Asapanna Rakesh

> Hey @INF800, we presently support zero shot voice cloning for American & British speakers only. For an indian accent, you will need to finetune. I would recommend 1-5 mins...

The apt name would be `small_model_filepath` instead of `small_model_filename`.

Needed this because my API key did not have access to gpt4 and there wasn't any direct way for changing data synthesis model

Would like natural / authentic speech models like bark or some other alternative

Quick workaround (janky) that I was able to come up is using `rx.script` by writing my own JS code manipulating `document.cookie`. But what would be the best way to do...

> Even with the above method, I am not sure how to access the output of JS code in my Python code. For this (janky) method I think I can...

Anyone??

Can I use instructions present in below link for time series dataset as well? https://github.com/huggingface/datasets/blob/master/ADD_NEW_DATASET.md

Thankyou. This is how raw data looks like before cleaning for an individual stocks: 1. https://github.com/INF800/marktech/tree/raw-data/f/data/raw 2. https://github.com/INF800/marktech/tree/raw-data/t/data/raw 3. https://github.com/INF800/marktech/tree/raw-data/rdfn/data/raw 4. https://github.com/INF800/marktech/tree/raw-data/irbt/data/raw 5. https://github.com/INF800/marktech/tree/raw-data/hll/data/raw 6. https://github.com/INF800/marktech/tree/raw-data/infy/data/raw 7. https://github.com/INF800/marktech/tree/raw-data/reli/data/raw 8. https://github.com/INF800/marktech/tree/raw-data/hdbk/data/raw...

Referencing https://github.com/qingsongedu/time-series-transformers-review