Repository Issue Activity (beta)

#182 Feature request: Add SenseVoice/Paraformer as alternative non-autoregressive backends

#186 Feature: Add SenseVoice as non-autoregressive alternative — lower latency for streaming

#185 Feature request: Add SenseVoice/Paraformer as alternative ASR backend

#184 Feature request: Add FunASR/SenseVoice as alternative streaming backend

#183 Feature: Add SenseVoice as alternative ASR for lower-latency streaming

#172 SimulStreaming and MT Marathon in August

#84 Can't run from windows the command of recording from mic

#179 Why does the system still pick up content when I'm not talking?

#175 Segment / chunking errors

#178 server\agent_pool_manager.py

#176 What user-facing implementations are available for this project?

#177 REP-4325-4326

#174 Can I use CPU to run it?

#173 VAD end issue

#133 High latency and low accuracy with "huggingface finetuned model converted to faster whisper format"

#171 **Fixing Vite dependency optimization warnings**

#170 copilotkit-runtime-handler as of 06292025 12:01PM

#169 Indic language accuracy is low in streaming mode

#167 VAD Speech Start Question

#166 问题

#159 Ignoring the vac_chunk_size using VAC

#164 [json.exception.type_error.305] cannot use operator[] with a string argument with null

#119 Could not load library libcudnn_ops_infer.so.8.

#161 faster-whisper repetition penalty ( Was: One part of the transcription is corrupted, causing everything behind it to be incorrect. )

#163 RuntimeError: CUDA failed with error system has unsupported display driver / cuda driver combination