For usage instructions follow openai/whisper-large-v3. Large-v3 finetune trained as a baseline with smaller checkpoints in progress. Expecting worse long form and equal short form. Benchmarks. Has occasional repetition issue compared to previous models but achieves competitive/SOTA CER across all tested sets.
whisper-large-v3 is an open-weight model for speech recognition from OpenAI, released under Apache License 2.0. It has 1.5B parameters. At 16-bit it needs about 3.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 3.7M downloads a month.
Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al. from OpenAI.
Parameters1.5B
Context—
Weights24.7 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads3.7M
Runs On
What it takes to serve whisper-large-v3 (1.5B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 3.1 GB | 3.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 1.5 GB | 1.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.8 GB | 0.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 16, 2026.
whisper-large-v3 on every accelerator the SAVRN Index prices, at every precision
SAVRN's Notes on whisper-large-v3
Whisper large-v3 is the reference open speech recognition model: 1.5B parameters, trained on more than 5 million hours of audio, transcribing and translating speech across dozens of languages. About 4.8 million downloads a month and more than 6,300 likes make it one of the most used models anywhere.
It needs about 4 GB at 16-bit, so it runs on nearly any GPU. Apache 2.0 allows commercial use. Whisper large-v3 turbo in our catalog is much faster with a small accuracy cost; choose between them on your own audio.
Model Card
By OpenAI, published under apache-2.0, revision 06f233fe06e7.
Whisper
Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many datasets and domains in a zero-shot setting.
Whisper large-v3 has the same architecture as the previous large and large-v2 models, except for the following minor differences:
- The spectrogram input uses 128 Mel frequency bins instead of 80
- A new language token for Cantonese
The Whisper large-v3 model was trained on 1 million hours of weakly labeled audio and 4 million hours of pseudo-labeled audio collected using Whisper large-v2 . The model was trained for 2.0 epochs over this mixture dataset.
Configuration
- Architecture
- WhisperForConditionalGeneration
- Layers
- 32
- Vocabulary size
- 51,866
- Stored precision
- float16
- Model type
- whisper
Identity and Version
- Repository
- openai/whisper-large-v3
- Publisher
- OpenAI
- Task
- Speech recognition
- Modality
- Audio
- Library
- transformers
- Parameters
- 1.5B parameters
- Languages
- en, zh, de, es, ru, ko, fr, ja
- Revision
- 06f233fe06e710322aca913c1bc4249a0d71fce1
- First published
- 2023-11-07
- Last updated
- 2024-08-12
Files and Weights
21 files, 24.7 GB in total. The weights are 7 files totalling 24.7 GB in bin, msgpack, safetensors.
Weights7 files · 24.7 GB
Configuration8 files · 330.8 KB
Tokenizer4 files · 4.3 MB
Documentation1 file · 21.8 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| flax_model.msgpack | Weights | 6.2 GB | e9c7b745947d |
| model.fp32-00001-of-00002.safetensors | Weights | 5.0 GB | 08e0005225b3 |
| model.fp32-00002-of-00002.safetensors | Weights | 1.2 GB | 630ca7746728 |
| model.safetensors | Weights | 3.1 GB | a8e94b85976e |
| pytorch_model.bin | Weights | 3.1 GB | 8f3dd0108a56 |
| pytorch_model.fp32-00001-of-00002.bin | Weights | 5.0 GB | fed9e023b351 |
| pytorch_model.fp32-00002-of-00002.bin | Weights | 1.2 GB | aadd3bdfecf9 |
| added_tokens.json | Configuration | 34.6 KB | — |
| config.json | Configuration | 1.3 KB | — |
| generation_config.json | Configuration | 3.9 KB | — |
| model.safetensors.index.fp32.json | Configuration | 117.9 KB | — |
| normalizer.json | Configuration | 52.7 KB | — |
| preprocessor_config.json | Configuration | 340 B | — |
| pytorch_model.bin.index.fp32.json | Configuration | 118.0 KB | — |
| special_tokens_map.json | Configuration | 2.1 KB | — |
| README.md | Documentation | 21.8 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| merges.txt | Tokenizer | 493.9 KB | — |
| tokenizer.json | Tokenizer | 2.5 MB | — |
| tokenizer_config.json | Tokenizer | 282.8 KB | — |
| vocab.json | Tokenizer | 1.0 MB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 24.7 GB
Download from OpenAI
Released by OpenAI through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:2212.04356
Evaluations
Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical.
