I wish I had enough spare cash to buy you a coffee. I was having issues getting whisper, python installed and playing together. I spent hours on it. You did it for me in a single line. You sir are a scholar and a gentleman. Thank you.
*Thank You So Much!!!🌹🌹🌹🌹* I have been a big Whisper now for awhile. Last 2 times I installed I went through the big nightmare install. Now with my new computer I wanted something EZ and I found you. SO EZ! It did not install first time but at the end it said Whisper not installed would you like to reinstall. I clicked YES and it worked. Big Thank You. I have done a couple shout outs to whisper on my channel about a year ago or so. :) Thanks much... *Fun's Channel🤗*
If you followed this tutorial and the script still doesn't work, make sure you navigate to C:\Users\[Your Username] before running the script. Sometimes Powershell opens in a different folder and it doesn't work
HI there, thanks for the awesome efforts. Unfortunately this or the full tutorial are not working for me. Here it reaches a place asking "Do you want to install cuDNN? (y/n) [Default: n]:" If I click n it aborts and if I click yes it asks "Enter the cuDNN zip's path:" and I have no idea what that is..
Is Anaconda necessary to transcribe mp3 files speech to text? All mp3 speech files are stored on a local windows directory C:\Recodings . Each file needs to be transcribed separately into text. Your help would be highly appreciated
Hi there, could you please advise what is the best and easiest way to transcribe mp3 files speech recordings to text with no coding experience at all. Thank you
It asked me if I wanted to install cuDNN. I typed n, it was unable to install whisper. I ran the script again and typed y, it is not asking for the "cuDNN zip's path"
How do I use Whisper after I've installed it? I mean where will it appear on my computer and how do I attach files to it so that it transcribes them? Thanks
Hi TC! I hope you're doing well. I was wondering if you could possibly create a video on how to train the Vicuna model. I'm really interested in learning more about it. Thank you so much in advance!
could you tell me what file path(s) all the dependence get installed to? i would also like to know how i can manually install the right python version without the potental of messing up other similar projects like this that might rely on other versions
i call bs, this gives error 2 sec after start of the command. :( Posting the error leads to the comment getting removed, so forking cant even do that...
I get an error about my python version because I have python 3.11 "Python version is not between 3.8 and 3.10. Assuming you've installed the correct version, please enter the comand you use to access Python 3.8/3.10."
Most python scripts that call for 3.8 or a close by version are broken on 3.11. Some changes cause programs to just not work on this newer version. Just enter the following and hit enter: python
@@TroubleChute Thanks this seems to be working. EDIT: Didnt install everything that was needed, was able to install most stuff manually but numba doesnt work with 3.11. I uninstalled 3.11 and installed 3.10, but for some reason it needs to be called with "py" instead of python now. Looks to be working fine now.
@@TroubleChute Any chance you could make a guide on using opus-mt? I gave it a try and couldn't figure out how to use the models I wanted (chinese to english).
Thank you very much, it works for me. I only have a problem in a previous installation whisper put the transcription in a txt. file and it does not save anything in it.
Does anyone know how to get whisper to accept text input? It seems to be looking for an audio stream by default since I get an ffmpeg error when I try: whisper --language zh --task translate .\test.txt
I wish I had enough spare cash to buy you a coffee. I was having issues getting whisper, python installed and playing together. I spent hours on it. You did it for me in a single line. You sir are a scholar and a gentleman. Thank you.
Thank you for putting this together. Those are the most parenthetical brackets I've ever seen, that's for sure.
*Thank You So Much!!!🌹🌹🌹🌹* I have been a big Whisper now for awhile. Last 2 times I installed I went through the big nightmare install. Now with my new computer I wanted something EZ and I found you. SO EZ! It did not install first time but at the end it said Whisper not installed would you like to reinstall. I clicked YES and it worked. Big Thank You. I have done a couple shout outs to whisper on my channel about a year ago or so. :) Thanks much... *Fun's Channel🤗*
You are legend ! with your "no stress" installation scripts !!
i tried your Oobabooga auto installer script and everything just works. going to try this now! you are truly GOAT'ed
I've recently discovered your channel, and you work is overwhelming ❤
If you followed this tutorial and the script still doesn't work, make sure you navigate to C:\Users\[Your Username] before running the script. Sometimes Powershell opens in a different folder and it doesn't work
Thanks for keeping us updated with useful information 👍
HI there, thanks for the awesome efforts.
