Repository Issue Activity (beta)

#1474 TypeError: __init__() should return None, not 'NoneType' in SpeechTimestampsMap under Python 3.14

#1479 Importing faster_whisper.vad (or any submodule) eagerly pulls in the full Whisper/ctranslate2/transformers stack via __init__.py

#949 Funny and revealing hallucinations

#901 faster-whisper not able to include/transcribe the disfluencies and filler words in transcription like um,ah,oh,uh

#1322 Phantom hearing is prone to occur during multilingual transcription.

#1476 multilingual=True silently returns translated text unless condition_on_previous_text=False

#1473 i have issue about pyav==11 , dont have binarywheel, and i am using vscode and conda envirment do i need to shift to linux

#717 Library libcublas.so.12 is not found

#1447 Feature request: Add SenseVoice/Paraformer as alternative ASR backend

#1293 Windows Crash on Exit (0xC0000409 in ucrtbase.dll) Post-Transcription with faster-whisper 1.1.1

#1469 On Home Assistant greeen unusable

#1463 Error on using converted model

#384 Streaming support

#1450 Feature request: Add FunASR/Paraformer as alternative ASR backend

#1449 Discussion: Non-autoregressive ASR models (SenseVoice) as alternative backend

#1448 Discussion: FunASR/SenseVoice as alternative non-autoregressive ASR

#1342 Divide by zero crash on Windows for specific audio files when word level timestamps are enabled with faster-whisper-large-v2 model

#1456 Leaked semaphore warning on shutdown when using WhisperModel

#1320 Unable to install Faster Whisper

#1454 Companion code + book chapter for whisper users (Building Speech AI)

#1260 It does not work normally on the RTX 5070 TI.

#1451 decode_audio crashes with "Frame does not match AudioFifo parameters" on files whose sample rate/format changes mid-stream

#1420 Need expert help fine-tuning Whisper for Heimish Yiddish (production ASR)

#1445 Batch inference from a diverse list of audio sources for better GPU utilization

#1370 Does faster whisper support AMD GPU?