31 lines
467 B
Plaintext
31 lines
467 B
Plaintext
|
# SenseVoice语音识别工具依赖包
|
|||
|
|
|
|||
|
|
# 核心FunASR框架
|
|||
|
|
funasr>=1.0.0
|
|||
|
|
modelscope>=1.9.0
|
|||
|
|
|
|||
|
|
# 音频处理
|
|||
|
|
librosa>=0.10.0
|
|||
|
|
soundfile>=0.12.0
|
|||
|
|
audioread>=3.0.0
|
|||
|
|
resampy>=0.4.0
|
|||
|
|
|
|||
|
|
# 深度学习框架
|
|||
|
|
torch>=1.13.0
|
|||
|
|
torchaudio>=0.13.0
|
|||
|
|
onnxruntime>=1.15.0
|
|||
|
|
|
|||
|
|
# 数据处理
|
|||
|
|
numpy>=1.21.0
|
|||
|
|
scipy>=1.9.0
|
|||
|
|
pandas>=1.5.0
|
|||
|
|
|
|||
|
|
# 其他依赖
|
|||
|
|
pyyaml>=6.0
|
|||
|
|
tqdm>=4.64.0
|
|||
|
|
requests>=2.28.0
|
|||
|
|
protobuf>=3.20.0
|
|||
|
|
|
|||
|
|
# 可选：GPU支持
|
|||
|
|
# torch>=1.13.0+cu117 # CUDA 11.7
|
|||
|
|
# torchaudio>=0.13.0+cu117
|