change default values in submit_video. improve readme and html.

README.md

@@ -1,6 +1,8 @@
 ## Multilang ASR Captioner
 
-A multilingual automatic speech recognition and video captioning tool using faster whisper on cpu.
+A multilingual automatic speech recognition and video captioning tool using faster whisper. 
+
+Supports real-time translation to english. Runs on consumer grade cpu.
 
 <video width="400" height="300" src="https://github.com/marquesafonso/multilang-asr-captioner/assets/79766107/fcff8ac1-cdfc-4400-821c-f797d84c2d8a"></video>
 
@@ -26,7 +28,7 @@ Check the [landing page](http://127.0.0.1:8000).
 
 From there you will see the [submit_video endpoint](http://127.0.0.1:8000/submit_video/) and the [documentation](http://127.0.0.1:8000/docs/)
 
-**Tip**: on Linux or Mac localhost will resolve directly to 0.0.0.0 but on windows you will need to change it to 127.0.0.1
+**Tip**: on Linux or Mac localhost will resolve directly to 0.0.0.0 but on windows you will need to change it to 127.0.0.1 or localhost
 
 ### Local
 
@@ -62,18 +64,4 @@ Then check the [landing page](http://127.0.0.1:8000).
 
 From there you will see the [submit_video endpoint](http://127.0.0.1:8000/submit_video/) and the [documentation](http://127.0.0.1:8000/docs/)
 
-**Tip**: on Linux or Mac localhost will resolve directly to 0.0.0.0 but on windows you will need to change it to 127.0.0.1
-
-### Command Line Interface
-
-Run the following code to use the CLI. The input file must be in mp4 format.
-
-```
-pipenv run python cli.py --invideo_filename '<your_file_name>' --max_words_per_line 8
-```
-
-Fontsize, Font, Background Color and Text Color arguments are available:
-
-```
-pipenv run python cli.py --invideo_filename '<your_file>' --max_words_per_line 8 --fontsize 28 --font "Arial-Bold" --bg_color None --text_color 'white'
-```
+**Tip**: on Linux or Mac localhost will resolve directly to 0.0.0.0 but on windows you will need to change it to 127.0.0.1 or localhost

cli.py

@@ -1,53 +0,0 @@
-from argparse import ArgumentParser
-from utils.transcriber import transcriber
-from utils.subtitler import subtitler
-from utils.convert_video_to_audio import convert_video_to_audio
-import logging, os
-from tqdm import tqdm
-
-logging.basicConfig(filename='main.log',
-                encoding='utf-8',
-                level=logging.DEBUG,
-                format='%(asctime)s %(levelname)s %(message)s',
-                datefmt='%m/%d/%Y %I:%M:%S %p')
-
-def main(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)
-    os.makedirs(INVIDEO_DIR, exist_ok=True)
-    SRT_PATH = os.path.join(INVIDEO_DIR, f"{invideo_filename}.srt")
-    OUTVIDEO_PATH = os.path.join(INVIDEO_DIR, f"result_{invideo_filename}.mp4")
-    with tqdm(total=100, desc="Overall Progress") as pbar:       
-        INVIDEO_PATH = os.path.join(INVIDEO_DIR, f"{invideo_filename}.mp4")
-        INAUDIO_PATH = os.path.join(INVIDEO_DIR, f"{invideo_filename}.m4a")
-        if not os.path.exists(INAUDIO_PATH):
-            convert_video_to_audio(INVIDEO_PATH,INAUDIO_PATH)
-        pbar.update(50)
-        if not os.path.exists(SRT_PATH):
-            transcriber(INAUDIO_PATH, SRT_PATH, max_words_per_line)
-        pbar.update(25)
-        subtitler(INVIDEO_PATH, SRT_PATH, OUTVIDEO_PATH, fontsize, font, bg_color, text_color)
-        pbar.update(25)
-
-if __name__ == '__main__':
-    parser = ArgumentParser()
-    parser.add_argument('--invideo_filename', required=True, type=str, help='Filename to caption.')
-    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('--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.invideo_filename,
-        args.max_words_per_line,
-        args.fontsize,
-        args.font,
-        args.bg_color,
-        args.text_color
-        )

static/landing_page.html

@@ -142,7 +142,8 @@
     <body>
         <div class="container">
             <h1>Multilang-ASR-Captioner</h1>
-            <p>A multilingual automatic speech recognition and video captioning tool using faster whisper on cpu.</p>
+            <p>A multilingual automatic speech recognition and video captioning tool using faster whisper.</p>
+            <p>Supports real-time translation to english. Runs on consumer grade cpu.</p>
             <a href="/submit_video" class="button submit">Submit Video</a>
             <a href="/docs" class="button docs">Documentation</a>
         </div>

static/submit_video.html

@@ -105,8 +105,8 @@
                 <option value="transcribe">Transcribe</option>
                 <option value="translate">Translate</option>
             </select><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>
+            Max words per line: <input type="number" name="max_words_per_line" value="6"><br>
+            Font size: <input type="number" name="fontsize" value="42"><br>
             Font: <input type="text" name="font" value="FuturaPTHeavy"><br>
             Background color (Pro tip: #00FFFF00 = transparent): <input type="text" name="bg_color" value="#070a13b3"><br>
             Text color: <input type="text" name="text_color" value="white"><br>