umlx5h/LLPlayer
LLPlayer
LLPlayer is a language learning media player and AI subtitle generator that integrates large language models for real-time audio transcription and translation. It functions as an LLM-integrated video player and SRT transcription tool, utilizing local or remote AI models to generate text subtitles from audio and video streams.
The project distinguishes itself through a contextual translation workflow that sends preceding subtitle lines to language models to maintain conversational flow and sentence structure. It also includes an optical character recognition system to convert bitmap-based subtitles into searchable and editable text.
The software provides a specialized environment for language study, featuring dual subtitle display with independent rendering to prevent visual overlap and a searchable sidebar for timestamp-linked navigation. It includes dictionary and lookup utilities that sync active subtitles to the system clipboard to trigger word definitions via external browser extensions.
Additional capabilities cover online video streaming, external subtitle downloads, and the export of AI-generated transcriptions to standard SRT files.
Features
- Language Learning Video Players - Provides a specialized video playback environment integrated with linguistic tools for foreign language study.
- Subtitle Translation - Translates video subtitles using AI that considers preceding lines to preserve sentence structure.
- Conversational Flow Preservation - Sends sequences of preceding subtitle lines to LLMs to maintain conversational flow and natural sentence structure.
- LLM Translation Integrations - Integrates large language models to perform context-aware subtitle translation that maintains conversational flow.
- Automated Video Subtitling - Provides AI-driven pipelines to automatically generate timed subtitles from audio or video streams.
- Concurrent Dual-Track Rendering - Provides dual subtitle display with independent rendering to ensure both languages are visible without overlapping.
- Automated Subtitle Generators - Uses AI models to automatically transcribe audio and embed subtitles for media without existing tracks.
- Language Learning Players - Ships a specialized media player with dual subtitles and dictionary lookups for language acquisition.
- Contextual Word Lookups - Provides instant word lookup interfaces that trigger definitions when subtitle text is selected.
- Real-Time Transcription - Implements low-latency, real-time transcription of audio streams to generate subtitles without blocking playback.
- OCR-Based Extraction - Extracts textual data from image-based subtitle bitmaps using optical character recognition.
- Bilingual Subtitle Renderers - Renders dual-track bilingual subtitles with independent offsets and sizing to prevent visual overlap.
- Hardcoded Subtitle Extraction - Converts burned-in bitmap subtitles into editable text via local OCR extraction.
- Timestamped Searchable Indices - Features a searchable sidebar that maps subtitles to a seekable timeline for rapid video navigation.
- Transcript-to-Timestamp Mapping - Maps searchable subtitle text to specific playback timestamps for rapid video navigation.
- Hardcoded Subtitle Extractors - Retrieves embedded text from video frames and converts it into standard subtitle files using OCR.
- Transcription Tools - Provides utilities to convert spoken audio into timed text and export them as SRT files.
- Optical Character Recognition - Uses optical character recognition to convert image-based bitmap subtitles into searchable and editable text.
- Video Streaming - Integrates AI subtitle generation and word lookup tools directly into a web-based video streaming playback engine.
Star history
How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
