PyPI page
Home page
Author:
Speech Lab of Alibaba Group
License:
The MIT License
Summary:
OpenAI-compatible speech recognition toolkit with WebSocket streaming, vLLM acceleration, and llama.cpp/GGUF edge runtime.
Latest version:
1.4.0
Required dependencies:
huggingface_hub
|
hydra-core
|
jaconv
|
jamo
|
jieba
|
kaldiio
|
librosa
|
modelscope
|
numpy
|
omegaconf
|
oss2
|
pyyaml
|
rapidfuzz
|
regex
|
requests
|
safetensors
|
scipy
|
sentencepiece
|
soundfile
|
tensorboardx
|
tiktoken
|
torch_complex
|
tqdm
|
transformers
|
umap_learn
|
websockets
Optional dependencies:
accelerate
|
black
|
commonmark
|
configargparse
|
einops
|
fairscale
|
flake8
|
flake8-docstrings
|
hacking
|
jinja2
|
jsondiff
|
matplotlib
|
mock
|
nbsphinx
|
openai-whisper
|
pillow
|
pycodestyle
|
pytest
|
pytest-cov
|
pytest-pythonpath
|
pytest-timeouts
|
rapidfuzz
|
recommonmark
|
scipy
|
sphinx
|
sphinx-argparse
|
sphinx-markdown-tables
|
sphinx-rtd-theme
|
tiktoken
|
torch_optimizer
|
torchvision
|
transformers
|
transformers_stream_generator
Downloads last day:
18,091
Downloads last week:
114,608
Downloads last month:
471,579