Finetune ASR Models: CuttingEdgeAI Tutorial | Sushant Gautam

✨ Resources for Tutorial: Finetune ASR Models

By Sushant Gautam (sushant@simula.no)

CuttingEdgeAI: Talking to Machines – The Future of Speech-to-Text

🗓️ Time & Place: Nov. 29, 2024, 12:00 PM – 4:00 PM at Domus Bibliotheca
🏢 Organizer: NORA - Norwegian Artificial Intelligence Research Consortium

🎥 Video:

📄 Slides:

🌐 Useful Links

🤗 HuggingFace Speech-to-text finetuning tutorial huggingface.co/blog/fine-tune-whisper
🤗 Sanchit's Speech-to-text finetuning notebook colab.research.google.com/github/sanchit-gandhi/notebooks/blob/main/fine_tune_whisper.ipynb
🎵 Music Lab Spectrogram: musiclab.chromeexperiments.com
🤖 OpenAI Tokenizer: platform.openai.com/tokenizer
📝 View my research papers: Researchgate | Google Scholar
☁️་༘ Norwegian AI Cloud: naic.no

🔗 Connect with Me

🌐 Personal Website 💼 LinkedIn 📸 Instagram 👥 Facebook 🏢 Simula Page