it doesn't work anymore. I got the following error: ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. llmx 0.0.15a0 requires cohere, which is not installed. llmx 0.0.15a0 requires openai, which is not installed. torchaudio 2.1.0+cu118 requires torch==2.1.0, but you have torch 2.0.1 which is incompatible. torchdata 0.7.0 requires torch==2.1.0, but you have torch 2.0.1 which is incompatible. torchtext 0.16.0 requires torch==2.1.0, but you have torch 2.0.1 which is incompatible. torchvision 0.16.0+cu118 requires torch==2.1.0, but you have torch 2.0.1 which is incompatible.
Try adding [ --use-deprecated=legacy-resolver ] at the end of your first line command. [ Eg: !pip install git+github.com/openai/whisper.git --use-deprecated=legacy-resolver ] **For the FIRST Line Only** I've UPDATED the COMMANDS in Description. HOPE IT HELPS.
For me the application runs without errors... but when I attach the file to be transcribed it doesn't load it. it spins in circles and then appears in red on the bottom bar. Has this happened to anyone else? can you help me? Thank you
Hi, I am having the same issue? Were you able to figure out how to fix this? I even used a shorter video that is only 4 minutes, but it still doesn't load it.
Sorry For late Reply... You need to make sure to Run this command before other commands... ------ !pip install git+github.com/openai/whisper.git !sudo apt update && sudo apt install ffmpeg ------ And if you don't see the files just click on the refresh button at the top.
Everytime you open google colaboratory again you need re-run the commands again. And if you don't see the files at the left side, give it a few seconds and press the restart button at the top of the box. I Hope this will help.
Hi I have this error "Skipping Nelly.mp4--model due to RuntimeError: Failed to load audio: ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers built with gcc 11 (Ubuntu 11.2.0-19ubuntu1) Nelly.mp4--model: No such file or directory." How can I solve this?
me too i need your help actually, pasting the code is not even possible i dont see paste feacture and aslo if i text thr codr they tell me that its error,,, what can i do?
If you have any other language other than english then choose the model "medium" (which refers to the multiple language medium model) & if you have english model then choose the model "medium.en" (which refers to the english medium model) .
My audio file was in German and I used the simple medium model. The text was fully extracted, but under the command box, and in the left column, no folder for text files was created. what's the reason?
Sorry for late Reply... Actually You need to wait a few seconds and then hit the reload button at the top to refresh. (As Sometimes it doesn't shows up automatically)
Hello my friend, thank you for your video, it realy helped me but i still got one probelm: it trascribed only like 30 min of an audio that has one hour and a half... Do you know what went wrong?
@@easybotyt i had tô use the small instead of médium and it fineshed the filé.. tomorow i Will try again the médium after reinitiating my lap i think it Will work Better... tks anyway
it doesn't work anymore. I got the following error:
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. llmx 0.0.15a0 requires cohere, which is not installed. llmx 0.0.15a0 requires openai, which is not installed. torchaudio 2.1.0+cu118 requires torch==2.1.0, but you have torch 2.0.1 which is incompatible. torchdata 0.7.0 requires torch==2.1.0, but you have torch 2.0.1 which is incompatible. torchtext 0.16.0 requires torch==2.1.0, but you have torch 2.0.1 which is incompatible. torchvision 0.16.0+cu118 requires torch==2.1.0, but you have torch 2.0.1 which is incompatible.
Try adding [ --use-deprecated=legacy-resolver ] at the end of your first line command.
[ Eg: !pip install git+github.com/openai/whisper.git --use-deprecated=legacy-resolver ]
**For the FIRST Line Only** I've UPDATED the COMMANDS in Description.
HOPE IT HELPS.
great video, worked like a charm!!!
Thank you so much for this video! Finally it worked.
For me the application runs without errors... but when I attach the file to be transcribed it doesn't load it. it spins in circles and then appears in red on the bottom bar. Has this happened to anyone else? can you help me? Thank you
Hi, I am having the same issue? Were you able to figure out how to fix this? I even used a shorter video that is only 4 minutes, but it still doesn't load it.
Thaink u so much sir . i am pakistani .sir i like ur confedent .sir please create more of speach translate into text . please sir
don't see the files on the left side :/
"/bin/bash: whisper: command not found"
Sorry For late Reply... You need to make sure to Run this command before other commands...
------
!pip install git+github.com/openai/whisper.git
!sudo apt update && sudo apt install ffmpeg
------
And if you don't see the files just click on the refresh button at the top.
It did not fix the issue. My file won't even load. Please help.@@easybotyt
Colab are now running as root. No `sudo` is needed when using `apt` command. Run `$whoami` to check.
Everytime you open google colaboratory again you need re-run the commands again. And if you don't see the files at the left side, give it a few seconds and press the restart button at the top of the box. I Hope this will help.
Hi I have this error "Skipping Nelly.mp4--model due to RuntimeError: Failed to load audio: ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers
built with gcc 11 (Ubuntu 11.2.0-19ubuntu1)
Nelly.mp4--model: No such file or directory." How can I solve this?
me too i need your help actually, pasting the code is not even possible i dont see paste feacture and aslo if i text thr codr they tell me that its error,,, what can i do?
is it possible to use silero VAD with this on colab?
how do you apply the language detection before the transcription?
If you have any other language other than english then choose the model "medium" (which refers to the multiple language medium model) & if you have english model then choose the model "medium.en" (which refers to the english medium model) .
My audio file was in German and I used the simple medium model. The text was fully extracted, but under the command box, and in the left column, no folder for text files was created. what's the reason?
Sorry for late Reply... Actually You need to wait a few seconds and then hit the reload button at the top to refresh. (As Sometimes it doesn't shows up automatically)
@@easybotyt thanks. I try to check again
Finally got it to work thanks to your help!!!! (One thing, when pasting the code I had to use Ctrl v or it did not paste.
Glad it helped!
after pasting '' !whisper "file name" --model mediumI ''
I keep getting this error: /bin/bash: line 1: whisper: command not found
Hello my friend, thank you for your video, it realy helped me but i still got one probelm: it trascribed only like 30 min of an audio that has one hour and a half... Do you know what went wrong?
not 100% sure! but I think google might have interrupted the process!
@@easybotyt i had tô use the small instead of médium and it fineshed the filé.. tomorow i Will try again the médium after reinitiating my lap i think it Will work Better... tks anyway
Thank you!