Created a NLTK summarizer model that works as follows :
- input of YOUTUBE VIDEO LINK
- convert video to audio
- generate text from audio
- Summarize the generated text
- Translation of summarized text
Used the HUGGING FACE TRANSFORMERS
silero-vad: For generating Audio ChunksWav2Vec2Processor: Pre-Trained TokenizerWav2Vec2ForCTC: Speech Recognition Modellong-t5-tglobal-base-16384-book-summary: Summarizer Modelfacebook/wmt19-en-ru: Translation Models