No project description provided
Reason this release was yanked:
Broken CI due to hermetic toolchain
Project description
Pybind11 bindings for whisper.cpp
Quickstart
Install with pip:
pip install whispercpp
To use the latest version, install from source:
pip install git+https://github.com/aarnphm/whispercpp.git
For local setup, initialize all submodules:
git submodule update --init --recursive
Build the wheel:
# Option 1: using pypa/build
python3 -m build -w
# Option 2: using bazel
./tools/bazel build //:whispercpp_wheel
Install the wheel:
# Option 1: via pypa/build
pip install dist/*.whl
# Option 2: using bazel
pip install $(./tools/bazel info bazel-bin)/*.whl
The binding provides a Whisper class:
from whispercpp import Whisper
w = Whisper.from_pretrained("tiny.en")
Currently, the inference API is provided via transcribe:
w.transcribe(np.ones((1, 16000)))
You can use ffmpeg or librosa to load audio files into a Numpy array, then pass it to transcribe:
import ffmpeg
import numpy as np
try:
y, _ = (
ffmpeg.input("/path/to/audio.wav", threads=0)
.output("-", format="s16le", acodec="pcm_s16le", ac=1, ar=sample_rate)
.run(
cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True
)
)
except ffmpeg.Error as e:
raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e
arr = np.frombuffer(y, np.int16).flatten().astype(np.float32) / 32768.0
w.transcribe(arr)
The Pybind11 bindings supports all of the features from whisper.cpp.
The binding can also be used via api:
from whispercpp import api
ctx = api.Context.from_file("/path/to/saved_weight.bin")
params = api.Params()
ctx.full(arr, params)
Development
See DEVELOPMENT.md
APIs
Whisper
Whisper.from_pretrained(model_name: str) -> Whisper
Load a pre-trained model from the local cache or download and cache if needed.
w = Whisper.from_pretrained("tiny.en")
The model will be saved to $XDG_DATA_HOME/whispercpp or ~/.local/share/whispercpp if the environment variable is not set.
Whisper.transcribe(arr: NDArray[np.float32], num_proc: int = 1)
Running transcription on a given Numpy array. This calls full from whisper.cpp. If num_proc is greater than 1, it will use full_parallel instead.
w.transcribe(np.ones((1, 16000)))
api
api is a direct binding from whisper.cpp, that has similar APIs to whisper-rs.
api.Context
This class is a wrapper around whisper_context
from whispercpp import api ctx = api.Context.from_file("/path/to/saved_weight.bin")
api.Params
This class is a wrapper around whisper_params
from whispercpp import api params = api.Params()
Why not?
whispercpp.py. There are a few key differences here:
They provides the Cython bindings. From the UX standpoint, this achieves the same goal as whispercpp. The difference is whispercpp use Pybind11 instead. Feel free to use it if you prefer Cython over Pybind11. Note that whispercpp.py and whispercpp are mutually exclusive, as they also use the whispercpp namespace.
whispercpp doesn’t pollute your $HOME directory, rather it follows the XDG Base Directory Specification for saved weights.
Using cdll and ctypes and be done with it?
This is also valid, but requires a lot of hacking and it is pretty slow comparing to Cython and Pybind11.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distribution
Hashes for whispercpp-0.0.14-cp38-cp38-manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8b769cf54efb25aaa79939be36e612fb9cd43ab10c0e5d8a3944bf897b572fa1 |
|
MD5 | e500a8b383829a24f1e0e71d1706e8ea |
|
BLAKE2b-256 | fc7f4b4fb8ec3c160991b3ca75ce6560a7d0bf9b4e114f70a4d35f5de9a9c602 |