-
The Parla-Clarin documentation specifies the use of ```next``` and ```prev``` attributes for sequences of utterances:
https://clarin-eric.github.io/parla-clarin/#sec-interruptions
```xml
I prop…
-
We should look into how we would go about making a Java program read out text given to it. People assigned to this should be ready to go by next week.
-
Al momento non abbiamo ancora orari e sale per cui potete procedere con una semplice pagina di lista con le relative pagine di dettaglio.
Gli speaker da caricare si trovano nella cartella ["website…
-
Thank you for your open-source work. I would like to ask you some questions. I tried to use diffloss for a speech generation task, adopting the next token prediction approach. This corresponds to the …
-
- [ ] Provide graphs to check resource exhaustion
- [ ] Debug why the audio fails
-
The deaf person will also try to speak sometimes. We need a model to figure out if the transcription is poor quality or not and if it is below a particular threshold we should not show it.
-
This is a task to do a spike (limited time to do research) on speech recognition and see how good it can be running on local device. It would be neat to have "Search with your voice" capability like Y…
-
hi ;
i do speech recognition in python and use vosk example with english model (vosk-model-small-fa-0.4) and work correctly , but when replace english model with persian model (vosk-model-fa-0.5) …
-
# Goal:
- We need to improve speech multiturn ability of model and teach model to say "I can't hear you" to non-speech/noise audio but still need to keep the MMLU and Audio Bench not degarde much.
# …
-
**Is your feature request related to a problem? Please describe.**
This requested feature isn't just useful as much as it is to be following the trend when it comes to prompting users.
OpenAI, Ge…