Faster Whisper transcription with CTranslate2

faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models.

This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU.

Benchmark

For reference, here's the time and memory usage that are required to transcribe 13 minutes of audio using different implementations:

• openai/whisper@6dea21fd
• whisper.cpp@3b010f9
• faster-whisper@cce6b53e

Large-v2 model on GPU

Implementation	Precision	Beam size	Time	Max. GPU memory	Max. CPU memory
openai/whisper	fp16	5	4m30s	11325MB	9439MB
faster-whisper	fp16	5	54s	4755MB	3244MB
faster-whisper	int8	5	59s	3091MB	3117MB

Executed with CUDA 11.7.1 on a NVIDIA Tesla V100S.

Small model on CPU

Implementation	Precision	Beam size	Time	Max. memory
openai/whisper	fp32	5	10m31s	3101MB
whisper.cpp	fp32	5	17m42s	1581MB
whisper.cpp	fp16	5	12m39s	873MB
faster-whisper	fp32	5	2m44s	1675MB
faster-whisper	int8	5	2m04s	995MB

Executed with 8 threads on a Intel(R) Xeon(R) Gold 6226R.

Installation

The module can be installed from PyPI:

pip install faster-whisper

Other installation methods:

# Install the master branch:
pip install --force-reinstall "faster-whisper @ https://github.com/guillaumekln/faster-whisper/archive/refs/heads/master.tar.gz"

# Install a specific commit:
pip install --force-reinstall "faster-whisper @ https://github.com/guillaumekln/faster-whisper/archive/a4f1cc8f11433e454c3934442b5e1a4ed5e865c3.tar.gz"

GPU support

GPU execution requires the NVIDIA libraries cuBLAS 11.x and cuDNN 8.x to be installed on the system. Please refer to the CTranslate2 documentation.

Usage

from faster_whisper import WhisperModel

model_size = "large-v2"

# Run on GPU with FP16
model = WhisperModel(model_size, device="cuda", compute_type="float16")

# or run on GPU with INT8
# model = WhisperModel(model_size, device="cuda", compute_type="int8_float16")
# or run on CPU with INT8
# model = WhisperModel(model_size, device="cpu", compute_type="int8")

segments, info = model.transcribe("audio.mp3", beam_size=5)

print("Detected language '%s' with probability %f" % (info.language, info.language_probability))

for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

Warning: segments is a generator so the transcription only starts when you iterate over it. The transcription can be run to completion by gathering the segments in a list or a for loop:

segments, _ = model.transcribe("audio.mp3")
segments = list(segments)  # The transcription will actually run here.

Word-level timestamps

segments, _ = model.transcribe("audio.mp3", word_timestamps=True)

for segment in segments:
    for word in segment.words:
        print("[%.2fs -> %.2fs] %s" % (word.start, word.end, word.word))

VAD filter

The library integrates the Silero VAD model to filter out parts of the audio without speech:

segments, _ = model.transcribe("audio.mp3", vad_filter=True)

The default behavior is conservative and only removes silence longer than 2 seconds. See the available VAD parameters and default values in the source code. They can be customized with the dictionary argument vad_parameters:

segments, _ = model.transcribe(
    "audio.mp3",
    vad_filter=True,
    vad_parameters=dict(min_silence_duration_ms=500),
)

Logging

The library logging level can be configured like this:

import logging

logging.basicConfig()
logging.getLogger("faster_whisper").setLevel(logging.DEBUG)

Going further

See more model and transcription options in the WhisperModel class implementation.

Community integrations

Here is a non exhaustive list of open-source projects using faster-whisper. Feel free to add your project to the list!

• whisper-ctranslate2 is a command line client based on faster-whisper and compatible with the original client from openai/whisper.
• whisper-diarize is a speaker diarization tool that is based on faster-whisper and NVIDIA NeMo.
• whisper-standalone-win contains the portable ready to run binaries of faster-whisper for Windows.
• asr-sd-pipeline provides a scalable, modular, end to end multi-speaker speech to text solution implemented using AzureML pipelines.
• Open-Lyrics is a Python library that transcribes voice files using faster-whisper, and translates/polishes the resulting text into .lrc files in the desired language using OpenAI-GPT.

Model conversion

When loading a model from its size such as WhisperModel("large-v2"), the correspondig CTranslate2 model is automatically downloaded from the Hugging Face Hub.

We also provide a script to convert any Whisper models compatible with the Transformers library. They could be the original OpenAI models or user fine-tuned models.

For example the command below converts the original "large-v2" Whisper model and saves the weights in FP16:

pip install transformers[torch]>=4.23

ct2-transformers-converter --model openai/whisper-large-v2 --output_dir whisper-large-v2-ct2 \
    --copy_files tokenizer.json --quantization float16

• The option --model accepts a model name on the Hub or a path to a model directory.
• If the option --copy_files tokenizer.json is not used, the tokenizer configuration is automatically downloaded when the model is loaded later.

Models can also be converted from the code. See the conversion API.

Load a converted model

1. Directly load the model from a local directory:

model = faster_whisper.WhisperModel("whisper-large-v2-ct2")

2. Upload your model to the Hugging Face Hub and load it from its name:

model = faster_whisper.WhisperModel("username/whisper-large-v2-ct2")

Comparing performance against other implementations

If you are comparing the performance against other Whisper implementations, you should make sure to run the comparison with similar settings. In particular:

• Verify that the same transcription options are used, especially the same beam size. For example in openai/whisper, model.transcribe uses a default beam size of 1 but here we use a default beam size of 5.
• When running on CPU, make sure to set the same number of threads. Many frameworks will read the environment variable OMP_NUM_THREADS, which can be set when running your script:

OMP_NUM_THREADS=4 python3 my_script.py