chatterbox icon indicating copy to clipboard operation
chatterbox copied to clipboard

Wrong numbers pronouncation in Russian language

Open kaihatsu-dg opened this issue 3 months ago • 1 comments

If text prompt contains numbers or dates written as digits (1, 1900), they are not prounounced in Russian, even though the language is specified. Example: text: 25470 language_id = "ru" Reference voice is Russian Below are the examples of chatterbox generated audio and google generated audio with correct pronouncation.

Chatterbox Audio

Google Audio(Correct)

kaihatsu-dg avatar Sep 14 '25 08:09 kaihatsu-dg

The speech synthesis task does not guarantee the conversion of numbers and abbreviations into correct Russian. Raw text cannot be fed to the generator without pre-processing, and in this case, Russian normalization is required. For Example https://github.com/saarus72/text_normalization

MixxxGit avatar Sep 25 '25 17:09 MixxxGit