{"id":12970,"date":"2025-01-26T07:38:34","date_gmt":"2025-01-26T06:38:34","guid":{"rendered":"https:\/\/flaven.fr\/?post_type=bf_videos_manager&#038;p=12970"},"modified":"2025-01-26T07:53:52","modified_gmt":"2025-01-26T06:53:52","slug":"beyond-subtitles-ai-powered-video-content-discovery-ia-nlp-spacy-whisper-streamlit-python","status":"publish","type":"bf_videos_manager","link":"https:\/\/flaven.fr\/videos\/beyond-subtitles-ai-powered-video-content-discovery-ia-nlp-spacy-whisper-streamlit-python\/","title":{"rendered":"Beyond Subtitles: AI-Powered Video Content Discovery #ia #nlp #spacy #whisper #streamlit #python"},"content":{"rendered":"<p>This video covers advanced techniques for analyzing subtitle files using machine learning models. We explore a Streamlit application that uses the spaCy library to load and process subtitles from a JSON file, extracting entities and key phrases along with their timecodes. Users can upload a video file and a JSON transcription file, and the application displays the video with interactive buttons to jump to specific timecodes based on the analysis. The script utilizes Streamlit for the user interface and spaCy for natural language processing.<\/p>\n<p><b>Full Details:<\/b><br \/>\nYou can read the article on my blog: Content Quality: How Sentence Embeddings Can Save AI-Generated Content and some other concerns on AI: Environmental Impact, Job Loss<br \/>\n<a href=\"https:\/\/wp.me\/p3Vuhl-3mP\" target=\"_blank\" rel=\"noopener\">https:\/\/wp.me\/p3Vuhl-3mP<\/a><\/p>\n<p><b>The code is available on my github account:<\/b><br \/>\n<a href=\"https:\/\/shorturl.at\/y5HNV\" target=\"_blank\" rel=\"noopener\">https:\/\/shorturl.at\/y5HNV<\/a><\/p>\n<p>\ufe0f<b>Dive Deeper:<\/b><br \/>\nYou can listen to the 2 &#8220;podcasts&#8221; extracted from this Blog Post Audio made with NotebookLM on this post:<br \/>\n<a href=\"https:\/\/on.soundcloud.com\/KYsxEU7Zh1qdDLGo8\" target=\"_blank\" rel=\"noopener\">https:\/\/on.soundcloud.com\/KYsxEU7Zh1qdDLGo8<\/a><br \/>\n<a href=\"https:\/\/on.soundcloud.com\/THjokmLiH8q194Gr9\" target=\"_blank\" rel=\"noopener\">https:\/\/on.soundcloud.com\/THjokmLiH8q194Gr9<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>This video covers advanced techniques for analyzing subtitle files using machine learning models. We explore a Streamlit application that uses the spaCy library to load&hellip; <\/p>\n<p class=\"text-center\"><a href=\"https:\/\/flaven.fr\/videos\/beyond-subtitles-ai-powered-video-content-discovery-ia-nlp-spacy-whisper-streamlit-python\/\" class=\"more-link\">Continue reading &rarr; <span class=\"screen-reader-text\">Beyond Subtitles: AI-Powered Video Content Discovery #ia #nlp #spacy #whisper #streamlit #python<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":12185,"comment_status":"open","ping_status":"closed","template":"","bf_videos_manager_tag":[2668,3244,2685,3060,2803,2684,2846,3062,2672,2688,2806,2766,3190,3061,3058,3030,2749,2677],"bf_videos_manager_cat":[2729,3091,2700,3081,2681,2682,2767,2678,2679,2680],"class_list":["post-12970","bf_videos_manager","type-bf_videos_manager","status-publish","has-post-thumbnail","hentry","bf_videos_manager_tag-ai","bf_videos_manager_tag-ai-generated","bf_videos_manager_tag-anaconda","bf_videos_manager_tag-multilingual","bf_videos_manager_tag-natural-language-processing","bf_videos_manager_tag-nlp","bf_videos_manager_tag-poc","bf_videos_manager_tag-product-owner","bf_videos_manager_tag-python","bf_videos_manager_tag-spacy","bf_videos_manager_tag-streamlit","bf_videos_manager_tag-television","bf_videos_manager_tag-transcript","bf_videos_manager_tag-transcription","bf_videos_manager_tag-whisper","bf_videos_manager_tag-work","bf_videos_manager_tag-workflow","bf_videos_manager_tag-yolo","bf_videos_manager_cat-agile","bf_videos_manager_cat-ai","bf_videos_manager_cat-anaconda","bf_videos_manager_cat-api","bf_videos_manager_cat-development","bf_videos_manager_cat-experiences","bf_videos_manager_cat-news","bf_videos_manager_cat-python","bf_videos_manager_cat-tutorials","bf_videos_manager_cat-videos"],"jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/flaven.fr\/happy-api\/wp\/v2\/bf_videos_manager\/12970","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/flaven.fr\/happy-api\/wp\/v2\/bf_videos_manager"}],"about":[{"href":"https:\/\/flaven.fr\/happy-api\/wp\/v2\/types\/bf_videos_manager"}],"author":[{"embeddable":true,"href":"https:\/\/flaven.fr\/happy-api\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/flaven.fr\/happy-api\/wp\/v2\/comments?post=12970"}],"version-history":[{"count":5,"href":"https:\/\/flaven.fr\/happy-api\/wp\/v2\/bf_videos_manager\/12970\/revisions"}],"predecessor-version":[{"id":12986,"href":"https:\/\/flaven.fr\/happy-api\/wp\/v2\/bf_videos_manager\/12970\/revisions\/12986"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/flaven.fr\/happy-api\/wp\/v2\/media\/12185"}],"wp:attachment":[{"href":"https:\/\/flaven.fr\/happy-api\/wp\/v2\/media?parent=12970"}],"wp:term":[{"taxonomy":"bf_videos_manager_tag","embeddable":true,"href":"https:\/\/flaven.fr\/happy-api\/wp\/v2\/bf_videos_manager_tag?post=12970"},{"taxonomy":"bf_videos_manager_cat","embeddable":true,"href":"https:\/\/flaven.fr\/happy-api\/wp\/v2\/bf_videos_manager_cat?post=12970"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}