Store › model › Speech

whisper.cpp

Name: whisper.cpp
Author: ggerganov

by ggerganov · source Hugging Face · updated 2024-10-29

mit78 MB~1 GB RAMsource aliveunlabeled

OpenAI's Whisper models converted to ggml format for use with whisper.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:ggerganov/whisper.cpp and its progress lives in the Resource Center.

Source and license

Source: https://huggingface.co/ggerganov/whisper.cpp
License: mit
Requirements: about 1 GB of RAM, 78 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with whisper.cpp.
Tags: automatic-speech-recognition

Numbers

0 downloads on Hugging Face
1,623 likes
license mit
0.1 GB for ggml-base-q8_0.bin
15,195 npm downloads a week for nodejs-whisper
latest nodejs-whisper@0.3.1

Numbers as of 2026-10-02 21:01 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
`ggml-base-q5_1.bin`	Q5_1	57 MB
`ggml-base-q8_0.bin`	Q8_0	78 MB
`ggml-base.bin`		141 MB
`ggml-base.en-q5_1.bin`	Q5_1	57 MB
`ggml-base.en-q8_0.bin`	Q8_0	78 MB
`ggml-base.en.bin`		141 MB
`ggml-large-v1.bin`		2.9 GB
`ggml-large-v2-q5_0.bin`	Q5_0	1.0 GB
`ggml-large-v2-q8_0.bin`	Q8_0	1.5 GB
`ggml-large-v2.bin`		2.9 GB
`ggml-large-v3-q5_0.bin`	Q5_0	1.0 GB
`ggml-large-v3-turbo-q5_0.bin`	Q5_0	547 MB
`ggml-large-v3-turbo-q8_0.bin`	Q8_0	834 MB
`ggml-large-v3-turbo.bin`		1.5 GB
`ggml-large-v3.bin`		2.9 GB
`ggml-medium-q5_0.bin`	Q5_0	514 MB
`ggml-medium-q8_0.bin`	Q8_0	785 MB
`ggml-medium.bin`		1.4 GB
`ggml-medium.en-q5_0.bin`	Q5_0	514 MB
`ggml-medium.en-q8_0.bin`	Q8_0	785 MB
`ggml-medium.en.bin`		1.4 GB
`ggml-small-q5_1.bin`	Q5_1	181 MB
`ggml-small-q8_0.bin`	Q8_0	252 MB
`ggml-small.bin`		465 MB
`ggml-small.en-q5_1.bin`	Q5_1	181 MB
`ggml-small.en-q8_0.bin`	Q8_0	252 MB
`ggml-small.en.bin`		465 MB
`ggml-tiny-q5_1.bin`	Q5_1	31 MB
`ggml-tiny-q8_0.bin`	Q8_0	42 MB
`ggml-tiny.bin`		74 MB
`ggml-tiny.en-q5_1.bin`	Q5_1	31 MB
`ggml-tiny.en-q8_0.bin`	Q8_0	42 MB
`ggml-tiny.en.bin`		74 MB

From the source README

OpenAI's Whisper models converted to ggml format for use with whisper.cpp

Available models

| Model | Disk | SHA |
| ------------------- | ------- | ------------------------------------------ |
| tiny | 75 MiB | `bd577a113a864445d4c299885e0cb97d4ba92b5f` |
| tiny-q5_1 | 31 MiB | `2827a03e495b1ed3048ef28a6a4620537db4ee51` |
| tiny-q8_0 | 42 MiB | `19e8118f6652a650569f5a949d962154e01571d9` |
| tiny.en | 75 MiB | `c78c86eb1a8faa21b369bcd33207cc90d64ae9df` |
| tiny.en-q5_1 | 31 MiB | `3fb92ec865cbbc769f08137f22470d6b66e071b6` |
| tiny.en-q8_0 | 42 MiB | `802d6668e7d411123e672abe4cb6c18f12306abb` |
| base | 142 MiB | `465707469ff3a37a2b9b8d8f89f2f99de7299dac` |
| base-q5_1 | 57 MiB | `a3733eda680ef76256db5fc5dd9de8629e62c5e7` |
| base-q8_0 | 78 MiB | `7bb89bb49ed6955013b166f1b6a6c04584a20fbe` |
| base.en | 142 MiB | `137c40403d78fd54d454da0f9bd998f78703390c` |
| base.en-q5_1 | 57 MiB | `d26d7ce5a1b6e57bea5d0431b9c20ae49423c94a` |
| base.en-q8_0 | 78 MiB | `bb1574182e9b924452bf0cd1510ac034d323e948` |
| small | 466 MiB | `55356645c2b361a969dfd0ef2c5a50d530afd8d5` |
| small-q5_1 | 181 MiB | `6fe57ddcfdd1c6b07cdcc73aaf620810ce5fc771` |
| small-q8_0 | 252 MiB | `bcad8a2083f4e53d648d586b7dbc0cd673d8afad` |
| small.en | 466 MiB | `db8a495a91d927739e50b3fc1cc4c6b8f6c2d022` |
| small.en-q5_1 | 181 MiB | `20f54878d608f94e4a8ee3ae56016571d47cba34` |
| small.en-q8_0 | 252 MiB | `9d75ff4ccfa0a8217870d7405cf8cef0a5579852` |
| small.en-tdrz | 465 MiB | `b6c6e7e89af1a35c08e6de56b66ca6a02a2fdfa1` |
| medium | 1.5 GiB | `fd9727b6e1217c2f614f9b698455c4ffd82463b4` |
| medium-q…

Source: https://huggingface.co/ggerganov/whisper.cpp

Card id model:hf:ggerganov/whisper.cpp · collected 2026-10-02 21:01 UTC · JSON