faster-whisper
faster-whisper copied to clipboard
SYSTRAN
Faster Whisper transcription with CTranslate2
So I have large quantity of short 10-60 seconds audio files. I try to transcribe them with faster whisper in a loop. But sometimes whisper just stops/freezes all of a...
## Issue quick look I am running a faster whisper on a Flask app to use it for real-time transcription. It is running, occupying memory, and not releasing it. Eventually,...
model.transcribe(fileName,vad_filter=True) 报错误文件不存在 [ONNXRuntimeError] : 3 : NO_SUCHFILE : Load model from C:\Users\ADMINI~1\AppData\Local\Temp\_MEI92922\faster_whisper\assets\silero_vad.onnx failed:Load model C:\Users\ADMINI~1\AppData\Local\Temp\_MEI92922\faster_whisper\assets\silero_vad.onnx failed. File doesn't exist Traceback (most recent call last): File "broadcast_record.py", line 100, in save_recording...
I've been trying to make faster-whisper run on CUDA the whole day and it just does not work. The model get initialized on CUDA with no issues, but when I...
Hi faster-whisper. Wonderful work. I'm wondering, what is the recommended (minimum) hardware for this project to run in a "reasonable" amount of time? Like what GPU. You did your benchmark...
**unsupported version**: 1. faster-whisper >= v1.0.0 2. ctranslate2==4.0.0 [From ctranslate2 official guideline that ctranslate2==4.0.0 will support cuda 11.x](https://opennmt.net/CTranslate2/installation.html#install-with-docker) But actually it's not supported it will return CUDA failed with the...
Hi everyone, I need to check detected segments empty or not. In order to achieve that I have tried this, ``` segments, info = self.whisper_model.transcribe(audio_data, **self.options.transcribe_settings) try: next(segments) except StopIteration:...
Hi, I've been trying to implement faster-whisper on my project but I came across a weird issue. For some reason, when I use the GPU, Whisper successfully transcribes the audio...
I have many files that need to be translated into text, but the task exits every time I try to process a file。 、 def video_to_text(file, model_size="large-v3"): # or run...
I want to use [cahya/whisper-large-id](https://huggingface.co/cahya/whisper-large-id) ``` ct2-transformers-converter --model "cahya/whisper-large-id" \ --output_dir "cahya-whisper-large-id-ct2" --quantization float16 ``` but changing `beam_size` has no effect, it always return 30 second segments, I want under...
