We are working on this - we don't have quite enough Irish speech data.
Part of this is the "dark L" sound
12 layers of 768-dim each. The 3 dimensions visualized are chosen by UMAP.
Not sure, could be the large number of Spanish dialects represented in the dataset, label noise, or something else. There may just be too much diversity in the class to fit neatly in a cluster. Also, the training…
We didn't explicitly. Because we finetuned this model for accent classification, the later transformer layers appear to ignore non-accent vocal characteristics. I verified this for gender for example.
People have all sorts of motivations for learning languages and accents. Right now, I'm using this tech to work on my accent in Spanish. Honestly I would rather mumble almost unintelligibly with an decent Mexican accent…
We are working on this - we don't have quite enough Irish speech data.
Part of this is the "dark L" sound
12 layers of 768-dim each. The 3 dimensions visualized are chosen by UMAP.
Not sure, could be the large number of Spanish dialects represented in the dataset, label noise, or something else. There may just be too much diversity in the class to fit neatly in a cluster. Also, the training…
We didn't explicitly. Because we finetuned this model for accent classification, the later transformer layers appear to ignore non-accent vocal characteristics. I verified this for gender for example.
People have all sorts of motivations for learning languages and accents. Right now, I'm using this tech to work on my accent in Spanish. Honestly I would rather mumble almost unintelligibly with an decent Mexican accent…