add font and text color args. fix api behaviour. improve readme.

README.md

@@ -22,14 +22,28 @@ Note that this assumes a proper Git installation and ssh key configuration.
 
 ## Quick start
 
-Run the following code to your example. The example is based on a youtube video url (optional):
+### Command Line Interface
+
+Run the following code to your example using the CLI. The example is based on a youtube video url (optional):
+
+```
+pipenv run python .\cli.py --invideo_filename '<your_file_name>' --video_url 'https://www.youtube.com/watch?v=<your_youtube_video>' --max_words_per_line 8
+```
+
+Fontsize, Font, Background Color and Text Color arguments are available:
 
 ```
-pipenv run python .\main.py --invideo_dir './data/' --invideo_filename '<your_video>.mp4' --outvideo_path './data/<output_video>.mp4' --video_url 'https://www.youtube.com/watch?v=<your_youtube_video>' --srt_path '<your_srt_file>.srt'
+pipenv run python .\cli.py --invideo_filename '<your_file>' --video_url 'https://www.youtube.com/watch?v=<your_youtube_video>' --max_words_per_line 8 --fontsize 28 --font "Arial-Bold" --bg_color None --text_color 'white'
 ```
 
-Fontsize and Background Color arguments are available:
+### API
+
+A FastAPI API is also made available.
+
+To start the API run:
 
 ```
-pipenv run python .\main.py --invideo_dir './data/' --invideo_filename '<your_video>.mp4' --outvideo_path './data/<output_video>.mp4' --video_url 'https://www.youtube.com/watch?v=<your_youtube_video>' --srt_path '<your_srt_file>.srt' --fontsize 28 --bg_color None
+pipenv run uvicorn main:app --reload
 ```
+
+Then check the [submit_video](http://127.0.0.1:8000/submit_video/) endpoint.

cli_app.py → cli.py

@@ -11,11 +11,13 @@ logging.basicConfig(filename='main.log',
                 format='%(asctime)s %(levelname)s %(message)s',
                 datefmt='%m/%d/%Y %I:%M:%S %p')
 
-def main(video_url,
-        invideo_filename,
-        fontsize,
-        bg_color,
-        max_words_per_line
+def main(video_url:str,
+        invideo_filename:str,
+        max_words_per_line:int,
+        fontsize:int,
+        font:str,
+        bg_color:str,
+        text_color:str
         ):
     INVIDEO_DIR = os.path.join('data/',invideo_filename)
     if not os.path.exists(INVIDEO_DIR):
@@ -29,28 +31,32 @@ def main(video_url,
             if not os.path.exists(SRT_PATH):
                 transcriber(stream_title, SRT_PATH, max_words_per_line)
             pbar.update(33.33)
-            subtitler(stream_title, SRT_PATH, OUTVIDEO_PATH,fontsize, bg_color)
+            subtitler(stream_title, SRT_PATH, OUTVIDEO_PATH,fontsize, font, bg_color, text_color)
             pbar.update(33.34)
             return
         INVIDEO_PATH = os.path.join(INVIDEO_DIR, f"{invideo_filename}.mp4")
         if not os.path.exists(SRT_PATH):
             transcriber(INVIDEO_PATH, SRT_PATH, max_words_per_line)
         pbar.update(66.66)
-        subtitler(INVIDEO_PATH, SRT_PATH, OUTVIDEO_PATH, fontsize,bg_color)
+        subtitler(INVIDEO_PATH, SRT_PATH, OUTVIDEO_PATH, fontsize, font, bg_color, text_color)
         pbar.update(33.34)
 
