Model reference · open weights
faster-whisper-large is an open-weight audio or speech model from Systran. faster-whisper-large-v3 (BF16) weighs 3.1 GB; the smallest configuration that runs it is RTX 3060 12 GB.
Summary of the Systran/faster-whisper-large-v3 model card, 2026-10-01
What it is
| Released by | Systran |
|---|---|
| Released | 2023-11-23 |
| VRAM | 3.1 GB for the weights |
What it runs on
| Card | One stream | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
This repository contains the conversion of openai/whisper-large-v3 to the CTranslate2 model format.
This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper.
from faster_whisper import WhisperModel
model = WhisperModel("large-v3")
segments, info = model.transcribe("audio.mp3")
for segment in segments:
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
The original model was converted with the following command:
ct2-transformers-converter --model openai/whisper-large-v3 --output_dir faster-whisper-large-v3 \
--copy_files tokenizer.json preprocessor_config.json --quantization float16
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.
For more information about the original model, see its model card.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
How it works