ai/py-openai-whisper 20250625_1 MidnightBSD
Robust Speech Recognition via Large-Scale Weak Supervision
- System
- MidnightBSD
- Repository
- mports
- Maintainer
- [email protected]
- Last update
- Commit
dee1e47e52- License
- mit
- Categories
- ai, python
Description
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.
Install
Binary package:
mport install ${PYTHON_PKGNAMEPREFIX}openai-whisper
From mports:
cd /usr/mports/ai/py-openai-whisper && make install clean
To depend on this port in another port's Makefile:
RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}openai-whisper>0:ai/py-openai-whisper
Dependency graph
Ports that need it on the left, what it needs to run on the right; at most 8 of each. "Dependencies" below lists them all.
Dependencies
As this port's Makefile names them.
Build 1
${PYTHON_PKGNAMEPREFIX}wheel>0: devel/py-wheel
Runtime 6
${PYTHON_PKGNAMEPREFIX}more-itertools>0: devel/py-more-itertools${PYTHON_PKGNAMEPREFIX}numba>0: devel/py-numba${PYTHON_PKGNAMEPREFIX}numpy1>=1.16: math/py-numpy1${PYTHON_PKGNAMEPREFIX}tiktoken>0: textproc/py-tiktoken${PYTHON_PKGNAMEPREFIX}pytorch>0: ai/py-pytorch${PYTHON_PKGNAMEPREFIX}tqdm>0: misc/py-tqdm
Test 1
${PYTHON_PKGNAMEPREFIX}scipy>0: science/py-scipy
Build dependencies 1
Run dependencies 6
No port depends on this one.
Configuration
No options to configure.
- USES
- python
- Service scripts
- none
Files
distinfo 1
| File | Size | SHA256 |
|---|---|---|
| openai-whisper-v20250625_GH0.tar.gz | 7.262903e+06 | 812e8a4b54e117c1bda827597f54886084bf062453ede274caf4699153b673f9 |