Abrar Ahmed

This is what worked for me to fix it: trainer = SFTTrainer( model = model, tokenizer = tokenizer, train_dataset = train_dataset, dataset_text_field = "text", max_seq_length = max_seq_length, data_collator = DataCollatorForSeq2Seq(tokenizer...

1. It happens about a 25% of the time, occurring inconsistently and unpredictably. I'm having trouble nailing down how to reproduce it. Which makes me wonder if it is dependent...

Thanks for your suggestion. I'm already using STTMuteFilter with the FUNCTION_CALL strategy. I suspect that there's something besides user interruptions that might be causing the issue. I will just have...

I just saw that the new v0.0.63 release mentions a fix: "Fixed an issue where LLMAssistantContextAggregator would prevent a BotStoppedSpeakingFrame from moving through the pipeline." I'm suspecting that this might...

@rahultyl I haven't upgraded yet. I'm running 0.0.61 and I tried to upgrade to 0.0.62 some time ago when it released and some of the changes were breaking other things...

@markbackman I'm noticing that you made the commit which fixes the BotStoppedSpeakingFrame issue in v0.0.63. But I see that you haven't mentioned it here, which leads me to wonder if...

@rahultyl So I still want to see what Mark says, but it looks like it's just a one line change if you want to try it out and see if...

Hi, You are correct, ulaw_8000 is popular with VoIP and telephone providers. We actually currently do support outputting to as ulaw_8000. We keep ElevenLabs output as PCM and then we...