Come one, come all! We're back with ML 4 Audio paper readings! This time we'll unravel the mysteries behind @OpenAI Whisper and what makes it so good at speech recognition and other Seq2Seq tasks! We'll be live this Thursday, 24th Nov, 18:00 CET on @huggingface discord
@reach_vb
-
Whisper Fine-tuning Sprint Guide Now Available for All
By
–
Can't wait for the Whisper fine-tuning sprint to start!? Come check out the official whisper fine-tuning guide from @sanchitgandhi99
, all you need is a colab account to get the ball rolling! https://
huggingface.co/blog/fine-tune
-whisper
… -
Fine-tune Whisper models on your GPU server
By
–
Want to fine-tune whisper models on your own GPU server? Check out our official fine-tuning scripts in transformers! https://
github.com/huggingface/tr
ansformers/blob/main/examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py
… -
Hugging Face Hub and Gradio Democratizing Machine Learning Ecosystem
By
–
Will be live in an hour to talk about @huggingface hub, Gradio and how the entire ecosystem comes together to democratise ML.
-
Fine-tuning Whisper in Google Colab Now Available
By
–
I’m sorry about that. We’ll try our level best to arrange for that this time.
Besides you should be able to fine-tune Whisper in Colabs quite comfortably now 🙂 -
Building Better ASR Models Community Event Discord
By
–
Brilliant idea. The event would be focused on building better ASR models but you can join our discord server and we have a thriving community of people experimenting and testing things out. They’ll be more than happy to help out.
-
Democratizing Speech Technology at Lightning Speed
By
–
Awww! Thanks, Merve!! Looking forward to democratising speech at lightning speed in the coming months <3
-
Hugging Face Dev Advocacy Internship Focuses on Speech AI
By
–
Update: I’ll be interning with the Dev Advocacy team at @huggingface for the next couple months. I’ll be working on Speech and adjacent use-cases P.S. That’s my team mascot