README.md

---
license: apache-2.0
quantized_by: Pomni
language:
- en
- zh
- de
- es
- ru
- ko
- fr
- ja
- pt
- tr
- pl
- ca
- nl
- ar
- sv
- it
- id
- hi
- fi
- vi
- he
- uk
- el
- ms
- cs
- ro
- da
- hu
- ta
- 'no'
- th
- ur
- hr
- bg
- lt
- la
- mi
- ml
- cy
- sk
- te
- fa
- lv
- bn
- sr
- az
- sl
- kn
- et
- mk
- br
- eu
- is
- hy
- ne
- mn
- bs
- kk
- sq
- sw
- gl
- mr
- pa
- si
- km
- sn
- yo
- so
- af
- oc
- ka
- be
- tg
- sd
- gu
- am
- yi
- lo
- uz
- fo
- ht
- ps
- tk
- nn
- mt
- sa
- lb
- my
- bo
- tl
- mg
- as
- tt
- haw
- ln
- ha
- ba
- jw
- su
base_model:
- openai/whisper-large-v2
pipeline_tag: automatic-speech-recognition
tags:
- whisper.cpp
- ggml
- whisper
- audio
- speech
- voice
new_version: Pomni/whisper-large-v3-ggml-allquants
---
# Whisper-Large-v2 quants
This is a repository of **GGML quants for [whisper-large-v2](https://huggingface.co/openai/whisper-large-v2)**, for use with [whisper.cpp](https://github.com/ggml-org/whisper.cpp).

If you are looking for a program to run this model with, then I would recommend [EasyWhisper UI](https://github.com/mehtabmahir/easy-whisper-ui), as it is user-friendly, has a GUI, and will automate a lot of the hard stuff for you.
## List of Quants
Clicking on a link will download the corresponding quant instantly.
| Link | Quant | Size | Notes
|:-----|:-----|--------:|:------|
| [GGML](https://huggingface.co/Pomni/whisper-large-v2-ggml-allquants/resolve/main/ggml-large-v2-f32.bin) | F32 | 6.17 GB | Likely overkill. |
| [GGML](https://huggingface.co/Pomni/whisper-large-v2-ggml-allquants/resolve/main/ggml-large-v2-f16.bin) | F16 | 3.09 GB | Performs better than Q8_0 for noisy audio and music. |
| [GGML](https://huggingface.co/Pomni/whisper-large-v2-ggml-allquants/resolve/main/ggml-large-v2-q8_0.bin) | Q8_0 | 1.66 GB | Sweet spot; superficial quality loss at nearly double the speed. |
| [GGML](https://huggingface.co/Pomni/whisper-large-v2-ggml-allquants/resolve/main/ggml-large-v2-q6_k.bin) | Q6_K | 1.28 GB | |
| [GGML](https://huggingface.co/Pomni/whisper-large-v2-ggml-allquants/resolve/main/ggml-large-v2-q5_k.bin) | Q5_K | 1.08 GB | |
| [GGML](https://huggingface.co/Pomni/whisper-large-v2-ggml-allquants/resolve/main/ggml-large-v2-q5_1.bin) | Q5_1 | 1.18 GB | |
| [GGML](https://huggingface.co/Pomni/whisper-large-v2-ggml-allquants/resolve/main/ggml-large-v2-q5_0.bin) | Q5_0 | 1.08 GB | Last "good" quant; anything below loses quality rapidly. |
| [GGML](https://huggingface.co/Pomni/whisper-large-v2-ggml-allquants/resolve/main/ggml-large-v2-q4_k.bin) | Q4_K | 889 MB | *Might* not have lost too much quality, but I'm not sure. |
| [GGML](https://huggingface.co/Pomni/whisper-large-v2-ggml-allquants/resolve/main/ggml-large-v2-q4_1.bin) | Q4_1 | 985 MB | |
| [GGML](https://huggingface.co/Pomni/whisper-large-v2-ggml-allquants/resolve/main/ggml-large-v2-q4_0.bin) | Q4_0 | 889 MB | |
| [GGML](https://huggingface.co/Pomni/whisper-large-v2-ggml-allquants/resolve/main/ggml-large-v2-q3_k.bin) | Q3_K | 685 MB | |
| [GGML](https://huggingface.co/Pomni/whisper-large-v2-ggml-allquants/resolve/main/ggml-large-v2-q2_k.bin) | Q2_K | 529 MB | Completely non-sensical outputs. |

The F16 quant was taken from [ggerganov/whisper.cpp/ggml-large-v2.bin](https://huggingface.co/ggerganov/whisper.cpp/blob/main/ggml-large-v2.bin).
## Questions you may have
### Why do the "K-quants" not work for me?
My guess is that your GPU might be too old to recognize them, considering that I have gotten the same error on my GTX 1080. If you would like to run them regardless, you can try switching to CPU inference.
### Are the K-quants "S", "M", or "L"?
The quantizer I was using was not specific about this, so I do not know about this either.
### What program did you use to make these quants?
I used [whisper.cpp v1.7.6](https://github.com/ggml-org/whisper.cpp/releases/tag/v1.7.6) on Windows x64, leveraging CUDA 12.4.0. For the F32 quant, I converted the original Hugging Face (H5) format model to a GGML using the `models/convert-h5-to-ggml.py` script.
### One or multiple of the quants are not working for me.
[Open a new discussion](https://huggingface.co/Pomni/whisper-large-v2-ggml-allquants/discussions/new) in the community tab about this, and I will look into the issue.