makaveli
makaveli
@JonathanLehner can you share more details when do you see the segfault?and does it happen always on the latest version?
@stkr22 yes good point, we will make it optional in an upcoming release next week.
@JohnMama12 did you test the whisper-live client & server alone, without eleven labs and text gen ui? if not please do and if yes please let us know what issues...
@JohnMama12 we want to listen always if we want to transcribe everything, no? Not sure how your chatbot setup looks like but we have used it in a chatbot assistant...
@JohnMama12 If you follow [WhisperFusion]( https://github.com/collabora/WhisperFusion ) you should be able to setup WhisperLive with an LLM, we use `EOS` signal based on `VAD(Voice Activity Detection)` for turn taking in...
@stkr22 This is something we have in the pipeline. But feel free to open a PR and make a contribution. Thanks!
Hello @drajvver , thanks for using WhisperLive. The srt file is written at the end of the session. So, the transcription that is streamed is actually without timestamps i.e. whatever...
@Stinosko what OS are you on? I double checked the file format and it is `LF` indeed
@stkr22 I think its the sample rate, you mentioned that you send the audio with 44100 sample rate to the server but the server expects 16kHz of audio. So, I...
@stkr22 yes please! that would be great