This is just an 8bit gguf quant of https://huggingface.co/distil-whisper/distil-large-v3.5
Works really well with very high accuracy on older 2gb laptop gpus or raspberry pis.
oneshot download prompt:
wget https://huggingface.co/nisten/distil-large-3.5-q8/resolve/main/ggml-distil-large-q8_0.bin
./build/bin/whisper-server -m ggml-distil-large-q8_0.bin -fa -t 1
Cheers, Nisten
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for nisten/distil-large-3.5-q8
Base model
distil-whisper/distil-large-v3.5