initial commit

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+flagged/
+__pycache__/

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.9-slim-buster
+
+RUN apt-get update && apt-get install -y ffmpeg
+
+WORKDIR /app
+
+COPY requirements.txt .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+CMD ["python", "app.py"]

README.md

@@ -0,0 +1,11 @@
+---
+title: Video Convertor
+emoji: 👀
+colorFrom: blue
+colorTo: purple
+sdk: docker
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,92 @@
+import gradio as gr
+import subprocess
+from pathlib import Path
+from utlis import HHMMSS_to_sec
+
+def trim_media(media_in, media_out, start, end): 
+    
+    # options for writing out audio if converting
+    WAV_CHANNELS = 1
+    WAV_SAMPLE_RATE = 16000
+    
+    media_type = Path(media_in).suffix
+    ext = Path(media_out).suffix
+
+    if isinstance(start, str):
+        start_sec = HHMMSS_to_sec(start)
+    else: 
+        start_sec = float(start)
+    if isinstance(end, str):
+        end_sec = HHMMSS_to_sec(end)
+    else:
+        end_sec = float(end)
+
+    if ext == '.wav':
+        # convert to wav with standard format for audio models
+        print(f'...Using ffmpeg to trim video from {start} to {end} \n   and convert to {WAV_SAMPLE_RATE}Hz WAV with {WAV_CHANNELS} channels...')            
+        print(f'...generating {media_out}...')            
+
+        subprocess.call(['ffmpeg',
+            '-y',
+            '-i',
+            media_in,
+            '-ss',
+            f'{start_sec}',
+            '-to',
+            f'{end_sec}',
+            '-acodec',
+            'pcm_s16le',
+            '-ac',
+            WAV_CHANNELS,
+            '-ar',
+            WAV_SAMPLE_RATE,
+            media_out,
+            '-hide_banner', 
+            '-loglevel', 
+            'warning'        
+        ], shell=False)   
+    
+    else: 
+        print(f'...Using ffmpeg to trim video from {start_sec} to {end_sec}...')      
+        print(f'...generating {media_out}...')            
+      
+        subprocess.call(['ffmpeg',
+            '-y',
+            '-i',
+            media_in,
+            '-ss',
+            f'{start_sec}',
+            '-to',
+            f'{end_sec}',
+            '-c',
+            'copy',
+            media_out,
+            '-hide_banner', 
+            '-loglevel', 
+            'warning'        
+        ], shell=False) 
+        
+def convert_video(input_file, output_format, start_time, end_time):
+    try:
+        # Set output file name and extension
+        output_file = f"{input_file.name.split('.')[0]}.{output_format}"
+        
+        if start_time == "":
+            start_time = 0
+        if end_time == "":
+            end_time = 0
+        # Trim the video
+        trim_media(input_file.name, output_file, start_time, end_time)
+        
+        return output_file
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+input_file = gr.File(label="Select video file")
+output_format = gr.Dropdown(choices=["mkv", "MOV", "mp4", "wav"], label="Select output format")
+start_time = gr.Textbox(label="Start time (in seconds or HH:MM:SS). Leave blank to start at beginning.")
+end_time = gr.Textbox(label="End time (in seconds or HH:MM:SS). Leave blank to end at end.")
+output_file = gr.File(label="Download converted file")
+
+interface = gr.Interface(fn=convert_video, inputs=[input_file, output_format, start_time, end_time], outputs=output_file, title="Video Trimmer")
+interface.launch(server_name="0.0.0.0", server_port=7860)

requirments.txt

@@ -0,0 +1,3 @@
+gradio==3.23.0
+moviepy==1.0.3
+panads==1.1.3

utlis.py

@@ -0,0 +1,35 @@
+import os
+import csv
+import re
+import pandas as pd
+from pathlib import Path
+
+def HHMMSS_to_sec(time_str):
+    """Get Seconds from timestamp string with milliseconds."""
+    if not time_str:
+        return None
+    if time_str.count(':')==2:
+        h, m, s = time_str.split(':')
+    elif time_str.count(':')==3:
+    # weird timestamps where there is a field followign seconds delimited by colon
+        h, m, s, u = time_str.split(':')
+        # determine whether ms field is in tenths or hundredths or thousandths by countng how many digits
+        if len(u)==1:
+            print('Weird time format detected - HH:MM:SS:tenths - please verify this is how you want the time interpreted')
+            ms = float(u)/10
+        elif len(u)==2: # hundredths
+            ms = float(u)/100
+        elif len(u)==3: # hundredths
+            ms = float(u)/1000
+        else:
+            print(f'input string format not supported: {time_str}')
+            return None
+        s = int(s)+ms
+    elif time_str.count(':')==1:
+        # print('missing HH from timestamp, assuming MM:SS')
+        m, s = time_str.split(':')
+        h=0
+    else:
+        print(f'input string format not supported: {time_str}')
+        return None
+    return int(h) * 3600 + int(m) * 60 + float(s)