whisper-base-int8-ct2

pip install transformers[torch]
ct2-transformers-converter --model openai/whisper-base --output_dir whisper-base-int8-ct2 --quantization int8 --copy_files preprocessor_config.json tokenizer.json

Downloads last month: 3

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jpy794/whisper-base-int8-ct2

Base model

openai/whisper-base

Finetuned

(496)

this model