[项目打包]完成docker的打包，项目README更新，使用uv控制依赖。
This commit is contained in:
Ziyang.Zhang
parent
db811763d4
commit
2172e58fce
27
Dockerfile
27
Dockerfile
@ -1,27 +0,0 @@
|
|||||||
FROM python:3.9-slim
|
|
||||||
|
|
||||||
# 安装系统依赖
|
|
||||||
RUN apt-get update && apt-get install -y \
|
|
||||||
build-essential \
|
|
||||||
libsndfile1 \
|
|
||||||
ffmpeg \
|
|
||||||
&& rm -rf /var/lib/apt/lists/*
|
|
||||||
|
|
||||||
WORKDIR /app
|
|
||||||
|
|
||||||
# 安装Python依赖
|
|
||||||
COPY requirements.txt .
|
|
||||||
RUN pip install --no-cache-dir -r requirements.txt
|
|
||||||
|
|
||||||
# 复制应用代码
|
|
||||||
COPY . .
|
|
||||||
|
|
||||||
# 设置环境变量
|
|
||||||
ENV PYTHONPATH=/app
|
|
||||||
ENV PYTHONUNBUFFERED=1
|
|
||||||
|
|
||||||
# 暴露WebSocket端口
|
|
||||||
EXPOSE 10095
|
|
||||||
|
|
||||||
# 启动服务
|
|
||||||
CMD ["python", "src/server.py"]
|
|
||||||
59
README.md
59
README.md
@ -17,7 +17,12 @@
|
|||||||
```
|
```
|
||||||
.
|
.
|
||||||
├── main.py # 应用程序主入口，使用 uvicorn 启动服务
|
├── main.py # 应用程序主入口，使用 uvicorn 启动服务
|
||||||
├── WEBSOCKET_API.md # WebSocket API 详细使用文档和示例
|
├── docker
|
||||||
|
│ ├── Dockerfile # Docker 镜像构建文件
|
||||||
|
│ ├── docker-compose.yml # Docker 容器编排文件
|
||||||
|
├── docs
|
||||||
|
│ ├── WEBSOCKET_API.md # WebSocket API 详细使用文档和示例
|
||||||
|
│ ├── SystemArchitecture.md # 系统架构文档
|
||||||
├── src
|
├── src
|
||||||
│ ├── server.py # FastAPI 应用核心，管理生命周期和全局资源
|
│ ├── server.py # FastAPI 应用核心，管理生命周期和全局资源
|
||||||
│ ├── runner
|
│ ├── runner
|
||||||
@ -30,12 +35,17 @@
|
|||||||
│ │ ├── endpoint
|
│ │ ├── endpoint
|
||||||
│ │ │ └── asr_endpoint.py # WebSocket 的业务逻辑端点
|
│ │ │ └── asr_endpoint.py # WebSocket 的业务逻辑端点
|
||||||
│ │ └── router.py # WebSocket 路由
|
│ │ └── router.py # WebSocket 路由
|
||||||
│ └── ...
|
│ ├── core
|
||||||
└── tests
|
│ │ └── model_loader.py # 模型加载器
|
||||||
├── runner
|
│ ├── utils
|
||||||
│ └── asr_runner_test.py # ASRRunner 的单元测试 (异步)
|
│ │ └── logger.py # 日志记录器
|
||||||
└── websocket
|
│ │ └── data_format.py # 数据格式转换
|
||||||
└── websocket_asr.py # WebSocket 服务的端到端测试
|
│ │ └── mock_websocket.py # 模拟 WebSocket 客户端
|
||||||
|
├── tests
|
||||||
|
│ ├── runner
|
||||||
|
│ │ └── asr_runner_test.py # ASRRunner 的单元测试 (异步)
|
||||||
|
│ ├── websocket
|
||||||
|
│ │ └── websocket_asr.py # WebSocket 服务的端到端测试
|
||||||
```
|
```
|
||||||
|
|
||||||
## 🚀 快速开始
|
## 🚀 快速开始
|
||||||
@ -95,3 +105,38 @@ python tests/websocket/websocket_asr.py
|
|||||||
python test_main.py
|
python test_main.py
|
||||||
```
|
```
|
||||||
|
|
||||||
|
## 🐳 使用 Docker 部署
|
||||||
|
|
||||||
|
### 1. 构建 Docker 镜像
|
||||||
|
|
||||||
|
在项目根目录下，运行：
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker build -t asr-server:x.x.x -f docker/Dockerfile .
