(Day 211) 2 hour mark !!! Glaswegian dataset goal - accomplished! + whisper-small fine-tuned

Ivan Ivanov · July 30, 2024

Hello :) Today is Day 211!

A quick summary of today:

  • fine-tuning the final whisper-small model for Glaswegian automatic speech recognition (ASR)

After yesterday, it the audio was 118 and I was not happy that we did not officially hit the 2 hour mark, so today I went on youtube and got a 3min clip from Limmy which I transcribed and added to our dataset. Here is a link to the final 2 hour Glaswegian dataset on HuggingFace.

After a few months of working on this side project we hit the set goal!~

After I got the dataset I started fine-tuning whisper-small. It took around 4 hours ~ and the fine-tuned model is ready and deployed for using on HuggingFace Spaces.

image

Looking at the metrics, training could be improved.

image

As for what is next - training a Text-To-Speech model using our final dataset. This was the hard part before because the voice at the end was, while understandable, a bit robotic. So this is the next step and hopefully we get better results now.

That is all for today!

See you tomorrow :)