wehub/modelscope--funasr
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity

chore: import upstream snapshot with attribution

Browse Source
This commit is contained in:
wehub-resource-sync
2026-07-13 13:25:10 +08:00
commit c397331b1e
3684 changed files with 990993 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
runtime/python/http/README.md
+68
View File
@@ -0,0 +1,68 @@
# Service with http-python
## Server
1. Install requirements
```shell
cd funasr/runtime/python/http
pip install -r requirements.txt
```
2. Start server
```shell
python server.py --port 8000
```
More parameters:
```shell
python server.py \
--host [host ip] \
--port [server port] \
--asr_model [asr model_name] \
--vad_model [vad model_name] \
--punc_model [punc model_name] \
--device [cuda or cpu] \
--ngpu [0 or 1] \
--ncpu [1 or 4] \
--hotword_path [path of hot word txt] \
--certfile [path of certfile for ssl] \
--keyfile [path of keyfile for ssl] \
--temp_dir [upload file temp dir]
```
## Client
```shell
# get test audio file
wget https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav
python client.py --host=127.0.0.1 --port=8000 --audio_path=asr_example_zh.wav
```
More parameters:
```shell
python server.py \
--host [sever ip] \
--port [sever port] \
--audio_path [use audio path]
```
## 支持多进程
方法是启动多个`server.py`，然后通过Nginx的负载均衡分发请求，达到支持多用户同时连效果，处理方式如下，默认您已经安装了Nginx，没安装的请参考[官方安装教程](https://nginx.org/en/linux_packages.html#Ubuntu)。
配置Nginx。
```shell
sudo cp -f asr_nginx.conf /etc/nginx/nginx.conf
sudo service nginx reload
```
然后使用脚本启动多个服务，每个服务的端口号不一样。
```shell
sudo chmod +x start_server.sh
./start_server.sh
```
**说明：** 默认是3个进程，如果需要修改，首先修改`start_server.sh`的最后那部分，可以添加启动数量。然后修改`asr_nginx.conf`配置文件的`upstream backend`部分，增加新启动的服务，可以使其他服务器的服务。
runtime/python/http/asr_nginx.conf
+44
View File
@@ -0,0 +1,44 @@
user nginx;
worker_processes auto;
error_log /var/log/nginx/error.log notice;
pid /var/run/nginx.pid;
events {
worker_connections 1024;
}
http {
include /etc/nginx/mime.types;
default_type application/octet-stream;
log_format main '$remote_addr - $remote_user [$time_local] "$request" '
'$status $body_bytes_sent "$http_referer" '
'"$http_user_agent" "$http_x_forwarded_for"';
access_log /var/log/nginx/access.log main;
sendfile on;
keepalive_timeout 65;
upstream backend {
# 最少连接算法
least_conn;
# 启动的服务地址
server localhost:8001;
server localhost:8002;
server localhost:8003;
}
server {
# 实际访问的端口
listen 8000;
location / {
proxy_pass http://backend;
}
}
include /etc/nginx/conf.d/*.conf;
}
runtime/python/http/client.py
+33
View File
@@ -0,0 +1,33 @@
import os
import requests
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("--host", type=str, default="127.0.0.1", required=False, help="sever ip")
parser.add_argument("--port", type=int, default=8000, required=False, help="server port")
parser.add_argument(
"--audio_path", type=str, default="asr_example_zh.wav", required=False, help="use audio path"
)
args = parser.parse_args()
print("----------- Configuration Arguments -----------")
for arg, value in vars(args).items():
print("%s: %s" % (arg, value))
print("------------------------------------------------")
url = f"http://{args.host}:{args.port}/recognition"
headers = {}
files = [
(
"audio",
(
os.path.basename(args.audio_path),
open(args.audio_path, "rb"),
"application/octet-stream",
),
)
]
response = requests.post(url, headers=headers, files=files)
print(response.text)
runtime/python/http/hotwords.txt
+2
View File
@@ -0,0 +1,2 @@
阿里巴巴
通义实验室
runtime/python/http/requirements.txt
+6
View File
@@ -0,0 +1,6 @@
modelscope>=1.11.1
funasr>=1.0.5
fastapi>=0.95.1
aiofiles
uvicorn
requests
runtime/python/http/server.py
+133
View File
@@ -0,0 +1,133 @@
import argparse
import logging
import os
import uuid
import aiofiles
import ffmpeg
import uvicorn
from fastapi import FastAPI, File, UploadFile
from modelscope.utils.logger import get_logger
from funasr import AutoModel
logger = get_logger(log_level=logging.INFO)
logger.setLevel(logging.INFO)
parser = argparse.ArgumentParser()
parser.add_argument(
"--host", type=str, default="0.0.0.0", required=False, help="host ip, localhost, 0.0.0.0"
)
parser.add_argument("--port", type=int, default=8000, required=False, help="server port")
parser.add_argument(
"--asr_model",
type=str,
default="paraformer-zh",
