GitHub / JigsawStack / insanely-fast-whisper-api
An API to transcribe audio with OpenAI's Whisper Large v3!
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JigsawStack%2Finsanely-fast-whisper-api
PURL: pkg:github/JigsawStack/insanely-fast-whisper-api
Stars: 185
Forks: 27
Open issues: 10
License: mit
Language: Python
Size: 250 KB
Dependencies parsed at:
298
Created at: over 1 year ago
Updated at: 10 months ago
Pushed at: 10 months ago
Last synced at: 10 months ago
Topics: ai, api, openai, speech-to-text, whisper
Dockerfile
docker
- nvcr.io/nvidia/pytorch 24.01-py3 build
pyproject.toml
pypi
- accelerate ^0.27.2
- fastapi ^0.109.2
- gunicorn ^21.2.0
- optimum ^1.17.0
- pyannote-audio ^3.1.1
- python ^3.10
- setuptools ^69.1.0
- transformers ^4.37.2
- uvicorn ^0.27.1
requirements.txt
pypi
- accelerate ==0.27.2
- aiohttp ==3.9.3
- aiosignal ==1.3.1
- alembic ==1.13.1
- annotated-types ==0.6.0
- antlr4-python3-runtime ==4.9.3
- anyio ==4.2.0
- asteroid-filterbanks ==0.4.0
- async-timeout ==4.0.3
- attrs ==23.2.0
- audioread ==3.0.1
- certifi ==2024.2.2
- cffi ==1.16.0
- charset-normalizer ==3.3.2
- click ==8.1.7
- colorama ==0.4.6
- coloredlogs ==15.0.1
- colorlog ==6.8.2
- contourpy ==1.2.0
- cycler ==0.12.1
- datasets ==2.14.4
- decorator ==5.1.1
- dill ==0.3.7
- docopt ==0.6.2
- einops ==0.7.0
- exceptiongroup ==1.2.0
- fastapi ==0.109.2
- filelock ==3.13.1
- fonttools ==4.49.0
- frozenlist ==1.4.1
- fsspec ==2024.2.0
- greenlet ==3.0.3
- gunicorn ==21.2.0
- h11 ==0.14.0
- httptools ==0.6.1
- huggingface-hub ==0.20.3
- humanfriendly ==10.0
- hyperpyyaml ==1.2.2
- idna ==3.6
- jinja2 ==3.1.3
- joblib ==1.3.2
- julius ==0.2.7
- kiwisolver ==1.4.5
- lazy-loader ==0.3
- librosa ==0.10.1
- lightning ==2.2.0.post0
- lightning-utilities ==0.10.1
- llvmlite ==0.42.0
- mako ==1.3.2
- markdown-it-py ==3.0.0
- markupsafe ==2.1.5
- matplotlib ==3.8.3
- mdurl ==0.1.2
- mpmath ==1.3.0
- msgpack ==1.0.7
- multidict ==6.0.5
- multiprocess ==0.70.15
- networkx ==3.2.1
- numba ==0.59.0
- numpy ==1.26.4
- nvidia-cublas-cu12 ==12.1.3.1
- nvidia-cuda-cupti-cu12 ==12.1.105
- nvidia-cuda-nvrtc-cu12 ==12.1.105
- nvidia-cuda-runtime-cu12 ==12.1.105
- nvidia-cudnn-cu12 ==8.9.2.26
- nvidia-cufft-cu12 ==11.0.2.54
- nvidia-curand-cu12 ==10.3.2.106
- nvidia-cusolver-cu12 ==11.4.5.107
- nvidia-cusparse-cu12 ==12.1.0.106
- nvidia-nccl-cu12 ==2.19.3
- nvidia-nvjitlink-cu12 ==12.3.101
- nvidia-nvtx-cu12 ==12.1.105
- omegaconf ==2.3.0
- optimum ==1.17.0
- optuna ==3.5.0
- packaging ==23.2
- pandas ==2.2.0
- pillow ==10.2.0
- platformdirs ==4.2.0
- pooch ==1.8.0
- primepy ==1.3
- protobuf ==4.25.3
- psutil ==5.9.8
- pyannote-audio ==3.1.1
- pyannote-core ==5.0.0
- pyannote-database ==5.0.1
- pyannote-metrics ==3.2.1
- pyannote-pipeline ==3.0.1
- pyarrow ==15.0.0
- pycparser ==2.21
- pydantic ==2.6.1
- pydantic-core ==2.16.2
- pygments ==2.17.2
- pyparsing ==3.1.1
- pyreadline3 ==3.4.1
- python-dateutil ==2.8.2
- python-dotenv ==1.0.1
- pytorch-lightning ==2.2.0.post0
- pytorch-metric-learning ==2.4.1
- pytz ==2024.1
- pyyaml ==6.0.1
- regex ==2023.12.25
- requests ==2.31.0
- rich ==13.7.0
- ruamel-yaml ==0.18.6
- ruamel-yaml-clib ==0.2.8
- safetensors ==0.4.2
- scikit-learn ==1.4.1.post1
- scipy ==1.12.0
- semver ==3.0.2
- sentencepiece ==0.1.99
- setuptools ==69.1.0
- shellingham ==1.5.4
- six ==1.16.0
- sniffio ==1.3.0
- sortedcontainers ==2.4.0
- soundfile ==0.12.1
- soxr ==0.3.7
- speechbrain ==0.5.16
- sqlalchemy ==2.0.27
- starlette ==0.36.3
- sympy ==1.12
- tabulate ==0.9.0
- tensorboardx ==2.6.2.2
- threadpoolctl ==3.3.0
- tokenizers ==0.15.2
- torch ==2.2.0
- torch-audiomentations ==0.11.1
- torch-pitch-shift ==1.2.4
- torchaudio ==2.2.0
- torchmetrics ==1.3.1
- tqdm ==4.66.2
- transformers ==4.37.2
- triton ==2.2.0
- typer ==0.9.0
- typing-extensions ==4.9.0
- tzdata ==2024.1
- urllib3 ==2.2.0
- uvicorn ==0.27.1
- uvloop ==0.19.0
- watchfiles ==0.21.0
- websockets ==11.0.3
- xxhash ==3.4.1
- yarl ==1.9.4