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

Executed with CUDA 11.7.1 on a NVIDIA Tesla V100S.

Small model on CPU

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"

# Install for development:
git clone https://github.com/guillaumekln/faster-whisper.git
pip install -e faster-whisper/

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

Transcription

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))

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))

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

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.

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