Store › model › Speech

whisper-large-v3-gguf

Name: whisper-large-v3-gguf
Author: handy-computer

by handy-computer · source Hugging Face · updated 2026-09-15

apache-2.0951 MB~2 GB RAMsource aliveunlabeled

GGUF conversions of openai/whisper-large-v3 for use with transcribe.cpp.

Add to LogiShell Open in the web IDE

The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:handy-computer/whisper-large-v3-gguf and its progress lives in the Resource Center.

Source and license

Source: https://huggingface.co/handy-computer/whisper-large-v3-gguf
License: apache-2.0
Requirements: about 2 GB of RAM, 951 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with whisper.cpp.
Tags: transcribe.cpp gguf asr speech-to-text whisper openai automatic-speech-recognition af am ar as az ba be bg bn

Numbers

312,631 downloads on Hugging Face
2 likes
license apache-2.0
0.9 GB for whisper-large-v3-Q4_K_M.gguf
15,195 npm downloads a week for nodejs-whisper
latest nodejs-whisper@0.3.1

Numbers as of 2026-10-02 20:59 UTC, from the source API.

Summary

Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.

Reviews

No reviews yet. Reviews are written inside LogiShell: open this card in the app.

Files

file	quant	size
`whisper-large-v3-F16.gguf`	F16	2.9 GB
`whisper-large-v3-Q4_K_M.gguf`	Q4_K_M	951 MB
`whisper-large-v3-Q5_K_M.gguf`	Q5_K_M	1.1 GB
`whisper-large-v3-Q6_K.gguf`	Q6_K	1.2 GB
`whisper-large-v3-Q8_0.gguf`	Q8_0	1.6 GB

From the source README

whisper-large-v3: transcribe.cpp GGUF

GGUF conversions of openai/whisper-large-v3 for use
with transcribe.cpp.

Ported from upstream commit
06f233f,
pinned 2026-04-25.
Validated against the transformers reference at transcribe.cpp commit
5.6.1
on 2026-04-26.

OpenAI Whisper large-v3 — converted to GGUF for transcribe.cpp. Multilingual transcription, language detection, and speech translation (audio in any supported language → English text). v3 family adds Cantonese (yue) and uses a 128-bin mel input. Encoder-decoder transformer; 30-second windows with chunked long-form decoding.

Downloads

| Quantization | Download | Size | WER (LibriSpeech test-clean) |
| --- | --- | ---: | ---: |
| F16 | whisper-large-v3-F16.gguf | 3.11 GB | 1.81% |
| Q8_0 | whisper-large-v3-Q8_0.gguf | 1.67 GB | 1.82% |
| Q6_K | whisper-large-v3-Q6_K.gguf | 1.30 GB | 1.83% |
| Q5_K_M | whisper-large-v3-Q5_K_M.gguf | 1.16 GB | 1.84% |
| Q4_K_M | whisper-large-v3-Q4_K_M.gguf | 997 MB | 1.86% |

WER on the full LibriSpeech test-clean split (2,620 utterances), batch size 1, timestamps none. Figures without a commit were published before provenance was recorded.

OpenAI's self-reported number…

Source: https://huggingface.co/handy-computer/whisper-large-v3-gguf

Card id model:hf:handy-computer/whisper-large-v3-gguf · collected 2026-10-02 20:59 UTC · JSON