Any idea how to deal with this? OSError: [Errno -9996] Invalid input device (no default output device)
@tinafernandez413817 годин тому
"Promosm"
@abhishekhgupta630221 годину тому
I love you mam
@naveenalla3000День тому
wonderful project
@fiorellademedina8419День тому
hello, how you can know the version of llama 3 with ollama? Is it 8B or 70B.?
@AssemblyAIДень тому
The default 'llama3' model is 8B with ollama. If you want to call the 70B model you need to specifiy 'llama3:70b'. Check our their naming conventions here: github.com/ollama/ollama/blob/main/docs/api.md#conventions
@theghostycedДень тому
how would you handle interruptions while the ai is talking?
@user-mg7qw3zr1p2 дні тому
how learining the english
@AssemblyAI2 дні тому
🚀MEGA UPDATE 🚀 We've launched Universal-1, our most powerful and accurate multilingual speech-to-text model to date-trained on 12.5M hours of multilingual audio data. www.assemblyai.com/blog/announcing-universal-1-speech-recognition-model/?
@sanjaykrish871923 години тому
is it free 😜😜
@ilikegeorgiabutiveonlybeen67052 дні тому
good video
@ilikegeorgiabutiveonlybeen67052 дні тому
yeah nitty gritty indexing options overview and use cases for said options would be higlhy appreciated
@cheybrown20762 дні тому
Amazing video 🎉. Was portaudio the library used to listen and capture the audio?
@martinnoah97162 дні тому
Is there a benefit to using AssemblyAI to do audio transcriptions over native Zoom transcriptions?
@AssemblyAI2 дні тому
Hey there! The short answer is that the transcriptions will likely be more accurate - we've just released our Universal-1 model that attains top-level performance on application-relevant audio domains. You can learn more here: www.assemblyai.com/blog/announcing-universal-1-speech-recognition-model/ Beyond just this, using AssemblyAI also allows you to perform other operations on your meetings like summarization, PII redaction, or prompting via LLMs!
@user-ut7pc2di4c2 дні тому
Chat GTP
@thebackpainmiracle2 дні тому
Exactly what I was intending on making. Thanks!
@PalashDandge3 дні тому
i am getting error "Cannot find reference 'generate' in '__init__.py' " on from elevenlabs import generate, stream line can you please help me to resolve this issue
@user-po9ru7dl9j16 годин тому
yes same error, did you find a solution to it mate?
@ojasvisingh7863 дні тому
👏👏
@marketfinds3 дні тому
Sorry, newbie, what is the 'source' command you use at the start? You also jumped from step 1 to 6. ie when I run: The term 'ollama' is not recognized as the name of a cmdlet Thanks
@AssemblyAI2 дні тому
The 'source' command is used when activating the python virtual environment. As for ollama you might not have installed it. So run 'pip install ollama' before using it. And additionally, you need to download it here: ollama.com
@gileneusz3 дні тому
I'm not sure if talking to animals is a good idea....
@wesleydunn1693 дні тому
Genius!
@Pixelatedcharts3 дні тому
Can we use this api free for Life time ?
@Roopkishore7263 дні тому
some problems to make android application. Please make a video to make application for convert audio file to text in android studio when button click and text show in textview.
@cheybrown20762 дні тому
Source is used when activating virtual environment on Linux system. Ollama not being recognised is probably because you haven’t installed it or you have but aren’t in the environment where you’ve installed it
@cheybrown20762 дні тому
Ah I replied to the wrong comment lol. My bad. This was meant for a different comment
@atenohin3 дні тому
But why are we using numpy here it's supposed to be from scratch
@ahmadebrahem46114 дні тому
Thanks a lot I needed this clarification for my presentation
@ScottzPlaylists4 дні тому
What is the Best Open Source equivalent all these features❓
@kunalkhurana78224 дні тому
you are awesome! it's just that you use basically a lot. maybe 245 times in a 30 minutes video!
@kajalsharma094 дні тому
Hello, anyone please help me i am getting error again and again
@umeshkumarasamy66085 днів тому
also now the model count has gone to 650,000 and it has been two years since this video. AI boom ain't no joke.
@umeshkumarasamy66085 днів тому
Good sir, You have genuinely solved the question that was bugging me for the past two months. I have had no trouble training models using the Huggingface Trainer API but never knew what to do afterwards and the course is extremely ambiguous about this. I am not a very good student generally. You have saved me
@harisshakeel1715 днів тому
Can I get this code file?
@mbmathematicsacademic70385 днів тому
short and simple ,no complications
@mychromebook99355 днів тому
i'm really diggin' this calm-laid-back euro lady
@Roopkishore7265 днів тому
some problems to make android application. Please make a video to make application for convert audio file to text in android studio when button click and text show in textview.
@jeanneleung79535 днів тому
First.
@pseudonymous87026 днів тому
doesn't work. it doesn't include a reply from the assistant
@joe_cock6 днів тому
thank you!
@vidivy6 днів тому
This was awesome - clear, concise and relatable. Thanks
@thenerdyguy10886 днів тому
Pyttsx3 does the same thing
@Naveenbabuborugadda7 днів тому
ModuleNotFoundError
@TheRyanSmee7 днів тому
Hi, thanks for this video. Very interesting. Are there any good Python libraries for playing back multiple audio files at once. I am working on a project for my daughter where I have a load of multitrack stem files - I want to give her a simple ui to play back the files and mute channels as she goes.
@Introdigitalarts7 днів тому
does anyone have a clue how to fix this error : cannot import name ‘OpenAI’ from ‘openai’
@zimissscameras7 днів тому
can you create longer videos with this ?
@vincent_hall7 днів тому
Great stuff, thank you.
@vincent_hall7 днів тому
4th of May 2024 Models 636,695 so 18.2 times as many now!
@rara-avis-technology7 днів тому
Thanks for the informative video.
@cosorxndrw7 днів тому
Worst thing about this short is that you skipped a few steps...
@abeersalam16237 днів тому
We need lessons for nlp
@rafaelkobayashi-do4ms8 днів тому
it is not free haha
@memzo74908 днів тому
thanks to make it easier
@aleemuddinkhan18139 днів тому
Please guide how we we can generate chapters from video content....?
@MisusNuzo9 днів тому
OMGGGGGGGGGGGGGGGGGGGG, Muchas gracias!!!! Esto era lo que estaba esperando.