You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Add Speech2Text support so there's minimal typing required. We initially had done an implementation using Mozilla's DeepSpeech pre-trained model but it didn't work well for different types of accents.
We are thinking of using Chrome's built in Web Speech API and Firefox Voice addon and populate our query box with the text response. User can edit/fix the text and submit the query to get code. Another option which isn't explored yet, is to finetune DeepSpeech on a custom dataset, more suited for understanding dataframe, variable & column names.
Using Firefox voice is fine for short term/poc but it won't be useful for long term as it will no longer be supported by Mozilla due to their realigned priorities. For details please visit: https://github.com/mozilla-extensions/firefox-voice#status
I have had varying results with different algorithms in sagemaker. It would be nice to use the Google API but there are at least a hundered different AI's, some free, some not.
Add Speech2Text support so there's minimal typing required. We initially had done an implementation using Mozilla's DeepSpeech pre-trained model but it didn't work well for different types of accents.
We are thinking of using Chrome's built in Web Speech API and Firefox Voice addon and populate our query box with the text response. User can edit/fix the text and submit the query to get code. Another option which isn't explored yet, is to finetune DeepSpeech on a custom dataset, more suited for understanding dataframe, variable & column names.
Any contributions are welcome.
Following solutions can be explored:
The text was updated successfully, but these errors were encountered: