sentence-transformers VS pytube

txtai is an open-source first system. Given it's own open-source roots, like-minded projects such as sentence-transformers are prioritized during development. But that doesn't mean txtai can't work with Embeddings API services.

Ok great. My use case is not very specific, but rather general. I am looking for a model that can perform asymmetric semantic search for the languages I mentioned earlier (Urdu, Persian, Arabic etc.). I have also looked into the sentence-transformer training documentation. Do you think it would be a good idea to use the XNLI dataset for fine-tuning? Or maybe you can suggest much better dataset. Furthermore, I am not sure if fine-tuning is suitable for my task. Because my use case is general so I can use already trained model.

The task you are looking for is semantic textual similarity. There are a few models and datasets out there that can do this. I'd probably start with the SemEval2017 Task 1 task description and competition entries here and then work outward from there (using something like SemanticScholar or Papers With Code to find newer state of the art works that cite these models if needed). For what it's worth you might find that Sentence Bert (SBERT) gives good vectors for cosine similarity comparison out of the box for this task.

Check out the sentence-transformers implementation. If I don't miss anything they don't exclude CLS when the pooling strategy is set to 'mean'

Break up transcript into shorter segments and convert segments to a 768 vector array. Use a process known as embedding using our second ML model, UKP Labs BERT’s sentence transformer model.

Not sure what kind of texts you have, but these models have a max sequence limit of 512 (approx 350 words or so). If you're texts are longer than that, consider splitting them up into chunks or creating a summary and taking an embedding of that. Some clustering algorithm may be the way to go here. Here's a bunch of examples. I use agglomerative for my use case.

https://github.com/UKPLab/sentence-transformers/tree/master/examples/training/data_augmentation (Augmented Encoding)

For vector representation you can take the mean and then pca to get the size that you want, but if you have time then use sentence transformers to train a vector representation instead.

Then in the virtual environment pip install pytube, this is the documentation if you are interested.

This is a known issue, likely started by something on YouTube's end.

Pytube was used for YouTube video download logic.

$ python3 Python 3.10.6 (main, Nov 14 2022, 16:10:14) [GCC 11.3.0] on linux Type "help", "copyright", "credits" or "license" for more information. >>> from pytube import Search >>> s = Search('once in a lifetime talking heads'); >>> print('https://youtu.be/%s' % s.results[0].video_id) Unexpected renderer encountered. Renderer name: dict_keys(['reelShelfRenderer']) Search term: once in a lifetime talking heads Please open an issue at https://github.com/pytube/pytube/issues and provide this log output. https://youtu.be/5IsSpAOD6K8

If a transcript doesn’t exist, download the audio of the video as an mp3 file with Pytube and use our first ML model, OpenAI Whisper to transcribe

After all the parsing is done, we need to download videos from returned URLs using pytube. Here we only download audio with filter(only_audio=True) option as this is what we only need for transcript and defining output_path to create videos/ path with filename that was done at the parsing stage, i.e absolute filename.

pip install git+https://github.com/openai/whisper.git pip install git+https://github.com/pytube/pytube.git pip install pandas