65 lines
1.5 KiB
Plaintext
65 lines
1.5 KiB
Plaintext
# ============================================
|
||
# 语音识别 + 说话人分离 项目依赖
|
||
# ============================================
|
||
# 使用说明：
|
||
# 1. 创建虚拟环境：python -m venv funasr_env
|
||
# 2. 激活虚拟环境：funasr_env\Scripts\activate
|
||
# 3. 安装依赖：pip install -r requirements.txt
|
||
# ============================================
|
||
|
||
# ---------- 核心框架 ----------
|
||
torch>=2.7.0
|
||
torchaudio>=2.7.0
|
||
|
||
# ---------- FunASR 语音识别 ----------
|
||
funasr>=1.3.0
|
||
modelscope>=1.36.0
|
||
transformers>=5.7.0
|
||
|
||
# ---------- 3D-Speaker 说话人分离 ----------
|
||
# 注意：3D-Speaker 需要手动克隆到项目目录
|
||
# git clone https://github.com/alibaba-damo-academy/3D-Speaker.git
|
||
speakerlab>=0.0.6
|
||
|
||
# ---------- 音频处理 ----------
|
||
soundfile>=0.12.0
|
||
librosa>=0.11.0
|
||
scipy>=1.15.0
|
||
numpy>=1.26.0
|
||
|
||
# ---------- 机器学习基础库 ----------
|
||
scikit-learn>=1.7.0
|
||
numba>=0.65.0
|
||
pandas>=2.3.0
|
||
|
||
# ---------- 聚类算法 ----------
|
||
hdbscan>=0.8.42
|
||
umap-learn>=0.5.0
|
||
fastcluster>=1.2.0
|
||
|
||
# ---------- 深度学习组件 ----------
|
||
pytorch-lightning>=2.6.0
|
||
lightning>=2.6.0
|
||
pyannote.audio>=3.4.0
|
||
|
||
# ---------- 数据处理 ----------
|
||
datasets>=3.0.0,<4.0.0
|
||
pyarrow>=24.0.0
|
||
sentencepiece>=0.2.1
|
||
|
||
# ---------- 工具库 ----------
|
||
tqdm>=4.67.0
|
||
pyyaml>=6.0
|
||
simplejson>=3.19.0
|
||
sortedcontainers>=2.4.0
|
||
addict>=2.4.0
|
||
jieba>=0.42.0
|
||
|
||
# ---------- 可选：ONNX 加速 ----------
|
||
# onnxruntime-gpu>=1.23.0
|
||
|
||
# ---------- 可选：Web API 服务 ----------
|
||
Flask>=3.1.0
|
||
waitress>=3.0.0
|
||
# SQLAlchemy>=2.0.0
|