Thanks a ton, this is a wonderfully simple tutorial. When I looked up how to use OpenAI Whisper before, the instructions usually involved setting up a docker server and/or required a very powerful GPU.
This is brilliant, thank you. Not going to lie, I didn't realise I should open the Python Notebook link and then open in Colaborate as this is a very new world to me, but once I finally figured it out and let the system do it's thing, it has been a game changer. I record audio notes on my watch (Samsung Classic Watch 6), share them to my Google Drive into the WhisperAudio folder, and your magic code does the rest. You rock!
Hey Andrew, thank you for that wonderfull piece 🙂 How to change the code to other language recognition - or is it working only defined with loading the right "model" without ".en"??
For some reason it does not work for me. the transcripts resulting from this method do not make sense at all. My guess is that the 16 Khz mono setting is too low quality.
Same here! I had a snippet from Jurassic Park as a test mp3 and its Whisper transcription output was outlandish and made no sense at all. I used Kevin Stratvert's method (ruclips.net/video/ABFqbY_rmEk/видео.htmlsi=MA9r3_xTwsjC_fhj) and it worked perfectly, but a shame because I prefer this method from Andrew with the file transfer.
Thanks for your useful tutorial. The hardware accelerator list only includes CPU, T4, TPU, A100 GPU, and V100 GPU. How can I make use of M1 Max? Thank you.
Andrew, thanks for this awesome video. I need to add time code per line to use as subtitles, how would I do that. With your instruction I was able to transcribe a video to text, all I am missing is the time code that is needed for subtitle burner App. Thanks
❤Great video! So many similar videos everywhere these days, but you were the one of the fists and easiest to follow. Thank you! I was looking for this! By the way, I'm trying to add "Summarize" function after this transcribing step. I'd appreciate it if you could give me (us viewers) some idea?💙
What a great video! Thank you for all of your hard work. I was wondering if it is possible to set up some kind of trigger, maybe a time trigger, to run this script periodically, let's say every couple of hours.
I need assistance, i followed the instructions carefully, my original audio had Arabic voice over. so i removed the hashtag from the large model and added it to the others, that's the only difference from your tutorial but for some reason the exported txt file contains random English text. how to fix please..
Hi! I must say your explanation was clear, but I did not understand the part about language. My transcriptions are in Spanish, and, in this case, Which model do I have to use? Should the code be the following: model = whisper.load _model ("medium.sp")?
Hi, thiswas super helpful. However I had a query. I followed your process to begin transcribing my interviews. These are a mix of English and Hindi. As I ran the transcription, I realised that It was taking really long. A 45 min interview took more than 90 min. is this normal or is there a way I can improve the speed
Thanks a ton, this is a wonderfully simple tutorial. When I looked up how to use OpenAI Whisper before, the instructions usually involved setting up a docker server and/or required a very powerful GPU.
This is brilliant, thank you. Not going to lie, I didn't realise I should open the Python Notebook link and then open in Colaborate as this is a very new world to me, but once I finally figured it out and let the system do it's thing, it has been a game changer. I record audio notes on my watch (Samsung Classic Watch 6), share them to my Google Drive into the WhisperAudio folder, and your magic code does the rest. You rock!
Hey andrew, is there any way to use the new Whisperai using the API key, to transcribe from my google drive?
Thank you.
Short slamming stuff. Thanks for getting straight to it with no nonsense.
Hey Andrew, thank you for that wonderfull piece 🙂
How to change the code to other language recognition - or is it working only defined with loading the right "model" without ".en"??
Thank you Andrew. I have been looking for this super simple solution
For some reason it does not work for me. the transcripts resulting from this method do not make sense at all. My guess is that the 16 Khz mono setting is too low quality.
Same here! I had a snippet from Jurassic Park as a test mp3 and its Whisper transcription output was outlandish and made no sense at all. I used Kevin Stratvert's method (ruclips.net/video/ABFqbY_rmEk/видео.htmlsi=MA9r3_xTwsjC_fhj) and it worked perfectly, but a shame because I prefer this method from Andrew with the file transfer.
I am trying to figure out how to add translation to this. Still working on it. Anyone do this yet?
Thanks for your useful tutorial. The hardware accelerator list only includes CPU, T4, TPU, A100 GPU, and V100 GPU. How can I make use of M1 Max? Thank you.
Absolutely great video! Thanks!!
Andrew, thanks for this awesome video. I need to add time code per line to use as subtitles, how would I do that. With your instruction I was able to transcribe a video to text, all I am missing is the time code that is needed for subtitle burner App. Thanks
either me with this function
Thank you, Andrew! This was very helpful! You rock!
❤Great video! So many similar videos everywhere these days, but you were the one of the fists and easiest to follow. Thank you! I was looking for this! By the way, I'm trying to add "Summarize" function after this transcribing step. I'd appreciate it if you could give me (us viewers) some idea?💙
What a great video! Thank you for all of your hard work. I was wondering if it is possible to set up some kind of trigger, maybe a time trigger, to run this script periodically, let's say every couple of hours.
Hi. I have an error in Step 2: MessageError: Error: credential propagation was unsuccessful
I need assistance, i followed the instructions carefully, my original audio had Arabic voice over. so i removed the hashtag from the large model and added it to the others, that's the only difference from your tutorial but for some reason the exported txt file contains random English text. how to fix please..
Hi!
I must say your explanation was clear, but I did not understand the part about language. My transcriptions are in Spanish, and, in this case, Which model do I have to use? Should the code be the following: model = whisper.load _model ("medium.sp")?
Awesome, awesome video. Exactly what I was looking for. Thank you!!
Thanks so much for this! Running my first file now.
Is it possible to choose a specific language?
Thank you Andrew! Very clear and works perfectly!
Thank you Andrew, a life saver!
Really cool, it is possible to add speakers identification (diarization) in this model?
This is very helpful, thank you! How can I implement the language detection to Spanish?
did you find out? i would love to know how to make it with german. I tried it with the code, but the result is.. well rubish.. ^^
I just tried with Vietnamese. Take off en when loading the model and will automatically detect. It does give transcript in same language though.
This is great! Many thanks!
is Whisper more accurate than Playground?
This is amazing!
Nice video sir! Will it work in other languages as well?
Hi, thiswas super helpful. However I had a query. I followed your process to begin transcribing my interviews. These are a mix of English and Hindi. As I ran the transcription, I realised that It was taking really long. A 45 min interview took more than 90 min. is this normal or is there a way I can improve the speed
Lifesaver, love you g
I want to translate Spanish audio file in English can you send me Code