 if __name__ == '__main__':
     parser = ArgumentParser()
-    parser.add_argument('--invideo_filename', required=True, type=str, help='filename')
+    parser.add_argument('--invideo_filename', required=True, type=str, help='Filename to caption.')
     parser.add_argument('--video_url', required=False, default=None, type=str, help='A video file to be subtitled (Optional)')
+    parser.add_argument("--max_words_per_line", type=int, default=None, help="the maximum number of words in a segment. (int)")
     parser.add_argument('--fontsize', required=False, default=32, type=int, help='Font size for captions (int)')
-    parser.add_argument('--bg_color', required=False, default="#070a13b3", type=str, help='Hex color value for caption background colour.')
-    parser.add_argument("--max_words_per_line", type=int, default=None, help="(requires --word_timestamps True, no effect with --max_line_width) the maximum number of words in a segment")
+    parser.add_argument('--font', required=False, default="FuturaPTHeavy", type=str, help='Font style for captions (str)')
+    parser.add_argument('--bg_color', required=False, default="#070a13b3", type=str, help='Hex color value for caption background colour. (str)')
+    parser.add_argument('--text_color', required=False, default="white", type=str, help='color value for caption text. (str)')
     args = parser.parse_args()
     # Example usage
     main(args.video_url,
         args.invideo_filename,
+        args.max_words_per_line,
         args.fontsize,
+        args.font,
         args.bg_color,
-        args.max_words_per_line,
+        args.text_color
         )

example_cmd.txt

@@ -1,5 +0,0 @@
-[example no background]
-pipenv run python .\main.py --invideo_dir './data/' --invideo_filename '<your_video>.mp4' --outvideo_path './data/<output_video>.mp4' --video_url 'https://www.youtube.com/watch?v=<your_youtube_video>' --srt_path '<your_srt_file>.srt' --fontsize 28 --bg_color None
-
-[example with background]
-pipenv run python .\main.py --invideo_dir './data/' --invideo_filename '<your_video>.mp4' --outvideo_path './data/<output_video>.mp4' --video_url 'https://www.youtube.com/watch?v=<your_youtube_video>' --srt_path '<your_srt_file>.srt'

main.py

@@ -16,10 +16,13 @@ async def get_form():
     <html>
         <body>
             <form action="/process_video/" enctype="multipart/form-data" method="post">
-                <input type="file" name="file"><br>
-                Font size: <input type="number" name="fontsize" value="32"><br>
-                Background color: <input type="text" name="bg_color" value="#070a13b3"><br>
+                Video File: <input type="file" name="video_file"><br>
+                Subtitles File: <input type="file" name="srt_file"><br>
                 Max words per line: <input type="number" name="max_words_per_line" value="8"><br>
+                Font size: <input type="number" name="fontsize" value="36"><br>
+                Font: <input type="text" name="font" value="FuturaPTHeavy"><br>
+                Background color: <input type="text" name="bg_color" value="#070a13b3"><br>
+                Text color: <input type="text" name="text_color" value="white"><br>
                 <input type="submit">
             </form>
         </body>
@@ -28,26 +31,43 @@ async def get_form():
     return HTMLResponse(content=html_content)
 
 @app.post("/process_video/")
-async def process_video_api(file: UploadFile = File(...),
-                            fontsize: Optional[int] = Form(32),
+async def process_video_api(video_file: UploadFile = File(...),
+                            srt_file: Optional[UploadFile] = File(...),
+                            max_words_per_line: Optional[int] = Form(8),
+                            fontsize: Optional[int] = Form(36),
+                            font: Optional[str] = Form("FuturaPTHeavy"),
                             bg_color: Optional[str] = Form("#070a13b3"),
-                            max_words_per_line: Optional[int] = Form(8)):
+                            text_color: Optional[str] = Form("white")
+                            ):
     try:
-        if not str(file.filename).endswith('.mp4'):
+        if not str(video_file.filename).endswith('.mp4'):
             raise HTTPException(status_code=400, detail="Invalid file type. Please upload an MP4 file.")
-        # Save the uploaded file to a temporary file
+        # Create temp dir
         temp_dir = os.path.join(os.getcwd(),"temp")
         os.makedirs(temp_dir, exist_ok=True)
-        temp_input_path = os.path.join(temp_dir, file.filename)
-        # Copy UploadFile to the temp_input_path
+        temp_input_path = os.path.join(temp_dir, video_file.filename)
+        # Copy video UploadFile to the temp_input_path
         with open(temp_input_path, 'wb') as buffer:
             try:
-                shutil.copyfileobj(file.file, buffer)
+                shutil.copyfileobj(video_file.file, buffer)
             finally:
-                file.file.close()
+                video_file.file.close()
+        # Copy srt UploadFile to the temp_input_path
+        if srt_file.size > 0:
+            SRT_PATH = os.path.abspath(f"{temp_input_path.split('.')[0]}.srt")
+            with open(SRT_PATH, 'wb') as buffer:
+                try:
+                    shutil.copyfileobj(srt_file.file, buffer)
+                finally:
+                    srt_file.file.close()
+            # Process the video
+            output_path = process_video(temp_input_path, SRT_PATH, max_words_per_line, fontsize, font, bg_color, text_color)
+            return FileResponse(output_path, media_type="video/mp4", filename=f"result_{video_file.filename}")
         # Process the video
-        output_path = process_video(temp_input_path, fontsize, bg_color, max_words_per_line)
+        output_path = process_video(temp_input_path, None, max_words_per_line, fontsize, font, bg_color, text_color)
+        # FileResponse(output_path, media_type="text/srt", filename=f"result_{video_file.filename.split('.')[0]}.srt")
         # Return the processed video file
-        return FileResponse(output_path, media_type="video/mp4", filename=f"result_{file.filename}")
+        return FileResponse(output_path, media_type="video/mp4", filename=f"result_{video_file.filename}")
+                
     except Exception as e:
         raise HTTPException(status_code=500, detail=str(e))