|
||||||
|
```
|
||||||
|
|
||||||
|
### 2. 运行 Docker 容器
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker run -d -p 11096:11096 --name asr-server -v ~/.cache/modelscope:/root/.cache/modelscope asr-server:x.x.x
|
||||||
|
```
|
||||||
|
|
||||||
|
### 环境变量说明
|
||||||
|
|
||||||
|
- `SPEAKERS_URL`: 说话人数据库 API 的 URL。
|
||||||
|
|
||||||
|
示例/默认 SPEAKERS_URL="http://172.23.30.120:11200/api/v1/speakers/"
|
||||||
|
|
||||||
|
此url为后端api提供的查询所有数据库中说话人信息的接口
|
||||||
|
|
||||||
|
- `LOG_LEVEL`: 日志等级。
|
||||||
|
|
||||||
|
示例/默认 LOG_LEVEL="INFO"
|
||||||
|
|
||||||
|
`LOG_LEVEL` 为总项目日志等级，
|
||||||
|
|
||||||
|
- `LOG_LEVEL_ASR_SERVER`: 日志等级。
|
||||||
|
|
||||||
|
示例/默认 LOG_LEVEL_ASR_SERVER="INFO"
|
||||||
|
|
||||||
|
`LOG_LEVEL_ASR_SERVER` 为 ASR 服务日志等级，优先级高于 `LOG_LEVEL`
|
||||||
|
|||||||
@ -1,23 +0,0 @@
|
|||||||
version: '3.8'
|
|
||||||
|
|
||||||
services:
|
|
||||||
funasr:
|
|
||||||
build: .
|
|
||||||
container_name: funasr-websocket
|
|
||||||
volumes:
|
|
||||||
- .:/app
|
|
||||||
# 如果需要使用本地模型缓存
|
|
||||||
- ~/.cache/modelscope:/root/.cache/modelscope
|
|
||||||
ports:
|
|
||||||
- "10095:10095"
|
|
||||||
environment:
|
|
||||||
- PYTHONUNBUFFERED=1
|
|
||||||
deploy:
|
|
||||||
resources:
|
|
||||||
reservations:
|
|
||||||
devices:
|
|
||||||
- driver: nvidia
|
|
||||||
count: 1
|
|
||||||
capabilities: [gpu]
|
|
||||||
restart: unless-stopped
|
|
||||||
command: python src/server.py --device cuda --ngpu 1
|
|
||||||
36
docker/Dockerfile
Normal file
36
docker/Dockerfile
Normal file
@ -0,0 +1,36 @@
|
|||||||
|
FROM python:3.10-slim
|
||||||
|
|
||||||
|
# 更换系统源
|
||||||
|
# 科大大的 Debian 12 (bookworm) 镜像源
|
||||||
|
RUN echo "deb http://mirrors.ustc.edu.cn/debian bookworm main contrib non-free" > /etc/apt/sources.list && \
|
||||||
|
echo "deb http://mirrors.ustc.edu.cn/debian bookworm-updates main contrib non-free" >> /etc/apt/sources.list && \
|
||||||
|
echo "deb http://mirrors.ustc.edu.cn/debian-security bookworm-security main" >> /etc/apt/sources.list && \
|
||||||
|
echo "deb http://mirrors.ustc.edu.cn/debian bookworm-backports main contrib non-free" >> /etc/apt/sources.list
|
||||||
|
# 安装系统依赖
|
||||||
|
RUN apt-get update && apt-get install -y \
|
||||||
|
build-essential \
|
||||||
|
libsndfile1 \
|
||||||
|
ffmpeg \
|
||||||
|
&& rm -rf /var/lib/apt/lists/*
|
||||||
|
|
||||||
|
WORKDIR /app
|
||||||
|
|
||||||
|
# 安装Python依赖
|
||||||
|
COPY ../requirements.txt .
