search

snakers4 / silero-models

Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
Other
5.01k stars 316 forks source link

❓ Questions / Help / Support: Text enchancements fo RU lang #114

Closed konstantin-sancom closed 2 years ago

konstantin-sancom commented 2 years ago

❓ Questions and Help

Are there extra options available in torch.hub.load and in apply_te ? Where I can find full list of options and description of how they affect punctuation restoration and capitalization processes?

snakers4 commented 2 years ago

No, by design there are no custom settings and or options. If the input is longer than ~150 words, it is chunked internally. The model just works as-is, any pre- or post-processing should be done with text itself.

To think about it, I am not even sure, which options can there be?

konstantin-sancom commented 2 years ago

No, by design there are no custom settings and or options. If the input is longer than ~150 words, it is chunked internally. The model just works as-is, any pre- or post-processing should be done with text itself.

Ok. I see.

To think about it, I am not even sure, which options can there be?

Turning On/Off punctuation or capitalization for example.

But it's ok. No extra options - ok.

snakers4 commented 2 years ago

A flag for turning either one off is a nice idea, but same can be achieved with just .lower or a simple regex.