faster-whisper
faster-whisper copied to clipboard
SYSTRAN
Faster Whisper transcription with CTranslate2
I'm working mostly with very small files like 2-6s and what I noticed many times in Whisper is that transcription time is not linear. What I mean is that 3s...
version:1.0.1 system: win10 py310 cuda12 config: whisper-ctranslate2 --model medium --output_format srt --local_files_only True --word_timestamps True --language ko --vad_filter false Almost every sentence will be displayed 0.5s~1s earlier
I would like to use the microphone from webbrowser and send the audio chunks in realtime to a python backend. The data sent (float32arrays) are sent, but seem to be...
https://github.com/SYSTRAN/faster-whisper/blob/91c8307aa6b305dcaf12fc112b0187ee0d512b00/faster_whisper/transcribe.py#L799 I don't have CUDA, and when this line was encountered, to_cpu stays False
I use C#， Does it support converting to ONNX format models？ Or how to use C # to call this model？
An error occured while synchronizing the model Systran/faster-whisper-large-v3 from the Hugging Face Hub: An error happened while trying to locate the files on the Hub and we cannot find the...
Hi Is there support for real-time audio transcription using streaming? Thx
[ctranslate2] [thread 10436] [warning] The compute type inferred from the saved model is float16, but the target device or backend do not support efficient float16 computation. The model weights have...
After transcribing several audio files using medium model, I have noticed that the transcriptions lack capitalization and punctuation. For example: Transcribed text with punctuation and capitalization: "Produces, for example, a...
I am using whisper-live==0.2.1 , faster-whisper==0.10.0 and Ctranslate2==4.0.0 Transcribing a 30-second audio file currently requires the same amount of time whether processed on a CPU or GPU, approximately 2 minutes....
