Skip to content
Local AI Wizard
Your machine
Theme

How do I transcribe audio locally with Whisper?

Which Whisper to pick, the memory OpenAI documents and the commands its card prints.

Getting started · updated

Short answer

Run OpenAI's Whisper on your own computer: it turns an audio file into text, and the recording never leaves your machine.

  • Pick: large-v3-turbo. About 6 GB of GPU memory; much faster, slightly less accurate.
  • large-v3: About 10 GB; slightly more accurate, slower.
  • Licence: Both allow commercial use.

Documented memory from OpenAI, as linked on each model page; licences from the Hub cards. Methodology

Which Whisper

Whisper is OpenAI's open speech-recognition model: it listens to an audio file and writes what was said, in the language spoken. It runs entirely on your computer, so recordings never leave it. The two current large checkpoints differ mainly in the decoder: turbo keeps large-v3's encoder and uses far fewer decoding layers, which makes it smaller and, by OpenAI's description, much faster, with a small loss of accuracy.

Whisper large-v3 and large-v3-turbo: parameters, documented GPU memory, fit on a 6 GB card, licence and commercial use.
ModelParameters (B)Documented GPU memory (GB)RTX 3050 · 6 GB VRAMLicence · commercial use
Whisper large-v31.5510Needs more memoryApache 2.0 · Allowed
Whisper large-v3-turbo0.8096FitsMIT · Allowed

Run it

The ways Whisper large-v3-turbo's card documents, exactly as printed. Not run by this site.

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

Setup stated first by the source · Transformers
pip install --upgrade pip
pip install --upgrade transformers datasets[audio] accelerate
Transformers · model card · Usage
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from datasets import load_dataset


device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

model_id = "openai/whisper-large-v3-turbo"

model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
model.to(device)

processor = AutoProcessor.from_pretrained(model_id)

pipe = pipeline(
    "automatic-speech-recognition",
    model=model,
    tokenizer=processor.tokenizer,
    feature_extractor=processor.feature_extractor,
    torch_dtype=torch_dtype,
    device=device,
)

dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
sample = dataset[0]["audio"]

result = pipe(sample)
print(result["text"])
Setup stated first by the source · Transformers
pip install --upgrade pip
pip install --upgrade transformers datasets[audio] accelerate
Transformers · model card · Usage
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor
from datasets import Audio, load_dataset


device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

model_id = "openai/whisper-large-v3-turbo"

model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True
)
model.to(device)

processor = AutoProcessor.from_pretrained(model_id)

dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
dataset = dataset.cast_column("audio", Audio(processor.feature_extractor.sampling_rate))
sample = dataset[0]["audio"]

inputs = processor(
    sample["array"],
    sampling_rate=sample["sampling_rate"],
    return_tensors="pt",
    truncation=False,
    padding="longest",
    return_attention_mask=True,
)
inputs = inputs.to(device, dtype=torch_dtype)

gen_kwargs = {
    "max_new_tokens": 448,
    "num_beams": 1,
    "condition_on_prev_tokens": False,
    "compression_ratio_threshold": 1.35,  # zlib compression ratio threshold (in token space)
    "temperature": (0.0, 0.2, 0.4, 0.6, 0.8, 1.0),
    "logprob_threshold": -1.0,
    "no_speech_threshold": 0.6,
    "return_timestamps": True,
}

pred_ids = model.generate(**inputs, **gen_kwargs)
pred_text = processor.batch_decode(pred_ids, skip_special_tokens=True, decode_with_timestamps=False)

print(pred_text)
Setup stated first by the source · Transformers
pip install --upgrade pip
pip install --upgrade transformers datasets[audio] accelerate
Transformers · model card · Chunked Long-Form
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from datasets import load_dataset


device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

model_id = "openai/whisper-large-v3-turbo"

model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True
)
model.to(device)

processor = AutoProcessor.from_pretrained(model_id)

pipe = pipeline(
    "automatic-speech-recognition",
    model=model,
    tokenizer=processor.tokenizer,
    feature_extractor=processor.feature_extractor,
    chunk_length_s=30,
    batch_size=16,  # batch size for inference - set based on your device
    torch_dtype=torch_dtype,
    device=device,
)

dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
sample = dataset[0]["audio"]

result = pipe(sample)
print(result["text"])

Limits

OpenAI's memory figures are for NVIDIA (CUDA) graphics cards. No figure is documented for a Mac, so the site does not carry one over; community ports exist, but their memory and speed are their own.

Accuracy: on the Open ASR Leaderboard's English short-form results, large-v3 has an average word error rate of 7.44% and turbo 7.83% (lower is better), so turbo gives up about 0.4 points for its smaller decoder. These are the published checkpoints on the leaderboard's own GPU over eight English test sets, not runs on your hardware, and other languages are not measured here. (Open ASR Leaderboard, results file of 2026-05-22, read Oct 20, 2026)

Side by side: Whisper large-v3 vs large-v3-turbo for transcription