Download find_steps.py from gamora/ShortsAI: direct link, hf CLI and curl.
- Browser
- Download file 4.23 kB
-
https://huggingface.co/spaces/gamora/ShortsAI/resolve/main/find_steps.py
- Command line
-
hf download hf://spaces/gamora/ShortsAI/find_steps.py
-
curl -L -o find_steps.py https://huggingface.co/spaces/gamora/ShortsAI/resolve/main/find_steps.py
4.23 kB
| from sentence_transformers import SentenceTransformer, util | |
| import json | |
| from datetime import datetime | |
| # Function to read and parse the JSON file | |
| def find_next_step(data, current_context): | |
| try: | |
| # Read the JSON file | |
| # with open(file_path, 'r') as file: | |
| # data = json.load(file) | |
| # Initialize counters | |
| total_videos = len(data) | |
| total_scenes = 0 | |
| max_score=0.0 | |
| step={ | |
| "path" :"", | |
| "start":"", | |
| "end": "", | |
| } | |
| # Iterate through each video entry | |
| print(f"Processing {total_videos} videos...\n") | |
| for index, video in enumerate(data, 1): | |
| video_type = video.get('type', 'Unknown') | |
| video_path = video.get('path', 'No path provided') | |
| scenes = video.get('scenes', []) | |
| scene_count = len(scenes) | |
| total_scenes += scene_count | |
| # Iterate through each scene in the video | |
| for scene_index, scene in enumerate(scenes, 1): | |
| timestamp = scene.get('timestamp', 'No timestamp') | |
| description = scene.get('description', 'No description') | |
| time_obj = datetime.strptime(timestamp, "%M:%S.%f") | |
| start = time_obj.minute * 60 + time_obj.second + time_obj.microsecond / 1_000_000 | |
| score=compare_phrases(description,current_context) | |
| if score > max_score: | |
| if scene_index+1<len(scenes): | |
| next_scene=scenes[scene_index+1] | |
| next_timestamp=next_scene.get('timestamp', 'No timestamp') | |
| time_obj = datetime.strptime(next_timestamp, "%M:%S.%f") | |
| stop = time_obj.minute * 60 + time_obj.second + time_obj.microsecond / 1_000_000 | |
| step={ | |
| "path" :video_path, | |
| "start":start, | |
| "end": stop, | |
| "description":description | |
| } | |
| else: | |
| step={ | |
| "path" :video_path, | |
| "start":start, | |
| "end": "", | |
| "description":description | |
| } | |
| max_score=score | |
| if "Error" in description: | |
| print("[Note: This scene contains an error]") | |
| # Print overall summary | |
| print(f"Summary:") | |
| print(f" Total Videos: {total_videos}") | |
| print(f" Total Scenes: {total_scenes}") | |
| except FileNotFoundError: | |
| print(f"Error: File '{file_path}' not found.") | |
| except json.JSONDecodeError: | |
| print("Error: Invalid JSON format.") | |
| except Exception as e: | |
| print(f"Error: An unexpected error occurred: {str(e)}") | |
| return step | |
| def compare_phrases(phrase1,phrase2="Passing around a dj mixing a song"): | |
| model = SentenceTransformer('all-MiniLM-L6-v2',local_files_only=True) | |
| # Get embeddings | |
| embedding1 = model.encode(phrase1, convert_to_tensor=True) | |
| embedding2 = model.encode(phrase2, convert_to_tensor=True) | |
| # Compute cosine similarity | |
| similarity_score = util.cos_sim(embedding1, embedding2)[0][0] | |
| # print(f"Similarity score: {similarity_score:.4f}") | |
| # print(phrase1) | |
| return similarity_score | |
| def find_all_steps(data, context): | |
| context = context.replace("\n", "").lower() | |
| all_actions=context.split(".") | |
| steps=[] | |
| for action in all_actions: | |
| step=find_next_step(data,action) | |
| steps.append(step) | |
| return steps | |
| if __name__ == "__main__": | |
| file_path = '/Users/georgia.bucea/products/ShortsAI/all_files_metadata.json' # Update this with the actual file path | |
| context = """I am walking around San Francisco and passing around the big white building. I am walking around a music band and DJ mixing a song. I am showing a demo on the phone, I am explaining the demo on the mobile phone""" | |
| # Read the JSON file | |
| with open(file_path, 'r') as file: | |
| data = json.load(file) | |
| steps=find_all_steps(data,context) | |
| print(steps) | |