|
||||||
|
RUN pip install --no-cache-dir -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
|
||||||
|
|
||||||
|
# 复制应用代码
|
||||||
|
COPY ../src/ /app/src/
|
||||||
|
COPY ../logs/ /app/logs/
|
||||||
|
COPY ../main.py /app/
|
||||||
|
|
||||||
|
# 设置环境变量
|
||||||
|
ENV SPEAKERS_URL="http://172.23.30.120:11200/api/v1/speakers/" \
|
||||||
|
LOG_LEVEL="INFO" \
|
||||||
|
LOG_LEVEL_ASR_SERVER="INFO"
|
||||||
|
|
||||||
|
# 暴露WebSocket端口
|
||||||
|
EXPOSE 11096
|
||||||
|
|
||||||
|
# 启动服务
|
||||||
|
CMD ["python", "main.py"]
|
||||||
94
docs/SystemArchitecture.md
Normal file
94
docs/SystemArchitecture.md
Normal file
@ -0,0 +1,94 @@
|
|||||||
|
# 系统架构
|
||||||
|
|
||||||
|
本项目是一个基于 FunASR 和 FastAPI 构建的高性能、实时的语音识别（ASR）WebSocket 服务。其核心架构设计旨在处理实时的流式音频数据，并通过 "一发多收" 的广播模式，将识别结果分发给多个客户端。
|
||||||
|
|
||||||
|
## 核心组件
|
||||||
|
|
||||||
|
系统主要由以下几个核心组件构成，它们各司其职，通过异步和多线程协作，实现了高效的实时语音处理：
|
||||||
|
|
||||||
|
1. **WebSocket 服务 (FastAPI)**
|
||||||
|
- **文件**: `src/websockets/`, `src/server.py`, `main.py`
|
||||||
|
- **职责**: 作为系统的网络入口，负责处理 WebSocket 连接。它使用 FastAPI 构建，提供异步的、非阻塞的 I/O 处理能力，能够高效地管理大量并发客户端连接。`asr_endpoint.py` 是核心端点，负责根据客户端声明的 `mode` (sender/receiver) 将连接路由到 `ASRRunner`。
|
||||||
|
|
||||||
|
2. **会话管理器 (ASRRunner)**
|
||||||
|
- **文件**: `src/runner/ASRRunner.py`
|
||||||
|
- **职责**: 这是整个系统的"大脑"和协调中心。它管理所有活跃的语音识别会话（`SenderAndReceiver`，简称 SAR）。
|
||||||
|
- **会话生命周期**: 当一个 `sender` 连接时，`ASRRunner` 会创建一个新的 SAR 实例；当 `receiver` 连接时，会将其加入到指定的 SAR 中。
|
||||||
|
- **异步桥梁**: `ASRRunner` 运行在主 `asyncio` 事件循环中，负责从 `sender` 的 WebSocket 连接异步接收音频数据，然后通过线程安全的队列 (`queue.Queue`) 将数据传递给同步的 `ASRPipeline`。同时，它也负责接收来自 Pipeline 的最终结果，并将其异步广播给所有 `receiver`。
|
||||||
|
|
||||||
|
3. **语音处理流水线 (ASRPipeline)**
|
||||||
|
- **文件**: `src/pipeline/ASRpipeline.py`
|
||||||
|
- **职责**: 这是实际执行语音处理任务的核心引擎。每个 SAR 会话都拥有一个独立的 `ASRPipeline` 实例，该实例在自己的后台线程中运行。
|
||||||
|
- **模块化设计**: Pipeline 内部由多个 `Functor` (如 VAD, ASR, SPK) 组成，通过一系列内部队列连接，形成一个处理链。
|
||||||
|
- **处理流程**:
|
||||||
|
1. **VAD (Voice Activity Detection)**: 检测音频流中的有效语音片段。
|
||||||
|
2. **ASR (Automatic Speech Recognition)**: 将语音片段转换为文字。
|
||||||
|
3. **SPK (Speaker Recognition)**: 识别说话人（声纹识别）。
|
||||||
|
4. **ResultBinder**: 将 ASR 的文本结果和 SPK 的说话人结果合并，生成最终的识别消息。
|
||||||
|
|
||||||
|
4. **原子操作单元 (Functor)**
|
||||||
|
- **文件**: `src/functor/`
|
||||||
|
- **职责**: `Functor` 是 Pipeline 中执行具体原子任务的单元。每个 Functor 都是一个独立的类，负责调用底层 FunASR 模型来执行 VAD、ASR 或 SPK 等任务。这种设计使得处理流程更加清晰和模块化。
|
||||||
|
|
||||||
|
## 流程图
|
||||||
|
|
||||||
|
下面是系统处理一次完整语音识别请求的流程图，展示了从客户端连接到收到识别结果的全过程。
|
||||||
|
|
||||||
|
```mermaid
|
||||||
|
sequenceDiagram
|
||||||
|
participant Sender Client
|
||||||
|
participant Receiver Client
|
||||||
|
participant FastAPI WebSocket Endpoint
|
||||||
|
participant ASRRunner
|
||||||
|
participant ASRPipeline (Thread)
|
||||||
|
participant Functors (VAD, ASR, SPK)
|
||||||
|
|
||||||
|
par
|
||||||
|
Sender Client->>+FastAPI WebSocket Endpoint: 发起连接 (mode=sender, session_id=S1)
|
||||||
|
FastAPI WebSocket Endpoint->>+ASRRunner: new_SAR(ws, name="S1")
