sentence-transformers VS youtube-transcript-api

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.

no whisper involced. https://github.com/jdepoix/youtube-transcript-api

Get the transcript of a Youtube video using the URL from the youtube transcript api.

> What are the parts of the brain that become de-synchronized in the ADHD brain?

>> The default mode network and the task networks become de-synchronized in the ADHD brain.

> What are the three parts of the brain that become de-synchronized in the ADHD brain?

>> The default mode network, the task networks, and the dopamine circuits.

From https://youtu.be/hFL6qRIJZ_Y?t=1714:

> An area called the dorsolateral prefrontal cortex ... the posterior cingulate cortex, and ... the lateral parietal lobe ... these are three brain areas that normally are synchronized in their activities ... that's how it is in a typical person. In a person with ADHD ... these brain areas are not playing well with each other.

I wonder if part of the problem might be the usage of text to speech. Did you consider scraping the transcriptions instead? e.g. with https://github.com/jdepoix/youtube-transcript-api

from what I can make out, it's using a python api behind the scenes but it's hard-coded to use english. The site you linked seems to be using the Youtube api, so maybe this is something you can do with your own youtube API key?