Repository Issue Activity (beta)

#388 ASR VIDEO STUDIO

#385 TTS Remote Host Error

#321 TypeError on subsequent requests after MODEL_IDLE_TIMEOUT

#383 v1.10.0 crash loops with ASR_ENGINE=whisperx: lightning 2.6.5 and pyannote 3.x cannot load the VAD checkpoint

#360 Unable to run whisperx engine in docker

#377 Security: `encode=false` bypasses audio format validation — unrestricted compute access + resource exhaustion

#374 Feature: Add SenseVoice/Paraformer as alternative ASR backend

#373 Feature request: Add FunASR/SenseVoice as alternative ASR engine

#372 Feature: Add SenseVoice/FunASR as alternative ASR backend

#371 Feature Request: Add FunASR/SenseVoice as alternative ASR backend

#370 Feature request: Add SenseVoice/FunASR as alternative ASR backend

#311 Diarization using whisperx seems to fail to detect any more than 1 speaker

#367 No Response Body

#366 StreamingResponse media_type does not respect requested output format

#314 Initial setup - model can't be downloaded/used from Hugging Face

#365 Add batch and beam size settings for whisperx and faster-whisper

#309 Subtitle and non text output generation misformated for whisperX(did not try on other models)

#223 Exception in ASGI application

#295 WhisperX CPU only using 4 cores

#359 Add Arm support for GPU container

#358 Add support for sentiment analysis

#339 Add support for NVIDIA Parakeet models

#357 Add diarization support for openAI API based implementation

#190 Support for whisper.cpp stream capabilities for realtime transcription.

#296 Feat: Implement FastRTC for Realtime Transcription