|
||||||
|
ASRRunner->>ASRRunner: 创建 SenderAndReceiver (SAR) 实例
|
||||||
|
ASRRunner->>ASRPipeline (Thread): 创建并运行 Pipeline 实例
|
||||||
|
ASRPipeline (Thread)->>Functors (VAD, ASR, SPK): 初始化 Functor 线程
|
||||||
|
ASRRunner->>-FastAPI WebSocket Endpoint: 返回成功
|
||||||
|
FastAPI WebSocket Endpoint->>-Sender Client: 连接建立
|
||||||
|
and
|
||||||
|
Receiver Client->>+FastAPI WebSocket Endpoint: 发起连接 (mode=receiver, session_id=S1)
|
||||||
|
FastAPI WebSocket Endpoint->>+ASRRunner: join_SAR(ws, name="S1")
|
||||||
|
ASRRunner->>ASRRunner: 将 Receiver 加入 S1 的接收者列表
|
||||||
|
ASRRunner->>-FastAPI WebSocket Endpoint: 返回成功
|
||||||
|
FastAPI WebSocket Endpoint->>-Receiver Client: 连接建立
|
||||||
|
end
|
||||||
|
|
||||||
|
loop 音频流传输与处理
|
||||||
|
Sender Client->>ASRRunner: 发送音频数据块
|
||||||
|
ASRRunner->>ASRPipeline (Thread): (via Queue) 传递音频数据
|
||||||
|
ASRPipeline (Thread)->>Functors (VAD, ASR, SPK): (via sub-queues) 分发数据
|
||||||
|
Note over Functors (VAD, ASR, SPK): 1. VAD检测语音<br/>2. ASR识别文本<br/>3. SPK识别说话人<br/>4. ResultBinder合并结果
|
||||||
|
Functors (VAD, ASR, SPK)->>ASRPipeline (Thread): (via callback) 返回最终识别结果
|
||||||
|
ASRPipeline (Thread)->>ASRRunner: (via thread-safe callback) 发送结果
|
||||||
|
end
|
||||||
|
|
||||||
|
ASRRunner->>ASRRunner: 收到结果，准备广播
|
||||||
|
ASRRunner-->>Sender Client: 广播识别结果
|
||||||
|
ASRRunner-->>Receiver Client: 广播识别结果
|
||||||
|
|
||||||
|
par
|
||||||
|
Sender Client->>FastAPI WebSocket Endpoint: 关闭连接
|
||||||
|
FastAPI WebSocket Endpoint->>ASRRunner: (触发异常)
|
||||||
|
ASRRunner->>ASRPipeline (Thread): 发送停止信号
|
||||||
|
ASRPipeline (Thread)->>Functors (VAD, ASR, SPK): 停止 Functor 线程
|
||||||
|
Note right of ASRRunner: 清理会话资源
|
||||||
|
and
|
||||||
|
Receiver Client->>FastAPI WebSocket Endpoint: 关闭连接
|
||||||
|
FastAPI WebSocket Endpoint->>ASRRunner: (触发异常)
|
||||||
|
ASRRunner->>ASRRunner: 从接收者列表移除
|
||||||
|
end
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
## 架构优势
|
||||||
|
|
||||||
|
- **高并发和低延迟**: 采用 `asyncio` 和 WebSocket，网络层能够处理大量并发连接。音频处理在独立的线程中进行，避免了 CPU 密集型任务阻塞事件循环，保证了低延迟。
|
||||||
|
- **解耦与模块化**: `WebSocket Endpoint`、`ASRRunner` 和 `ASRPipeline` 职责清晰，相互解耦。`Functor` 的设计使得添加或修改处理步骤变得容易。
|
||||||
|
- **鲁棒性**: 每个识别会话（SAR）都是隔离的，一个会话的失败不会影响其他会话。优雅的关闭逻辑确保了资源的正确释放。
|
||||||
|
- **可扩展性**: "一发多收" 的广播模式可以轻松扩展到大量 `receiver`，适用于多种实时应用场景。
|
||||||
5
main.py
5
main.py
@ -4,7 +4,10 @@ from src.utils.logger import get_module_logger, setup_root_logger
|
|||||||
from datetime import datetime
|
from datetime import datetime
|
||||||
|
|
||||||
time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||||
setup_root_logger(level="DEBUG", log_file=f"logs/main_{time}.log")
|
# 日志等级 LOG_LEVEL_ASR_SERVER > LOG_LEVEL > INFO(default)
|
||||||
|
logger_level = os.getenv("LOG_LEVEL", "INFO")
|
||||||
|
logger_level = os.getenv("LOG_LEVEL_ASR_SERVER", logger_level)
|
||||||
|
setup_root_logger(level=logger_level, log_file=f"logs/main_{time}.log")
|
||||||
logger = get_module_logger(__name__)
|
logger = get_module_logger(__name__)
