-
hi,
the provided code was designed to extract word embedding after extraction of transcripts which is formatted in a specific way.
i changed the code to extract the word embedding from a given text …
-
Сергей, приветствую!
Не приходилось ли использовать русскую модель отличную от версии 0.6 ? Я пробовал подменить файлы модели от 0.10 (https://alphacephei.com/vosk/models/vosk-model-ru-0.10.zip) и…
-
We can fix it by returning speechService if it exists
instead of `result.error("INITIALIZE_FAIL", "SpeechService instance already exist.", null);`
-
Below is the trace and although there are no Exception I can se in the logs, the dictation is not working. The result is always "Partial Result".
17:13:48.898 Verbose Main Thread VoskNAudio+Init …
-
It would be nice to publish such packages
-
Do we have English support? Something like:
```python
model = Model(model_name="vosk-model-tts-en-0.6-multi")
```
TIA for any help!
-
1. vosk decode：
model config set：
```
--min-active=200
--max-active=7000
--beam=12.0
--lattice-beam=6.0
--acoustic-scale=1.0
--frame-subsampling-factor=3
--endpoint.silence-phones=1:2:3:4:5:6…
-
Hi,
I love Vosk, I have multiple python scripts using it and it works brilliantly!
I would like to be able to use Vosk with micropython on an eps32-wroom, is this possible?
-
There are some whisper realtime libraries out there.
Is there any possible way to make this library realtime ?
-
Hi msqr1.
I have tested simple app with mic on Android phone - it loads well and works.
On the other hand, I tried to run app on iphone (tried both Safari and Chrome) and it seems something is block…