Fine tuning Whisper for Speech Transcription
➡️ Get LIFETIME access to the ADVANCED Transcription Repo: https://trelis.com/advanced-transcrip...
🗝️ Get LIFETIME access to the Trelis Multi-Repo Bundle (https://Trelis.com/multi-repo-bundle)
Access all SEVEN Trelis Github Repos (-robotics, -vision, -evals, -fine-tuning, -inference, -voice, -time-series)
Support via Github Issues & Trelis’ Private Discord
KEY TRELIS LINKS:
🛠 Tools (Fine-tuning, Vision, Audio, Inference): https://Trelis.com
💡 Done-for-you Custom Fine-tuning Services: https://trelis.com/fine-tuning-services/
🤝 Work for Trelis: https://trelis.com/jobs/
💸 Grants Program: https://trelis.com/trelis-ai-grants/
📧 Newsletter: https://trelis.substack.com
Video Resources:
Dataset: https://huggingface.co/datasets/Treli...
Slides: https://docs.google.com/presentation/...
Simple Whisper Transcription Notebook: https://colab.research.google.com/dri...
Basic fine-tuning notebook: https://colab.research.google.com/git...
PEFT Example: https://colab.research.google.com/dri...
Chapters
0:00 Fine-tuning speech-to-text models
0:17 Video Overview
1:39 How to transcribe YouTube videos with Whisper
7:39 How do transcription models work?
20:08 Fine-tuning Whisper with LoRA
43:32 Performance evaluation of fine-tuned Whisper
48:32 Final Tips