JigsawStack / insanely-fast-whisper-api

An API to transcribe audio with OpenAI's Whisper Large v3!

JigsawStack/insanely-fast-whisper-api Issues

You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Updated 6 days ago
Deploy on Huggingface Inference Endpoint?
Updated a month ago
sjc [error] Not enough space to unpack image, possibly exceeds maximum of 8GB uncompressed
Updated 2 months ago1
Send file to transcribe trough POST file instead of url?
Updated 4 hours ago2
FEAT: how can i set the model i want to use?
Updated 2 months ago
not fas fast as faster-whisper?
Updated 2 months ago2
Diarization does not work
Updated 3 months ago1
"timestamp": "word" return empty
Updated 2 months ago3
getting strange error from uvicorn app.app:app --reload
Updated 3 months ago
WARNING: The NVIDIA Driver was not detected
Closed 3 months ago2