Comment by krackers
11 hours ago
You can run LLMs inside the shaping engine, so maybe you can use more advanced segmenting and transliteration algorithms? https://fuglede.github.io/llama.ttf/
11 hours ago
You can run LLMs inside the shaping engine, so maybe you can use more advanced segmenting and transliteration algorithms? https://fuglede.github.io/llama.ttf/
There aren't good datasets for that. Even neural TTS for Japanese struggles with it since Japanese transcriptions used to train models don't preserve pronunciations used.
(or maybe it could be theoretically done, just the mechanism to automatically classify wildly different pronunciations mapped to the same literal expressions don't yet exist)
It can depend on implied information, e.g. 方 can be hou or kata depending on if you're talking about about direction or a person. And that information can be before it, after it, on some image next to it, etc.
"Your scientists were so preoccupied with whether or not they could, that they didn't stop to think if they should."