Recognition Hangs Indefinitely When Completing Sentences in Nova-2-ea
Closed this issue · 1 comments
What is the current behavior?
What's happening that seems wrong?
The Deepgram Nova-2-ea model gets stuck in a loop where it keeps waiting for the user to finish the sentence even after the user has actually completed the sentence. Consequently, the user has to utter something further to somehow prompt the model to finish.
I have never faced this issue in Nova model.
Steps to reproduce
To make it faster to diagnose the root problem. Tell us how can we reproduce the bug.
- Input Sentence: Start a transcription session with Deepgram Nova2.
- Speak: Say a complete sentence or phrase clearly.
- Wait: Observe that Deepgram Nova2 does not recognize the end of the sentence and continues waiting indefinitely.
Expected behavior
The model should be able to recognize when the user has completed their sentence and stop waiting for further input.
What would you expect to happen when following the steps above?
Please tell us about your environment
We want to make sure the problem isn't specific to your operating system or programming language.
- Operating System/Version: Windows 10
- Language: [all | TypeScript | Python | PHP | etc]
- Browser: Chrome
Other information
Anything else we should know? (e.g. detailed explanation, stack-traces, related issues, suggestions how to fix, links for us to have context, eg. stack overflow, codepen, etc)
If possible, it would be helpful to investigate any previously raised issues (if any) related to this problem, and if the team can share any suggestions on how to overcome this issue on our end while you work on it, it would be of great help.
Hi @aniket-rudder could you please raise this as an issue on our community? This repo is specifically for the JavaScript SDK, and this is an issue with transcription from the API.