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| ARTPARK-IISc/Vaani-Benchmark-V1.0 | Task Hindi_WERMetric Hindi_WERComparison conditions not established | 26.8 | Not named Reported by a third party |
Evaluated revision not stated | 2026-06-26 |
| hf-audio/open-asr-leaderboard | Task ami_werMetric ami_werComparison conditions not established | 15.95 | open-asr-leaderboard Reported by a third party |
Evaluated revision not stated | 2023-11-07 |
| hf-audio/open-asr-leaderboard | Task earnings22_werMetric earnings22_werComparison conditions not established | 11.29 | open-asr-leaderboard Reported by a third party |
Evaluated revision not stated | 2023-11-07 |
| hf-audio/open-asr-leaderboard | Task gigaspeech_werMetric gigaspeech_werComparison conditions not established | 10.02 | open-asr-leaderboard Reported by a third party |
Evaluated revision not stated | 2023-11-07 |
| hf-audio/open-asr-leaderboard | Task librispeech_clean_werMetric librispeech_clean_werComparison conditions not established | 2.01 | open-asr-leaderboard Reported by a third party |
Evaluated revision not stated | 2023-11-07 |
| hf-audio/open-asr-leaderboard | Task librispeech_other_werMetric librispeech_other_werComparison conditions not established | 3.91 | open-asr-leaderboard Reported by a third party |
Evaluated revision not stated | 2023-11-07 |
| hf-audio/open-asr-leaderboard | Task mean_werMetric mean_werComparison conditions not established | 7.44 | open-asr-leaderboard Reported by a third party |
Evaluated revision not stated | 2023-11-07 |
| hf-audio/open-asr-leaderboard | Task rtfxMetric rtfxComparison conditions not established | 145.51 | open-asr-leaderboard Reported by a third party |
Evaluated revision not stated | 2023-11-07 |
| hf-audio/open-asr-leaderboard | Task spgispeech_werMetric spgispeech_werComparison conditions not established | 2.94 | open-asr-leaderboard Reported by a third party |
Evaluated revision not stated | 2023-11-07 |
| hf-audio/open-asr-leaderboard | Task tedlium_werMetric tedlium_werComparison conditions not established | 3.86 | open-asr-leaderboard Reported by a third party |
Evaluated revision not stated | 2023-11-07 |
| hf-audio/open-asr-leaderboard | Task voxpopuli_werMetric voxpopuli_werComparison conditions not established | 9.54 | open-asr-leaderboard Reported by a third party |
Evaluated revision not stated | 2023-11-07 |
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 24.7 GB |
| 16-bit | 3.1 GB |
| 8-bit | 1.5 GB |
| 4-bit | 0.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Built on This Model
- Derived fromwhisper-large-v3-turbo
- Derived fromspeech-emotion-recognition-with-openai-whisper-large-v3
- Derived fromwhisper-large-v3-msp-podcast-emotion-dim
- Derived fromwhisper-large-v3-msp-podcast-emotion
- Derived fromwhisper-large-v3-basque
- Derived fromwhisper.cpp
- Derived fromELARSpeech-Whisper-Large-v3-bfn
- Derived fromELARSpeech-Whisper-Large-v3-beg
- Derived fromELARSpeech-Whisper-Large-v3-bastimentos-creole-english
- Derived fromELARSpeech-Whisper-Large-v3-bao
Compare whisper-large-v3
Questions About whisper-large-v3
How much GPU memory does whisper-large-v3 need?
About 3.7 GB at 16-bit and 0.9 GB at 4-bit: the weights (1.5B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run whisper-large-v3 on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use whisper-large-v3 commercially?
Yes. whisper-large-v3 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
This whisper model was trained 2x faster with Unsloth and Huggingface's TRL library.
An ELARSpeech automatic speech recognition model for Bunak. Input audio must be mono, sampled at 16 kHz. Whisper uses an ELARSpeech language token in the explicit decoder prompt. Use the prompt above rather than language= to reproduce the exported model's decoding behavior. The exported artifact is checked against the original ELARSpeech checkpoint on a fixed evaluation sample set. Exact-transcription verification status: PASS. This is a single-language ASR model. Accuracy can vary by recording conditions, speaker population, orthography, and domain. Resample input audio to 16 kHz mono. Please cite ELARSpeech and the base model above when using this model. See the ELARSpeech project…
An ELARSpeech automatic speech recognition model for Belait. Input audio must be mono, sampled at 16 kHz. Whisper uses an ELARSpeech language token in the explicit decoder prompt. Use the prompt above rather than language= to reproduce the exported model's decoding behavior. The exported artifact is checked against the original ELARSpeech checkpoint on a fixed evaluation sample set. Exact-transcription verification status: PASS. This is a single-language ASR model. Accuracy can vary by recording conditions, speaker population, orthography, and domain. Resample input audio to 16 kHz mono. Please cite ELARSpeech and the base model above when using this model. See the ELARSpeech project…
An ELARSpeech automatic speech recognition model for Bastimentos Creole English. Input audio must be mono, sampled at 16 kHz. Whisper uses an ELARSpeech language token in the explicit decoder prompt. Use the prompt above rather than language= to reproduce the exported model's decoding behavior. The exported artifact is checked against the original ELARSpeech checkpoint on a fixed evaluation sample set. Exact-transcription verification status: PASS. This is a single-language ASR model. Accuracy can vary by recording conditions, speaker population, orthography, and domain. Resample input audio to 16 kHz mono. Please cite ELARSpeech and the base model above when using this model. See the…