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 |