Repository Issue Activity (beta)

#229 error: no models loaded

#307 generate_speech() silently yields zero audio for prompts producing <28 SNAC tokens (no flush of trailing buffer)

#251 The model skips random words sometimes in VLLM engine inference, while in transformers inference it does not.

#306 Is medium-3b intended to be a supported model alias?

#300 What version of python is compatiable?

#295 Feature request: Official Brazilian Portuguese voices/models

#241 emotions Is it possible to do this? Does she still support it? Custom emotions.

#305 Faster Playback

#304 Question: Is there a paper / technical report / blog etc. about the model?

#303 Speed Control, Energy Ramp-up, and Voice Gender Inconsistency when dealing

#301 vLLM Inference Produces Gibberish Outputs While Transformers Works Fine

#215 Cuda out of memory when tried finetuning , on 40gb A100 single gpu

#231 How you achieved emotion control through emotion labeling？

#283 Guidance Needed: Orpheus-TTS + TensorRT-LLM Optimization for Concurrency

#299 background noise at the start of generation

#37 Pre-train Data Structure

#228 Silence at the start of generations

#3 Unable to run the snippet or realtime-demo code

#6 Zero-Shot Voice Cloning

#298 Korean language Finetuning

#296 Inquiry on the design rationale towards synchronous single client requests

#110 Fine Tuning for Arabic

#180 Doubt in sample rate.

#10 training / finetuning other languages

#271 I have successfully fine tuned model but.........