Google cloud speech to text : Dealing with high amount of input data in realtime

[vaibhav_jio]

Scenario: We are receiving huge amount of voice data streams which could be upto couple of minutes long. There will huge set of data streams as an input every second. This a real time application where I get live data from multiple users and return response from api. I am using google' AsyncStreamingRecognize to create stream. This stream open, read and write functions are blocking as I cannot proceed with other operation until success is returned by get() functions. Due to this my threads responsible for dealing with stream data are getting blocked. Is there a better way to where I can write high amount of input data without my thread being blocked for previous write function ? The code/setup works fine for a single call in real time. But I doubt how to design it well that could handle huge realtime incoming traffic

[atranscript]

Hi vaibhav_jio, sorry for possible inconvenience. I've noticed you might be explorer of speech recognition engine. I’m owner of a small company A-Transcript, which providing Finnish and Russian native transcription crowd services within comparably small budget (might process other languages as well). (website: a-transcript.com, email: info@a-transcript.com). I do have also some work experience behind on LaMDA and speech recognition engines. Wonder if you could provide any contacts, who are qualified to discuss about collaboration and taking business proposal. Thank you in advance and wish you a great day.

[hello249]

Do you have the capability to deliver speech-to-text subtitles on a VR glass product?

[atranscript]

hi hello249, thank you for request. Unfortunately at the moment I'm not familiar with such technology. My services is about providing qualified transcribers, onboard and manage them. (Type of transcription text could be subtitles as well as AI datasets (text with tags including). In order if you are agree with this, then would be glad to have calloboration. my company's email: <PII removed by staff>

[hello249]

Maybe put Redis in front of BigQuery?

Otherwise take SaaS like getstream.com

Adidas has run a successful campaign at them

https://getstream.com/case/getstream-case-study-adidas-advertising-on-twitch/

With kind regards,

Sjoerd