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
|
|||||||
32
paerser.py
32
paerser.py
@ -1,32 +0,0 @@
|
|||||||
def pre_remove_details(input_string: str) -> str:
|
|
||||||
start_tag = '</details>'
|
|
||||||
start = input_string.find(start_tag, 0)
|
|
||||||
if start == -1:
|
|
||||||
return input_string, "unfind %s" % start_tag
|
|
||||||
return input_string[start + len(start_tag):], "success remove %s" % start_tag
|
|
||||||
|
|
||||||
def pre_remove_markdown(input_string: str) -> str:
|
|
||||||
start_tag = '```markdown'
|
|
||||||
end_tag = '```'
|
|
||||||
start = input_string.find(start_tag, 0)
|
|
||||||
if start == -1:
|
|
||||||
return input_string, "unfind %s" % start_tag
|
|
||||||
end = input_string.find(end_tag, start + 11)
|
|
||||||
if end == -1:
|
|
||||||
return input_string, "unfind %s" % end_tag
|
|
||||||
return input_string[start + 11:end].strip(), "success remove %s" % start_tag
|
|
||||||
|
|
||||||
def main(input_string: str) -> dict:
|
|
||||||
result = input_string
|
|
||||||
statuses = []
|
|
||||||
|
|
||||||
result, detail_status = pre_remove_details(result)
|
|
||||||
statuses.append(detail_status)
|
|
||||||
|
|
||||||
result, markdown_status = pre_remove_markdown(result)
|
|
||||||
statuses.append(markdown_status)
|
|
||||||
|
|
||||||
return {
|
|
||||||
"result": result,
|
|
||||||
"status": statuses
|
|
||||||
}
|
|
||||||
20
pyproject.toml
Normal file
20
pyproject.toml
Normal file
@ -0,0 +1,20 @@
|
|||||||
|
[project]
|
||||||
|
name = "asr-server"
|
||||||
|
version = "0.1.0"
|
||||||
|
requires-python = ">=3.9.21"
|
||||||
|
dependencies = [
|
||||||
|
"addict==2.4.0",
|
||||||
|
"datasets==2.21.0",
|
||||||
|
"fastapi==0.115.14",
|
||||||
|
"funasr==1.2.6",
|
||||||
|
"numpy==2.0.1",
|
||||||
|
"pillow==11.1.0",
|
||||||
|
"pydantic==2.11.3",
|
||||||
|
"pydub>=0.25.1",
|
||||||
|
"simplejson==3.20.1",
|
||||||
|
"sortedcontainers==2.4.0",
|
||||||
|
"torch==2.3.1",
|
||||||
|
"torchaudio==2.3.1",
|
||||||
|
"uvicorn==0.35.0",
|
||||||
|
"websockets==12.0",
|
||||||
|
]
|
||||||
330
requirements.txt
330
requirements.txt
@ -1,11 +1,335 @@
|
|||||||
|
# This file was autogenerated by uv via the following command:
|
||||||
|
# uv pip compile pyproject.toml -o requirements.txt
|
||||||
|
addict==2.4.0
|
||||||
|
# via asr-server (pyproject.toml)
|
||||||
|
aiohappyeyeballs==2.6.1
|
||||||
|
# via aiohttp
|
||||||
|
aiohttp==3.12.13
|
||||||
|
# via
|
||||||
|
# datasets
|
||||||
|
# fsspec
|
||||||
|
aiosignal==1.4.0
|
||||||
|
# via aiohttp
|
||||||
|
aliyun-python-sdk-core==2.16.0
|
||||||
|
# via
|
||||||
|
# aliyun-python-sdk-kms
|
||||||
|
# oss2
|
||||||
|
aliyun-python-sdk-kms==2.16.5
|
||||||
|
# via oss2
|
||||||
|
annotated-types==0.7.0
|
||||||
|
# via pydantic
|
||||||
|
antlr4-python3-runtime==4.9.3
|
||||||
|
# via
|
||||||
|
# hydra-core
|
||||||
|
# omegaconf
|
||||||
|
anyio==4.9.0
|
||||||
|
# via starlette
|
||||||
|
async-timeout==5.0.1
|
||||||
|
# via aiohttp
|
||||||
|
attrs==25.3.0
|
||||||
|
# via aiohttp
|
||||||
|
