SAVRN
Search Contact SAVRN

Open-weight model

faster-whisper-large-v3-turbo

by Dropbox Inc dropbox-dash/faster-whisper-large-v3-turbo

This repository contains the conversion of openai/whisper-large-v3-turbo to the CTranslate2 model format. This model can be used in CTranslate2 or projects based on CTranslate2 models such as faster-whisper.

Parameters
Context
Weights1.6 GB
Licensemit
AccessOpen weights
Monthly Downloads1.4M

Model Card

By Dropbox Inc, published under mit, revision 0a363e9161cb.

This repository contains the conversion of openai/whisper-large-v3-turbo to the CTranslate2 model format. This model can be used in CTranslate2 or projects based on CTranslate2 models such as faster-whisper. It is called automatically for Mobius Labs fork of faster-whisper. Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the computetype option in CTranslate2. The openAI model was converted with the following command: For more information about the original model, see its model card.

Read Dropbox Inc's full model card

Whisper large-v3 turbo model for CTranslate2

This repository contains the conversion of openai/whisper-large-v3-turbo to the CTranslate2 model format.

This model can be used in CTranslate2 or projects based on CTranslate2 models such as faster-whisper. It is called automatically for Mobius Labs fork of faster-whisper.

Example

from faster_whisper import WhisperModel

model = WhisperModel("dropbox-dash/faster-whisper-large-v3-turbo")

segments, info = model.transcribe("audio.mp3")
for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the compute_type option in CTranslate2.

Conversion details

The openAI model was converted with the following command:

ct2-transformers-converter --model openai/whisper-large-v3-turbo --output_dir faster-whisper-large-v3-turbo \
    --copy_files tokenizer.json preprocessor_config.json --quantization float16

More Information

For more information about the original model, see its model card.

Identity and Version

Repository
dropbox-dash/faster-whisper-large-v3-turbo
Publisher
Dropbox Inc
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
0a363e9161cbc7ed1431c9597a8ceaf0c4f78fcf
First published
2024-10-08
Last updated
2025-11-05

Files and Weights

7 files, 1.6 GB in total. The weights are 1 file totalling 1.6 GB in bin.

Weights1 file · 1.6 GB
Configuration3 files · 1.1 MB
Tokenizer1 file · 2.7 MB
Documentation1 file · 1.4 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.binWeights1.6 GB e76620f83d5f
config.jsonConfiguration2.3 KB
preprocessor_config.jsonConfiguration340 B
vocabulary.jsonConfiguration1.1 MB
README.mdDocumentation1.4 KB
.gitattributesRepository1.5 KB
tokenizer.jsonTokenizer2.7 MB

License and Download

License
mit
Access
Open weights, no gate
Download size
1.6 GB
Download from Dropbox Inc

Released by Dropbox Inc through its official repository on Hugging Face. Read the license.

Memory Requirements

PrecisionWeights in memory
As published1.6 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About faster-whisper-large-v3-turbo

Can I use faster-whisper-large-v3-turbo commercially?

Yes. faster-whisper-large-v3-turbo is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.