_video(video_data, voice_type, generate_subtitles=True, subtitle_size=24, subtitle_color='white'):
"""Main video processing function"""
processor = VideoProcessor()
try:
# Save uploaded video to temporary file
input_path = processor.create_temp_path(".mp4")
with open(input_path, "wb") as f:
f.write(video_data)
# Load video
video = VideoFileClip(input_path)
# Create progress tracking
progress_text = st.empty()
progress_bar = st.progress(0)
# Step 1: Transcribe
progress_text.text("Transcribing video...")
segments, duration = processor.transcribe_video(input_path)
progress_bar.progress(0.25)
# Step 2: Translate
progress_text.text("Translating to Tamil...")
translated_segments = processor.translate_segments(segments)
progress_bar.progress(0.50)
# Step 3: Generate audio
progress_text.text("Generating Tamil audio...")
subtitle_clips = []
audio_clips = []
for i, segment in enumerate(translated_segments):
# Generate audio
audio_path = processor.generate_tamil_audio(segment["text"])
audio_clip = AudioFileClip(audio_path)
audio_clips.append(audio_clip.set_start(segment["start"]))
# Create subtitle if enabled
if generate_subtitles:
subtitle_clip = processor.create_subtitle_clip(
segment["text"],
subtitle_size,
subtitle_color,
(video.w, None)
)
subtitle_clip = (subtitle_clip
.set_position(('center', 'bottom'))
.set_start(segment["start"])
.set_duration(segment["duration"]))
subtitle_clips.append(subtitle_clip)
progress_bar.progress(0.50 + (0.4 * (i + 1) / len(translated_segments)))
# Step 4: Combine everything
progress_text.text("Creating final video...")
# Combine audio clips
final_audio = CompositeVideoClip([*audio_clips])
# Create final video
if generate_subtitles:
final_video = CompositeVideoClip([video, *subtitle_clips])
else:
final_video = video
# Set audio
final_video = final_video.set_audio(final_audio)
# Write final video
output_path = processor.create_temp_path(".mp4")
final_video.write_videofile(
output_path,
codec='libx264',
audio_codec='aac',
temp_audiofile=processor.create_temp_path(".m4a"),
remove_temp=True,
verbose=False,
logger=None
)
progress_bar.progress(1.0)
progress_text.text("Processing complete!")
return output_path
except Exception as e:
raise Exception(f"Video processing error: {str(e)}")
finally:
# Cleanup
processor.cleanup()
def main():
st.title("Tamil Movie Dubbing System")
st.markdown("""
👋 Welcome! This tool helps you:
- 🎥 Convert English videos to Tamil
- 🗣️ Generate Tamil voiceovers
- 📝 Add Tamil subtitles
""")
# File uploader
video_file = st.file_uploader("Upload Video File", type=['mp4', 'mov', 'avi'])
if not video_file:
st.warning("Please upload a video to begin.")
return
# Settings
col1, col2 = st.columns(2)
with col1:
voice_type = st.selectbox("Select Voice", list(TAMIL_VOICES.keys()))
with col2:
generate_subtitles = st.checkbox("Generate Subtitles", value=True)
if generate_subtitles:
col3, col4 = st.columns(2)
with col3:
subtitle_size = st.slider("Subtitle Size", 16, 32, 24)
with col4:
subtitle_color = st.color_picker("Subtitle Color", "#FFFFFF")
# Process video
if st.button("Start Dubbing"):
try:
with st.spinner("Processing video..."):
output_path = process_video(
video_file.read(),
voice_type,
generate_subtitles,
subtitle_size if generate_subtitles else 24,
subtitle_color if generate_subtitles else 'white'
)
# Show success message
st.success("டப்பிங் வெற்றிகரமாக முடிந்தது!")
# Display video
st.video(output_path)
# Download button
with open(output_path, "rb") as f:
st.download_button(
"⬇️ Download Dubbed Video",
f,
file_name="tamil_dubbed_video.mp4",
mime="video/mp4"
)
except Exception as e:
st.error(f"Processing failed: {str(e)}")
st.error("Please try uploading a different video or check if the format is supported.")
if __name__ == "__main__":
main() |