PyPI page
Home page
Author:
Quentin Fuxa
Summary:
Real-time speech-to-text models
Latest version:
0.2.26
Required dependencies:
fastapi
|
faster-whisper
|
huggingface-hub
|
librosa
|
python-multipart
|
soundfile
|
starlette
|
tiktoken
|
torch
|
torchaudio
|
tqdm
|
uvicorn
|
websockets
Optional dependencies:
accelerate
|
datasets
|
deepgram-sdk
|
diart
|
funasr
|
kaldialign
|
librosa
|
matplotlib
|
mistral-common
|
mlx
|
mlx-whisper
|
mosestokenizer
|
nemo-toolkit
|
nllw
|
onnx
|
pytest
|
pytest-asyncio
|
qwen3-asr-causal
|
sounddevice
|
torch
|
torchaudio
|
torchvision
|
transformers
|
triton
|
wtpsplit
Downloads last day:
219
Downloads last week:
1,731
Downloads last month:
6,366
7-day smoothing