# Speech to Text in Python without PyTorch: Whisper in 27 MB

> Transcribe audio from Python with OpenAI's Whisper, running locally, without installing PyTorch or openai-whisper. The same transcript, 27 MB installed instead of 2.2 GB, no ffmpeg, and loaded in 0.4 seconds instead of 2.

Source: https://kjarni.ai/blog/speech-to-text-python/ (published 2026-11-19)

```python
from kjarni import Transcriber

transcriber = Transcriber("whisper-small", language="en")
print(transcriber.transcribe_file("jfk.wav").text)
```

```
 And so my fellow Americans, ask not what your country can do for you, ask what you can do for your country.
```

That is OpenAI's Whisper, running on your own machine, from a package with no
dependencies. `pip install openai-whisper` gives the same sentence, after installing
PyTorch, Triton, Numba and LLVM: 2.2 GB in 25 packages, and only once ffmpeg is on the
system as well.

## Try it

You need Python 3.9 or newer, on Linux, macOS or Windows.

```bash
mkdir transcribe && cd transcribe
python3 -m venv .venv && source .venv/bin/activate
pip install kjarni
curl -LO https://github.com/ggml-org/whisper.cpp/raw/master/samples/jfk.wav
```

The sample is the 11-second public domain Kennedy clip that whisper.cpp ships for the
same purpose. Save this as `transcribe.py`:

```python
from kjarni import Transcriber

transcriber = Transcriber("whisper-small", language="en")
result = transcriber.transcribe_file("jfk.wav")

print(result.text.strip())
for seg in result.segments:
    print(f"[{seg.start:5.2f} -> {seg.end:5.2f}] {seg.text.strip()}")
print(f"language {result.language}, {result.duration_secs:.1f} s of audio")
```

```bash
python transcribe.py
```

```
And so my fellow Americans, ask not what your country can do for you, ask what you can do for your country.
[ 0.00 -> 11.00] And so my fellow Americans, ask not what your country can do for you, ask what you can do for your country.
language en, 11.0 s of audio
```

The first run downloads whisper-small from Hugging Face (920 MB) and caches it, with a
progress bar; `quiet=True` hides it. After that it needs no network.

## MP3, FLAC and Ogg, with no ffmpeg

openai-whisper hands every file to ffmpeg to decode. Kjarni decodes WAV, MP3, FLAC and
Ogg Vorbis itself, so there is nothing else to install:

```python
transcriber.transcribe_file("interview.mp3")
transcriber.transcribe_file("lecture.flac")
transcriber.transcribe_file("voice-note.ogg")
```

M4A and video are not read directly. Convert them first:

```bash
ffmpeg -i meeting.m4a meeting.wav
```

## Audio you already have in memory

From a microphone, a web upload or a NumPy array, pass the samples and their rate. Mono
floats in -1..1, at any sample rate; Kjarni resamples to Whisper's 16 kHz:

```python
import soundfile as sf
from kjarni import Transcriber

samples, rate = sf.read("jfk.wav", dtype="float32")
transcriber = Transcriber("whisper-small", language="en", quiet=True)
print(transcriber.transcribe(samples, rate).text)
```

A float32 array is passed to the native library without being copied. A plain list
works too. Kjarni does not depend on NumPy; `soundfile` here is only for reading the file.

## Other languages, and translation

Leave out `language` and Whisper decides from the first 30 seconds, as openai-whisper
does:

```python
transcriber = Transcriber("whisper-small")
result = transcriber.transcribe_file("jfk.wav")
print(result.language)   # en
```

`translate=True` transcribes speech in any of Whisper's languages into English text.
For better accuracy than whisper-small on difficult audio, use
`Transcriber("whisper-large-v3")`, a 3 GB download that is several times slower.

## Against openai-whisper

The same script with openai-whisper, for comparison:

```python
import whisper

model = whisper.load_model("small", device="cpu")
print(model.transcribe("jfk.wav", language="en", fp16=False)["text"])
```

It prints the same sentence. Measured in fresh virtual environments on Python 3.13,
Linux x86-64, an Intel Core i7-13700, with PyTorch from its CPU-only index:

| | kjarni 0.7.0 | openai-whisper + torch 2.15 (CPU) |
|---|---|---|
| Installed | 27 MB, 1 package | 2.2 GB, 25 packages |
| Needs ffmpeg | no | yes |
| Load whisper-small | 0.44 s | 2.0 s |
| Transcribe 58 s of speech | 5.4 s (10.7× real time) | 6.5 s (8.9× real time) |

The default `pip install openai-whisper` on Linux brings the CUDA build of PyTorch,
which is larger again. faster-whisper is the other common choice: in the same benchmark
it took 7.6 s at full precision and 3.6 s with its int8 model, the fastest of the four.
Kjarni runs Whisper at full precision.

## What it does not do

- No word-level timestamps: segments only, as above.
- No speaker diarization.
- No live transcription from a microphone stream. Record a chunk, then transcribe it.

## FAQ

### Can I use OpenAI Whisper in Python without PyTorch?

Yes. `pip install kjarni` and `Transcriber("whisper-small").transcribe_file("audio.wav")`
run OpenAI's Whisper weights from a native library, with no PyTorch, no openai-whisper
and no ffmpeg. The model downloads once and then works offline.

### Does it need ffmpeg?

No. WAV, MP3, FLAC and Ogg Vorbis are decoded by Kjarni itself. Other formats, such as
M4A, need converting to one of those first.

### Is it as accurate as openai-whisper?

It runs the same Whisper weights at full precision and gives the same transcript on the
examples here. Accuracy depends on the model size you choose: whisper-small by default,
whisper-large-v3 for harder audio.

### Does it need a GPU?

No. It runs on the CPU. `Transcriber("whisper-small", device="gpu")` uses a GPU through
Vulkan, Metal or DirectX 12 when one is present.

## Getting it

```
Install: pip install kjarni
PyPI:    https://pypi.org/project/kjarni/
GitHub:  https://github.com/olafurjohannsson/kjarni
Docs:    https://kjarni.ai/docs/
```

## Related

- [Transcribe Audio from the Command Line](/blog/transcribe-audio-command-line/): the same model from one binary, no Python
- [Speech to Text in C#](/blog/speech-to-text-csharp/): Whisper inside a .NET process
- [Sentence Embeddings in Python without PyTorch](/blog/sentence-transformers-without-pytorch/): all-MiniLM-L6-v2 in 23 MB