Unfortunately this or the full tutorial are not working for me. Here it reaches a place asking "Do you want to install cuDNN? (y/n) [Default: n]:"
If I click n it aborts and if I click yes it asks "Enter the cuDNN zip's path:" and I have no idea what that is..
Is Anaconda necessary to transcribe mp3 files speech to text? All mp3 speech files are stored on a local windows directory C:\Recodings . Each file needs to be transcribed separately into text. Your help would be highly appreciated
Wonderful! Thank you so much. It worked very well.
I didn't even know this existed! There are so many thing I hope you hit next. This is amazing thank you!
script doesnt function. Python not installed und whisper endet with error
Hi there, could you please advise what is the best and easiest way to transcribe mp3 files speech recordings to text with no coding experience at all. Thank you
Not working, it wants me to go to several different websites, create accounts, download stuff and install it manually
Thanks for the installation scripts.
Thanks for the Ko-Fi tip. I'm happy you're finding them useful.
It asked me if I wanted to install cuDNN. I typed n, it was unable to install whisper.
I ran the script again and typed y, it is not asking for the "cuDNN zip's path"
It installed, but I cant get it to run..gets denied, path not found for file it just wont work :/ What am I doing wrong??
how do i use the large v3 model?
How do I use Whisper after I've installed it? I mean where will it appear on my computer and how do I attach files to it so that it transcribes them? Thanks
I installed whisper but got stuck with Anaconda. It did not work like your video. So how do I fix that?
Is there a GUI / web interface for WhisperX.. ? there seems to be many of open source GUIs for Whisper, but not for WhisperX...
Looks like this one does support WhisperX, but my knowledge of python is limited and I dont know how to install it
Hi TC! I hope you're doing well. I was wondering if you could possibly create a video on how to train the Vicuna model. I'm really interested in learning more about it. Thank you so much in advance!
Unfortunetely i got some errors that Python and Whisper could not be installled. Maybe you could update this guide?
could you tell me what file path(s) all the dependence get installed to?
i would also like to know how i can manually install the right python version without the potental of messing up other similar projects like this that might rely on other versions
WARNING: The script whisper.exe is installed in which is not on PATH. warning, use --no-warn-script-location
Would it not make sense to demonstrate it after the download, to show it working?
Will it now install whisper v3?
Does this one still work? Started a Fresh vm and tried with windows update but can't get it to work yet.
i call bs, this gives error 2 sec after start of the command. :(
Posting the error leads to the comment getting removed, so forking cant even do that...
I get an error about my python version because I have python 3.11
"Python version is not between 3.8 and 3.10.
Assuming you've installed the correct version, please enter the comand you use to access Python 3.8/3.10."
Most python scripts that call for 3.8 or a close by version are broken on 3.11. Some changes cause programs to just not work on this newer version.
Just enter the following and hit enter:
python
@@TroubleChute Thanks this seems to be working.
EDIT: Didnt install everything that was needed, was able to install most stuff manually but numba doesnt work with 3.11. I uninstalled 3.11 and installed 3.10, but for some reason it needs to be called with "py" instead of python now. Looks to be working fine now.
@@TroubleChute Any chance you could make a guide on using opus-mt? I gave it a try and couldn't figure out how to use the models I wanted (chinese to english).
Do you have any good tutorials for powershell scripting, would love to learn about the scripts you are making?
This works for Large V2?
How would I speed up the transcription process?
If you have a GPU, using "--device gpu" will speed it up, but it also allows you to use larger models which are more accurate with transcription
Thank you!
Thank you very much, it works for me. I only have a problem in a previous installation whisper put the transcription in a txt. file and it does not save anything in it.
Great work. Any chance you know how to go about installing a GPU version with an Intel graphics card?
pls make a video about how to fix installation issues on your last chatgpt video. in the comment section lost of issues
Updated the script to include options for 7B and 13B options. This should fix most issues :)
What was the code you typed is this wind or Linux
Windows, through PowerShell
Does anyone know how to get whisper to accept text input?
It seems to be looking for an audio stream by default since I get an ffmpeg error when I try:
whisper --language zh --task translate .\test.txt
not longer working
Keep up the AI videos!
not work on my setup
After manually installing Python 3.10.8, the script worked
@@AntoniYogolewic Hi Antoni how did you do this?
Very Much Difficult.
Not all heros wear caps
Merci
Well it's installed....now what 😂
Great! Now do Mac.
thanos
i ai-ed voiced thankes
computer