Live AMA with the Hugging Face Audio course team

Join us for a live Ask Me Anything (AMA) session with the Hugging Face Audio Course Team!

In this YouTube stream, you'll have the opportunity to interact directly with the experts behind the Hugging Face Audio Course and expand your understanding of the course materials, clear up any confusion, gain insight into audio tasks, and meet the team that brought the course to you!

Featuring:

Sanchit Gandhi, Machine Learning Research Engineer at Hugging Face
Vaibhav Srivastav, ML Developer Advocate Engineer at Hugging Face
Maria Khalusova, Documentation & Courses at Hugging Face
(to be confirmed) Matthijs Hollemans, Machine Learning Engineer at Hugging Face

So bring your questions about audio data, pre-trained models, speech recognition, audio classification, speech synthesis, the course itself, and anything else related to Audio AI.

[khalidiqbal]

Does it mean you can't change the model data if you get the script from the hugging face audio model? Are you saying there is certain limitation in already developed model?

[alvarobyrne]

could you please share the gist which "VB" talked about, about "whispering in real time" with GPU. thanks in advance

[enoccastro]

hola puedo tomar el curso sin saber mucho de ingles?, podemos aplicar alguna ia para ir escuchando traducido con alguna variacion en los tiempos, pero igual me servirira arto.
Hello, I can take the course without knowing much English, we can apply some ia to go listening translated with some variation in the times, but still it will be very useful for me.

[BumlifeBomblife]

I also want to learn how to build machine models on my own if anyone can help out with that....

[enoccastro]

hola saludos podrian, ponerle subtitulos en español a los videos, pliissss, gracias

[BumlifeBomblife]

Love the huggingface everyone so helpful to help...vegas in the building🦾🤖