audioread==3.0.1
|
||||||
|
# via librosa
|
||||||
|
certifi==2025.6.15
|
||||||
|
# via requests
|
||||||
|
cffi==1.17.1
|
||||||
|
# via
|
||||||
|
# cryptography
|
||||||
|
# soundfile
|
||||||
|
charset-normalizer==3.4.2
|
||||||
|
# via requests
|
||||||
|
click==8.2.1
|
||||||
|
# via uvicorn
|
||||||
|
crcmod==1.7
|
||||||
|
# via oss2
|
||||||
|
cryptography==45.0.5
|
||||||
|
# via aliyun-python-sdk-core
|
||||||
|
datasets==2.21.0
|
||||||
|
# via asr-server (pyproject.toml)
|
||||||
|
decorator==5.2.1
|
||||||
|
# via librosa
|
||||||
|
dill==0.3.8
|
||||||
|
# via
|
||||||
|
# datasets
|
||||||
|
# multiprocess
|
||||||
|
editdistance==0.8.1
|
||||||
|
# via funasr
|
||||||
|
exceptiongroup==1.3.0
|
||||||
|
# via anyio
|
||||||
fastapi==0.115.14
|
fastapi==0.115.14
|
||||||
|
# via asr-server (pyproject.toml)
|
||||||
|
filelock==3.18.0
|
||||||
|
# via
|
||||||
|
# datasets
|
||||||
|
# huggingface-hub
|
||||||
|
# torch
|
||||||
|
# triton
|
||||||
|
frozenlist==1.7.0
|
||||||
|
# via
|
||||||
|
# aiohttp
|
||||||
|
# aiosignal
|
||||||
|
fsspec==2024.6.1
|
||||||
|
# via
|
||||||
|
# datasets
|
||||||
|
# huggingface-hub
|
||||||
|
# torch
|
||||||
funasr==1.2.6
|
funasr==1.2.6
|
||||||
|
# via asr-server (pyproject.toml)
|
||||||
|
h11==0.16.0
|
||||||
|
# via uvicorn
|
||||||
|
hf-xet==1.1.5
|
||||||
|
# via huggingface-hub
|
||||||
|
huggingface-hub==0.33.2
|
||||||
|
# via datasets
|
||||||
|
hydra-core==1.3.2
|
||||||
|
# via funasr
|
||||||
|
idna==3.10
|
||||||
|
# via
|
||||||
|
# anyio
|
||||||
|
# requests
|
||||||
|
# yarl
|
||||||
|
jaconv==0.4.0
|
||||||
|
# via funasr
|
||||||
|
jamo==0.4.1
|
||||||
|
# via funasr
|
||||||
|
jieba==0.42.1
|
||||||
|
# via funasr
|
||||||
|
jinja2==3.1.6
|
||||||
|
# via torch
|
||||||
|
jmespath==0.10.0
|
||||||
|
# via aliyun-python-sdk-core
|
||||||
|
joblib==1.5.1
|
||||||
|
# via
|
||||||
|
# librosa
|
||||||
|
# pynndescent
|
||||||
|
# scikit-learn
|
||||||
|
kaldiio==2.18.1
|
||||||
|
# via funasr
|
||||||
|
lazy-loader==0.4
|
||||||
|
# via librosa
|
||||||
|
librosa==0.11.0
|
||||||
|
# via funasr
|
||||||
|
llvmlite==0.44.0
|
||||||
|
# via
|
||||||
|
# numba
|
||||||
|
# pynndescent
|
||||||
|
markupsafe==3.0.2
|
||||||
|
# via jinja2
|
||||||
modelscope==1.27.1
|
modelscope==1.27.1
|
||||||
|
# via funasr
|
||||||
|
mpmath==1.3.0
|
||||||
|
# via sympy
|
||||||
|
msgpack==1.1.1
|
||||||
|
# via librosa
|
||||||
|
multidict==6.6.3
|
||||||
|
# via
|
||||||
|
# aiohttp
|
||||||
|
# yarl
|
||||||
|
multiprocess==0.70.16
|
||||||
|
# via datasets
|
||||||
|
networkx==3.4.2
|
||||||
|
# via torch
|
||||||
|
numba==0.61.2
|
||||||
|
# via
|
||||||
|
# librosa
|
||||||
|
# pynndescent
|
||||||
|
# umap-learn
|
||||||
numpy==2.0.1
|
numpy==2.0.1
|
||||||
pyaudio==0.2.14
|
# via
|
||||||
pydantic==2.11.7
|
# asr-server (pyproject.toml)
|
||||||
|
# datasets
|
||||||
|
# kaldiio
|
||||||
|
# librosa
|
||||||
|
# numba
|
||||||
|
# pandas
|
||||||
|
# pytorch-wpe
|
||||||
|
# scikit-learn
|
||||||
|
# scipy
|