utils/process_video.py

@@ -1,5 +1,4 @@
 # Import necessary modules
-from utils.download_video import download_video
 from utils.transcriber import transcriber
 from utils.subtitler import subtitler
 import logging, os
@@ -13,15 +12,21 @@ logging.basicConfig(filename='main.log',
 
 # API Function
 def process_video(invideo_filename:str,
+                  srt_path: str,
+                  max_words_per_line:int,
                   fontsize:str,
+                  font:str,
                   bg_color:str,
-                  max_words_per_line:int
+                  text_color:str
                   ):
+    OUTVIDEO_PATH = os.path.join("temp/", "result.mp4")
+    if srt_path:
+        subtitler(invideo_filename, srt_path, OUTVIDEO_PATH, fontsize, font, bg_color, text_color)
+        return OUTVIDEO_PATH
     SRT_PATH = os.path.abspath(f"{invideo_filename.split('.')[0]}.srt")
-    OUTVIDEO_PATH = os.path.join("temp/", f"result.mp4")
     if not os.path.exists(SRT_PATH):
         transcriber(invideo_filename, SRT_PATH, max_words_per_line)
     logging.info("Transcription Complete")
-    subtitler(invideo_filename, SRT_PATH, OUTVIDEO_PATH, fontsize, bg_color)
+    subtitler(invideo_filename, SRT_PATH, OUTVIDEO_PATH, fontsize, font, bg_color, text_color)
     logging.info("Subtitling Complete")
     return OUTVIDEO_PATH

utils/subtitler.py

@@ -23,22 +23,25 @@ def parse_srt(srt_file):
 
 
 def subtitler(video_file:str,
-            srt_file:str,
+            srt_path:str,
             output_file:str,
             fontsize:int,
-            bg_color:str):
+            font: str,
+            bg_color:str,
+            text_color:str
+            ):
     """Add subtitles from an SRT file to a video."""
     video_file = os.path.abspath(video_file)
-    srt_file = os.path.abspath(srt_file)
+    srt_path = os.path.abspath(srt_path)
     output_file = os.path.abspath(output_file)
     
     clip = VideoFileClip(video_file)
-    subtitles = parse_srt(srt_file)
+    subtitles = parse_srt(srt_path)
 
     subtitle_clips = []
     for start, end, text in subtitles:
         # Create TextClip with specified styling
-        txt_clip = TextClip(text, fontsize=fontsize, color='white', font="Arial-Bold", method='caption',
+        txt_clip = TextClip(text, fontsize=fontsize, color=text_color, font=font, method='caption',
                             bg_color=bg_color, align='center', size=(clip.w*1/2, None))
         txt_clip = txt_clip.set_position(('center', 'bottom')).set_duration(clip.duration).set_start(start).set_end(end)
         subtitle_x_position = 'center'

utils/transcriber.py

@@ -58,6 +58,4 @@ def transcriber(input_path:str,
 
     logging.info("Detected language '%s' with probability %f" % (info.language, info.language_probability))
     logging.info("Writing file...")
-    write_srt(segments=segments, srt_path=srt_path, max_words_per_line=max_words_per_line)
-
-
+    write_srt(segments=segments, srt_path=srt_path, max_words_per_line=max_words_per_line)