Speech Recognition using Deep Learning Part 1

[@ioogleio]

Thanks for your introduction. I have a question, how much audios(in hours) needed to train a good model?

[@bhootpurvmanusya]

is deepspeech not compatible with vs 16 of nodejs?

[@marco114]

would love a video on how to improve the audio, using your own models, and making a model from another speaker if possible

[@Choknutchi23]

Would a Gtx 1050 suffice?

[@michalaugustyniak6449]

did you make part 2 ?

[@philiphales9993]

I subscribed but it's impossible to read almost everything and that makes it really hard to follow what you're talking about . could you at least increase the font size ? thanks

[@TravelVideosShorts]

Try changing the quality to 720p60 in the Settings; you should be able to see the text clearly.

[@murtazahussain8224]

is deepspeech compatible with nvidia Rtx 3090?

[@chrisatmachine]

GPU shouldn't matter. Drivers might.

[@murtazahussain8224]

@@chrisatmachine yeah drivers are not compatible .. is there any solution because I already got two NVIDIA RTX3090 and deepspeech drivers are not compatible with it

[@chrisatmachine]

@@murtazahussain8224 hmm, is it drivers or CUDA version?

[@murtazahussain8224]

@@chrisatmachine cuda version they aren't compatible.. do u know any developer can help ??

[@chrisatmachine]

@@murtazahussain8224 I may be able to help. What version of CUDA are you on?

[@rfyorfyo5022]

looks complicated even im not a linux user

[@chrisatmachine]

It's a little complicated sure but I think the work they're doing with deepspeech is awesome. Works just fine on Mac too.