help="asr model from https://github.com/alibaba-damo-academy/FunASR?tab=readme-ov-file#model-zoo",
)
parser.add_argument("--asr_model_revision", type=str, default="v2.0.4", help="")
parser.add_argument(
"--vad_model",
type=str,
default="fsmn-vad",
help="vad model from https://github.com/alibaba-damo-academy/FunASR?tab=readme-ov-file#model-zoo",
)
parser.add_argument("--vad_model_revision", type=str, default="v2.0.4", help="")
parser.add_argument(
"--punc_model",
type=str,
default="ct-punc-c",
help="model from https://github.com/alibaba-damo-academy/FunASR?tab=readme-ov-file#model-zoo",
)
parser.add_argument("--punc_model_revision", type=str, default="v2.0.4", help="")
parser.add_argument("--ngpu", type=int, default=1, help="0 for cpu, 1 for gpu")
parser.add_argument("--device", type=str, default="cuda", help="cuda, cpu")
parser.add_argument("--ncpu", type=int, default=4, help="cpu cores")
parser.add_argument(
"--hotword_path",
type=str,
default="hotwords.txt",
help="hot word txt path, only the hot word model works",
)
parser.add_argument("--certfile", type=str, default=None, required=False, help="certfile for ssl")
parser.add_argument("--keyfile", type=str, default=None, required=False, help="keyfile for ssl")
parser.add_argument("--temp_dir", type=str, default="temp_dir/", required=False, help="temp dir")
args = parser.parse_args()
logger.info("----------- Configuration Arguments -----------")
for arg, value in vars(args).items():
logger.info("%s: %s" % (arg, value))
logger.info("------------------------------------------------")
os.makedirs(args.temp_dir, exist_ok=True)
logger.info("model loading")
# load funasr model
model = AutoModel(
model=args.asr_model,
model_revision=args.asr_model_revision,
vad_model=args.vad_model,
vad_model_revision=args.vad_model_revision,
punc_model=args.punc_model,
punc_model_revision=args.punc_model_revision,
ngpu=args.ngpu,
ncpu=args.ncpu,
device=args.device,
disable_pbar=True,
disable_log=True,
)
logger.info("loaded models!")
app = FastAPI(title="FunASR")
param_dict = {"sentence_timestamp": True, "batch_size_s": 300}
if args.hotword_path is not None and os.path.exists(args.hotword_path):
with open(args.hotword_path, "r", encoding="utf-8") as f:
lines = f.readlines()
lines = [line.strip() for line in lines]
hotword = " ".join(lines)
logger.info(f"热词：{hotword}")
param_dict["hotword"] = hotword
@app.post("/recognition")
async def api_recognition(audio: UploadFile = File(..., description="audio file")):
suffix = audio.filename.split(".")[-1]
audio_path = f"{args.temp_dir}/{str(uuid.uuid1())}.{suffix}"
async with aiofiles.open(audio_path, "wb") as out_file:
content = await audio.read()
await out_file.write(content)
try:
audio_bytes, _ = (
ffmpeg.input(audio_path, threads=0)
.output("-", format="s16le", acodec="pcm_s16le", ac=1, ar=16000)
.run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
)
except Exception as e:
logger.error(f"读取音频文件发生错误，错误信息：{e}")
return {"msg": "读取音频文件发生错误", "code": 1}
rec_results = model.generate(input=audio_bytes, is_final=True, **param_dict)
# 结果为空
if len(rec_results[0]["text"] ) == 0:
return {"text": "", "sentences": [], "code": 0}
elif len(rec_results[0]["text"] ) > 0:
# 解析识别结果
rec_result = rec_results[0]
text = rec_result["text"]
sentences = []
for sentence in rec_result["sentence_info"]:
# 每句话的时间戳
sentences.append(
{"text": sentence["text"], "start": sentence["start"], "end": sentence["end"]}
)
ret = {"text": text, "sentences": sentences, "code": 0}
logger.info(f"识别结果：{ret}")
return ret
else:
logger.info(f"识别结果：{rec_results}")
return {"msg": "未知错误", "code": -1}
if __name__ == "__main__":
uvicorn.run(
app, host=args.host, port=args.port, ssl_keyfile=args.keyfile, ssl_certfile=args.certfile
)
runtime/python/http/start_server.sh
+21
View File
@@ -0,0 +1,21 @@
#!/bin/bash
# 创建日志文件夹
if [ ! -d "log/" ];then
mkdir log
fi
# kill掉之前的进程
server_id=`ps -ef | grep server.py | grep -v "grep" | awk '{print $2}'`
echo $server_id
for id in $server_id
do
kill -9 $id
echo "killed $id"
done
# 启动多个服务，可以设置使用不同的显卡
CUDA_VISIBLE_DEVICES=0 nohup python -u server.py --host=localhost --port=8001 >> log/output1.log 2>&1 &
CUDA_VISIBLE_DEVICES=0 nohup python -u server.py --host=localhost --port=8002 >> log/output2.log 2>&1 &
CUDA_VISIBLE_DEVICES=0 nohup python -u server.py --host=localhost --port=8003 >> log/output3.log 2>&1 &