SYSTRAN / faster-whisper

Faster Whisper transcription with CTranslate2

SYSTRAN/faster-whisper Issues

Transcribe crash jupyter notebook kernels
Updated 8 days ago6
mkl_malloc: failed to allocate memory
Closed a month ago2
no kernel image is available for execution on the device
Updated 11 days ago6
Model not producing accurate transcriptions in Python
Closed 14 days ago12
"Thanks for watching" shows up repeatedly
Closed 13 days ago6
How to use the local cached model?
Updated 13 days ago5
Does it support converting to ONNX format models？
Updated 14 days ago4
Gibberish Outputs
Updated 15 days ago3
support for running through docker
Updated 15 days ago2
Allow loading model from memory
Closed 17 days ago6
Transcription contains unicode
Updated 18 days ago
Whisper-live taking same time on CPU and GPU to transcribe an audio
Updated 18 days ago5
ImportError: cannot import name 'WhisperModel' from partially initialized module 'faster_whisper' (most likely due to a circular import)
Closed 19 days ago1
The timeline is advanced by 0.5s~1s
Updated 21 days ago1
to_cpu isn't switching
Updated 22 days ago1
run error
Updated 23 days ago2
initial_prompt used to the long speech
Closed 24 days ago1
Issues with Capitalization and Punctuation in Transcribed Audios
Updated 25 days ago
Duplicate words
Updated a month ago1
Question about CUDA failed with error out of memory error
Updated a month ago2
Fail to transcribe in Chinese
Updated a month ago1
change subtitles lenght per line
Updated a month ago1
Long video processing failure without error
Updated a month ago2
transcribe can't find files outside current script working directory
Updated a month ago4
Can we modify vocabulary
Updated a month ago
How do I get both transcript and translated output from single process?
Updated a month ago4
Are timestamp tokens used in previous text?
Updated a month ago
is it possible for customize VAD model path?
Updated a month ago
RuntimeError: CUDA failed with error CUDA driver version is insufficient for CUDA runtime version
Closed a month ago2
question: client sdk
Updated a month ago1
Large-v3 model hallucinates, large-v2 doesn't
Updated a month ago8
Word-level timestamps are off by some multiplier
Updated a month ago1
CUDA 12 required?
Closed a month ago4
faster-whisper docker example?
Closed a month ago2
Problem with audio
Updated a month ago5
How to run
Updated a month ago2
2 wavs file with same content generate different result
Closed 2 months ago4
CUDA Initialisation error
Updated 2 months ago3
Best strategy for low-latency, high-throuhgput serving in Multi-GPU setups
Updated 2 months ago3
Word-level timestamp accuracy is lower than whisper-timestamped, is there any plan to optimize ?
Closed 2 months ago8
I can't use language='zh' when I use large-v3
Updated 2 months ago3
Speculative Decoding
Closed 2 months ago2
_Warning: Package 'faster _whisper.assets' is absent from the `packages` configuration.
Updated 2 months ago3
Module 'os' has no attribute 'add_dll_directory' in Raspberry Pi
Updated 2 months ago
Supporting Distil-Whisper
Updated 2 months ago4
Transcription Segment Length Issue in Converted Whisper Model
Updated 2 months ago3
Change Time format from seconds to hour:minutes:seconds
Updated 2 months ago1
Processing from wav vs processing from buffer
Closed 2 months ago1
Aborted (core dumped)
Updated 2 months ago
Super long video processing failure
Updated 2 months ago7