||||||
|
# soundfile
|
||||||
|
# soxr
|
||||||
|
# tensorboardx
|
||||||
|
# torch-complex
|
||||||
|
# umap-learn
|
||||||
|
nvidia-cublas-cu12==12.1.3.1
|
||||||
|
# via
|
||||||
|
# nvidia-cudnn-cu12
|
||||||
|
# nvidia-cusolver-cu12
|
||||||
|
# torch
|
||||||
|
nvidia-cuda-cupti-cu12==12.1.105
|
||||||
|
# via torch
|
||||||
|
nvidia-cuda-nvrtc-cu12==12.1.105
|
||||||
|
# via torch
|
||||||
|
nvidia-cuda-runtime-cu12==12.1.105
|
||||||
|
# via torch
|
||||||
|
nvidia-cudnn-cu12==8.9.2.26
|
||||||
|
# via torch
|
||||||
|
nvidia-cufft-cu12==11.0.2.54
|
||||||
|
# via torch
|
||||||
|
nvidia-curand-cu12==10.3.2.106
|
||||||
|
# via torch
|
||||||
|
nvidia-cusolver-cu12==11.4.5.107
|
||||||
|
# via torch
|
||||||
|
nvidia-cusparse-cu12==12.1.0.106
|
||||||
|
# via
|
||||||
|
# nvidia-cusolver-cu12
|
||||||
|
# torch
|
||||||
|
nvidia-nccl-cu12==2.20.5
|
||||||
|
# via torch
|
||||||
|
nvidia-nvjitlink-cu12==12.9.86
|
||||||
|
# via
|
||||||
|
# nvidia-cusolver-cu12
|
||||||
|
# nvidia-cusparse-cu12
|
||||||
|
nvidia-nvtx-cu12==12.1.105
|
||||||
|
# via torch
|
||||||
|
omegaconf==2.3.0
|
||||||
|
# via hydra-core
|
||||||
|
oss2==2.19.1
|
||||||
|
# via funasr
|
||||||
|
packaging==25.0
|
||||||
|
# via
|
||||||
|
# datasets
|
||||||
|
# huggingface-hub
|
||||||
|
# hydra-core
|
||||||
|
# lazy-loader
|
||||||
|
# pooch
|
||||||
|
# tensorboardx
|
||||||
|
# torch-complex
|
||||||
|
pandas==2.3.0
|
||||||
|
# via datasets
|
||||||
|
pillow==11.1.0
|
||||||
|
# via asr-server (pyproject.toml)
|
||||||
|
platformdirs==4.3.8
|
||||||
|
# via pooch
|
||||||
|
pooch==1.8.2
|
||||||
|
# via librosa
|
||||||
|
propcache==0.3.2
|
||||||
|
# via
|
||||||
|
# aiohttp
|
||||||
|
# yarl
|
||||||
|
protobuf==6.31.1
|
||||||
|
# via tensorboardx
|
||||||
|
pyarrow==20.0.0
|
||||||
|
# via datasets
|
||||||
|
pycparser==2.22
|
||||||
|
# via cffi
|
||||||
|
pycryptodome==3.23.0
|
||||||
|
# via oss2
|
||||||
|
pydantic==2.11.3
|
||||||
|
# via
|
||||||
|
# asr-server (pyproject.toml)
|
||||||
|
# fastapi
|
||||||
|
pydantic-core==2.33.1
|
||||||
|
# via pydantic
|
||||||
pydub==0.25.1
|
pydub==0.25.1
|
||||||
pytest==8.3.5
|
# via asr-server (pyproject.toml)
|
||||||
|
pynndescent==0.5.13
|
||||||
|
# via umap-learn
|
||||||
|
python-dateutil==2.9.0.post0
|
||||||
|
# via pandas
|
||||||
|
pytorch-wpe==0.0.1
|
||||||
|
# via funasr
|
||||||
|
pytz==2025.2
|
||||||
|
# via pandas
|
||||||
|
pyyaml==6.0.2
|
||||||
|
# via
|
||||||
|
# datasets
|
||||||
|
# funasr
|
||||||
|
# huggingface-hub
|
||||||
|
# omegaconf
|
||||||
|
requests==2.32.4
|
||||||
|
# via
|
||||||
|
# datasets
|
||||||
|
# funasr
|
||||||
|
# huggingface-hub
|
||||||
|
# modelscope
|
||||||
|
# oss2
|
||||||
|
# pooch
|
||||||
|
scikit-learn==1.7.0
|
||||||
|
# via
|
||||||
|
# librosa
|
||||||
|
# pynndescent
|
||||||
|
# umap-learn
|
||||||
|
scipy==1.15.3
|
||||||
|
# via
|
||||||
|
# funasr
|
||||||
|
# librosa
|
||||||
|
# pynndescent
|
||||||
|
# scikit-learn
|
||||||
|
# umap-learn
|
||||||
|
sentencepiece==0.2.0
