Insanely Fast Whisper

An opinionated CLI to transcribe Audio files w/ Whisper on-device! Powered by 🤗 Transformers, Optimum & flash-attn

TL;DR - Transcribe 150 minutes (2.5 hours) of audio in less than 98 seconds - with OpenAI's Whisper Large v3. Blazingly fast transcription is now a reality!⚡️

Not convinced? Here are some benchmarks we ran on a Nvidia A100 - 80GB 👇

P.S. We also ran the benchmarks on a Google Colab T4 GPU instance too!

P.P.S. This project originally started as a way to showcase benchmarks for Transformers, but has since evolved into a lightweight CLI for people to use. This is purely community driven. We add whatever community seems to have a strong demand for!

🆕 Blazingly fast transcriptions via your terminal! ⚡️

We've added a CLI to enable fast transcriptions. Here's how you can use it:

Install insanely-fast-whisper with pipx (pip install pipx or brew install pipx):

pipx install insanely-fast-whisper

⚠️ If you have python 3.11.XX installed, pipx may parse the version incorrectly and install a very old version of insanely-fast-whisper without telling you (version 0.0.8, which won't work anymore with the current BetterTransformers). In that case, you can install the latest version by passing --ignore-requires-python to pip:

pipx install insanely-fast-whisper --force --pip-args="--ignore-requires-python"

If you're installing with pip, you can pass the argument directly: pip install insanely-fast-whisper --ignore-requires-python.

Run inference from any path on your computer:

insanely-fast-whisper --file-name <filename or URL>

Note: if you are running on macOS, you also need to add --device-id mps flag.

🔥 You can run Whisper-large-v3 w/ Flash Attention 2 from this CLI too:

insanely-fast-whisper --file-name <filename or URL> --flash True 

🌟 You can run distil-whisper directly from this CLI too:

insanely-fast-whisper --model-name distil-whisper/large-v2 --file-name <filename or URL> 

Don't want to install insanely-fast-whisper? Just use pipx run:

pipx run insanely-fast-whisper --file-name <filename or URL>

[!NOTE] The CLI is highly opinionated and only works on NVIDIA GPUs & Mac. Make sure to check out the defaults and the list of options you can play around with to maximise your transcription throughput. Run insanely-fast-whisper --help or pipx run insanely-fast-whisper --help to get all the CLI arguments along with their defaults.

CLI Options

The insanely-fast-whisper repo provides an all round support for running Whisper in various settings. Note that as of today 26th Nov, insanely-fast-whisper works on both CUDA and mps (mac) enabled devices.

  -h, --help            show this help message and exit
  --file-name FILE_NAME
                        Path or URL to the audio file to be transcribed.
  --device-id DEVICE_ID
                        Device ID for your GPU. Just pass the device number when using CUDA, or "mps" for Macs with Apple Silicon. (default: "0")
  --transcript-path TRANSCRIPT_PATH
                        Path to save the transcription output. (default: output.json)
  --model-name MODEL_NAME
                        Name of the pretrained model/ checkpoint to perform ASR. (default: openai/whisper-large-v3)
  --task {transcribe,translate}
                        Task to perform: transcribe or translate to another language. (default: transcribe)
  --language LANGUAGE   
                        Language of the input audio. (default: "None" (Whisper auto-detects the language))
  --batch-size BATCH_SIZE
                        Number of parallel batches you want to compute. Reduce if you face OOMs. (default: 24)
  --flash FLASH         
                        Use Flash Attention 2. Read the FAQs to see how to install FA2 correctly. (default: False)
  --timestamp {chunk,word}
                        Whisper supports both chunked as well as word level timestamps. (default: chunk)
  --hf-token HF_TOKEN
                        Provide a hf.co/settings/token for Pyannote.audio to diarise the audio clips
  --diarization_model DIARIZATION_MODEL
                        Name of the pretrained model/ checkpoint to perform diarization. (default: pyannote/speaker-diarization)
  --num-speakers NUM_SPEAKERS
                        Specifies the exact number of speakers present in the audio file. Useful when the exact number of participants in the conversation is known. Must be at least 1. Cannot be used together with --min-speakers or --max-speakers. (default: None)
  --min-speakers MIN_SPEAKERS
                        Sets the minimum number of speakers that the system should consider during diarization. Must be at least 1. Cannot be used together with --num-speakers. Must be less than or equal to --max-speakers if both are specified. (default: None)
  --max-speakers MAX_SPEAKERS
                        Defines the maximum number of speakers that the system should consider in diarization. Must be at least 1. Cannot be used together with --num-speakers. Must be greater than or equal to --min-speakers if both are specified. (default: None)

Frequently Asked Questions

How to correctly install flash-attn to make it work with insanely-fast-whisper?

Make sure to install it via pipx runpip insanely-fast-whisper install flash-attn --no-build-isolation. Massive kudos to @li-yifei for helping with this.

How to solve an AssertionError: Torch not compiled with CUDA enabled error on Windows?

The root cause of this problem is still unknown, however, you can resolve this by manually installing torch in the virtualenv like python -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121. Thanks to @pto2k for all tdebugging this.

How to avoid Out-Of-Memory (OOM) exceptions on Mac?

The mps backend isn't as optimised as CUDA, hence is way more memory hungry. Typically you can run with --batch-size 4 without any issues (should use roughly 12GB GPU VRAM). Don't forget to set --device-id mps.

How to use Whisper without a CLI?

pip install --upgrade transformers optimum accelerate

import torch
from transformers import pipeline
from transformers.utils import is_flash_attn_2_available

pipe = pipeline(
    "automatic-speech-recognition",
    model="openai/whisper-large-v3", # select checkpoint from https://huggingface.co/openai/whisper-large-v3#model-details
    torch_dtype=torch.float16,
    device="cuda:0", # or mps for Mac devices
    model_kwargs={"attn_implementation": "flash_attention_2"} if is_flash_attn_2_available() else {"attn_implementation": "sdpa"},
)

outputs = pipe(
    "<FILE_NAME>",
    chunk_length_s=30,
    batch_size=24,
    return_timestamps=True,
)

outputs

Acknowledgements

1. OpenAI Whisper team for open sourcing such a brilliant check point.
2. Hugging Face Transformers team, specifically Arthur, Patrick, Sanchit & Yoach (alphabetical order) for continuing to maintain Whisper in Transformers.
3. Hugging Face Optimum team for making the BetterTransformer API so easily accessible.
4. Patrick Arminio for helping me tremendously to put together this CLI.

Community showcase

1. @ochen1 created a brilliant MVP for a CLI here: https://github.com/ochen1/insanely-fast-whisper-cli (Try it out now!)
2. @arihanv created an app (Shush) using NextJS (Frontend) & Modal (Backend): https://github.com/arihanv/Shush (Check it outtt!)
3. @kadirnar created a python package on top of the transformers with optimisations: https://github.com/kadirnar/whisper-plus (Go go go!!!)