This video seems really helpful, but it takes a lot of effort for me to... well.. recognize and understand your speech... I can understand most of it, but whenever you pause to think of how to say something, then you say that thing pretty fast and with less space between words, and I usually can't keep up with those parts. I do not have the energy to understand what you say for 40 minutes. Other people seem to be finding the video very helpful, so don't let my inability to understand you stop you from making videos.

keep it up .it was very helpfull

can we get source code or google colab link ???

It was very helpful

It was awesome, Thanks a lot

thanks for giving this source

you have purposefully removed some content from the notebook i guess. Which is why i am getting error. We both know why

knowledge packed video but was extremely hard to follow

it is also better if you give us the repo link for this

Its taking a lot of time for a single epoch to run on my pc and its suggested to use more than 50 epochs . What possible measures should i take?

dears , source code please???????????????????????????????????????????????????????????????????????????????????????

GD! sorry sir, I have one question , how can I use thos code for listening morse code and convert it to text. Could you pls help me with this?

Hello sir when will be the HCR next video coming... waiting... thankyou

text to speech deeplearning please. It is not found in some dialectal languages. currently there is no mn in google

hello sir i tried the code form the video but i got an error in "Start the training process" section at the line "history = model.fit" . Can you please help me out ?

I want to fine-tune your model on Persian language, what do I need to change except alphabet?

Sir in the pre-processing step you are mapping the variables instead of that can we use word Embedding technique?

Sir i have question i used this code in google colab pro i runned with 50 epochs and it didn't give me a true result ,didn't predecte true . so what'is problem and you have a solution!

Sir, can you help with the code for taking wav file from user as input and then predicting its transcription

Do u have the source code plz ?

Hello, Sir. How can I train for new language (none English)? Is it that ok by changing Audio and Transcribe datasets? Thank you.

Sir is it possible to take inputs from the User while the Voice assistant reading the a text

ca. you please sent me the code please

Sir can u pls help me with the code of identifying any language using transformer model. Pls pls pls

sir i have sanskrit dataset can i do the same thing for sanskrit speech recognition

Hi, I have a question, does this system recognize speech from mp4 files as well?

But you split the data in to training and validation....where is the test split???

hello sir please am working on a similar project applying speech to text to a dataset of my local language is there anyway to contact you?

I've just sent an email for the source code. Hope that email finds you well😢

Sir when I'm running the Validation samples I'm getting an error. Transpose expects a vector of size 2. But input(1) is a vector of size 3. [ Op: Transpose] How to resolve this ?

I tried to contact with you but you did not respond for my messages?

Sir is it suitable for telugu language?

bro sub smj me aa rha he lekin maths ka kuchh smj nahi aa rha.....

Hello Sir, can i get the source code?? Please🙏🏻

hello sir can you send me source code please

kaise improve kru maths bro

Send code

can we get the source code? You number is also not showing in whatsapp.

Can we get the source code please?

can i get the source code ? i contacted the whatsapp number but no response

Sir i have question i used this code in google colab pro i runned with 50 epochs and it didn't give me a true result ,didn't predecte true . so what'is problem and you have a solution!