|
||||||
|
# via funasr
|
||||||
|
setuptools==80.9.0
|
||||||
|
# via modelscope
|
||||||
|
simplejson==3.20.1
|
||||||
|
# via asr-server (pyproject.toml)
|
||||||
|
six==1.17.0
|
||||||
|
# via
|
||||||
|
# oss2
|
||||||
|
# python-dateutil
|
||||||
|
sniffio==1.3.1
|
||||||
|
# via anyio
|
||||||
|
sortedcontainers==2.4.0
|
||||||
|
# via asr-server (pyproject.toml)
|
||||||
soundfile==0.13.1
|
soundfile==0.13.1
|
||||||
|
# via
|
||||||
|
# funasr
|
||||||
|
# librosa
|
||||||
|
soxr==0.5.0.post1
|
||||||
|
# via librosa
|
||||||
|
starlette==0.46.2
|
||||||
|
# via fastapi
|
||||||
|
sympy==1.14.0
|
||||||
|
# via torch
|
||||||
|
tensorboardx==2.6.4
|
||||||
|
# via funasr
|
||||||
|
threadpoolctl==3.6.0
|
||||||
|
# via scikit-learn
|
||||||
torch==2.3.1
|
torch==2.3.1
|
||||||
|
# via
|
||||||
|
# asr-server (pyproject.toml)
|
||||||
|
# torchaudio
|
||||||
|
torch-complex==0.4.4
|
||||||
|
# via funasr
|
||||||
|
torchaudio==2.3.1
|
||||||
|
# via asr-server (pyproject.toml)
|
||||||
|
tqdm==4.67.1
|
||||||
|
# via
|
||||||
|
# datasets
|
||||||
|
# funasr
|
||||||
|
# huggingface-hub
|
||||||
|
# modelscope
|
||||||
|
# umap-learn
|
||||||
|
triton==2.3.1
|
||||||
|
# via torch
|
||||||
|
typing-extensions==4.14.1
|
||||||
|
# via
|
||||||
|
# aiosignal
|
||||||
|
# anyio
|
||||||
|
# exceptiongroup
|
||||||
|
# fastapi
|
||||||
|
# huggingface-hub
|
||||||
|
# librosa
|
||||||
|
# multidict
|
||||||
|
# pydantic
|
||||||
|
# pydantic-core
|
||||||
|
# torch
|
||||||
|
# typing-inspection
|
||||||
|
# uvicorn
|
||||||
|
typing-inspection==0.4.1
|
||||||
|
# via pydantic
|
||||||
|
tzdata==2025.2
|
||||||
|
# via pandas
|
||||||
|
umap-learn==0.5.9.post2
|
||||||
|
# via funasr
|
||||||
|
urllib3==2.5.0
|
||||||
|
# via
|
||||||
|
# modelscope
|
||||||
|
# requests
|
||||||
uvicorn==0.35.0
|
uvicorn==0.35.0
|
||||||
|
# via asr-server (pyproject.toml)
|
||||||
|
websockets==12.0
|
||||||
|
# via asr-server (pyproject.toml)
|
||||||
|
xxhash==3.5.0
|
||||||
|
# via datasets
|
||||||
|
yarl==1.20.1
|
||||||
|
# via aiohttp
|
||||||
|
|||||||
@ -1,11 +0,0 @@
|
|||||||
pytest==7.3.1
|
|
||||||
pytest-cov==4.1.0
|
|
||||||
flake8==6.0.0
|
|
||||||
black==23.3.0
|
|
||||||
isort==5.12.0
|
|
||||||
flask==2.3.2
|
|
||||||
requests==2.31.0
|
|
||||||
websockets==11.0.3
|
|
||||||
numpy==1.24.3
|
|
||||||
funasr==0.10.0
|
|
||||||
modelscope==1.9.5
|
|
||||||
@ -167,6 +167,7 @@ class FunctorFactory:
|
|||||||
spk_functor = SPKFunctor(sv_pipeline=models["spk"])
|
spk_functor = SPKFunctor(sv_pipeline=models["spk"])
|
||||||
spk_functor.set_audio_config(audio_config)
|
spk_functor.set_audio_config(audio_config)
|
||||||
# spk_functor.set_model(model)
|
# spk_functor.set_model(model)
|
||||||
|
spk_functor.bake()
|
||||||
|
|
||||||
logger.debug(f"创建spk functor[完成]")
|
logger.debug(f"创建spk functor[完成]")
|
||||||
return spk_functor
|
return spk_functor
|
||||||
|
|||||||
File diff suppressed because one or more lines are too long
Loading…
x
Reference in New Issue
Block a user