Whisper Base, GGUF (Q8_0)

A GGUF file of openai/whisper-base, served as a language pack for Voice Tide.

File Size (bytes) SHA-256
whisper-base-Q8_0.gguf 84,962,880 81c069428bc8a24551a8169cf31cf09bcfd9d4cf50389ae281323c9aa9648c81

Origin

Licence

OpenAI licenses the original model under the Apache License, Version 2.0. A copy of the licence is in LICENSE. The file here is a modified version: it was converted to the GGUF format and quantized to Q8_0.

Downloads last month
28
GGUF
Model size
72.6M params
Architecture
whisper
Hardware compatibility
Log In to add your hardware

8-bit

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

Model tree for voicetide/whisper-base-gguf

Quantized
(249)
this model