generate.py

from moviepy.editor import VideoFileClip
import whisper
import torch

# Path to your video
video_path = "C:/Users/path/Downloads/movie.mp4"
clip = VideoFileClip(video_path)
duration = clip.duration

chunk_length = 60  # 1 minute chunks

# Load whisper model
model = whisper.load_model("tiny.en")
model = model.to(torch.device("cpu"))  # force CPU

# Store all segments here
all_segments = []

for i, start in enumerate(range(0, int(duration), chunk_length)):
    end = min(start + chunk_length, duration)
    print(f"Processing chunk {i+1}: {start}-{end} seconds")

    # Create subclip
    subclip = clip.subclip(start, end)
    subclip_path = f"chunk_{i}.mp4"
    subclip.write_videofile(subclip_path, audio_codec="aac", verbose=False, logger=None)

    # Transcribe subclip
    result = model.transcribe(subclip_path, language="English")

    # Add segments to main list
    all_segments.extend(result["segments"])

# Save all segments to a single SRT file
with open("output.srt", "w", encoding="utf-8") as f:
    for i, segment in enumerate(all_segments, start=1):
        start = segment["start"]
        end = segment["end"]
        text = segment["text"].strip()

        # Format SRT timestamp
        def srt_time(seconds):
            ms = int((seconds % 1) * 1000)
            h = int(seconds // 3600)
            m = int((seconds % 3600) // 60)
            s = int(seconds % 60)
            return f"{h:02}:{m:02}:{s:02},{ms:03}"

        f.write(f"{i}\n{srt_time(start)} --> {srt_time(end)}\n{text}\n\n")

print("✅ SRT file generated: output.srt")