🔄 In a Training Loop
Kavya Manohar
AI & ML interests
Speech Recognition, Low Resource Languages, Malayalam
Recent Activity
posted an update 3 days ago
Some bugs teach you more than they cost you. It's a small bug with a big lesson I keep running into: speech tools are built and benchmarked on English, so their limits are quietly calibrated for English. You only find the edges when you work in the languages they weren't tested on.
Learnt things the hard way, wrote it down so you don't have to.
https://huggingface.co/blog/adalat-ai/whisper-token-limit published an article 6 days ago
Why Whisper cuts off Indic transcripts after six seconds new activity 8 days ago
adalat-ai/malayalam-dictation:model release?