Today’s focus was data preparation for Wav2Vec finetuning — making sure our audio and transcripts are clean, properly formatted, and ready for the model.

We went through:

• Discussing “what’s next” for CTC finetuning — maybe training from scratch
• Downloading datasets via Hugging Face
• Preprocessing audio and transcripts
• Structuring data for Wav2Vec (input_ids & labels)

Data prep is the foundation and today we poured a solid one.

Replay: https://youtu.be/CXYp2YoTMO4?si=xxJSNehXPy0uzqV8 Live Schedule: https://www.twitch.tv/koleshjr/schedule

📢 Subscribe: https://www.youtube.com/@koleshjr