From 55c09aeaa25b4bb88a50e09ba68fa6ff00a6d676 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期一, 15 一月 2024 20:10:39 +0800
Subject: [PATCH] update readme, fix seaco bug
---
funasr/quick_start.md | 100 ++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 81 insertions(+), 19 deletions(-)
diff --git a/funasr/quick_start.md b/funasr/quick_start.md
index 202c709..44ce5c4 100644
--- a/funasr/quick_start.md
+++ b/funasr/quick_start.md
@@ -16,7 +16,7 @@
#### Server Deployment
```shell
-cd funasr/runtime/python/websocket
+cd runtime/python/websocket
python funasr_wss_server.py --port 10095
```
@@ -26,39 +26,101 @@
python funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode 2pass --chunk_size "5,10,5"
```
-For more examples, please refer to [docs](runtime/python/websocket/README.md).
+For more examples, please refer to [docs](../runtime/python/websocket/README.md).
-### C++ version Example
+### Service Deployment Software
-Currently, offline file transcription service (CPU) is supported, and concurrent requests of hundreds of channels are supported.
+Both high-precision, high-efficiency, and high-concurrency file transcription, as well as low-latency real-time speech recognition, are supported. It also supports Docker deployment and multiple concurrent requests.
-##### The real-time transcription service, Mandarin (CPU)
-###### Server Deployment
-You can use the following command to complete the deployment:
+##### Docker Installation (optional)
+###### If you have already installed Docker, skip this step.
+
```shell
-curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/funasr-runtime-deploy-online-cpu-zh.sh
-sudo bash funasr-runtime-deploy-online-cpu-zh.sh install --workspace ./funasr-runtime-resources
+curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/install_docker.sh;
+sudo bash install_docker.sh
```
+##### Real-time Speech Recognition Service Deployment
+
+###### Docker Image Download and Launch
+Use the following command to pull and launch the FunASR software package Docker image锛圼Get the latest image version](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/SDK_advanced_guide_online.md)锛夛細
+
+```shell
+sudo docker pull \
+ registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.6
+mkdir -p ./funasr-runtime-resources/models
+sudo docker run -p 10096:10095 -it --privileged=true \
+ -v $PWD/funasr-runtime-resources/models:/workspace/models \
+ registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.6
+```
+
+###### Server Start
+
+After Docker is started, start the funasr-wss-server-2pass service program:
+
+```shell
+cd FunASR/runtime
+nohup bash run_server_2pass.sh \
+ --download-model-dir /workspace/models \
+ --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
+ --model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
+ --online-model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online-onnx \
+ --punc-dir damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727-onnx \
+ --itn-dir thuduj12/fst_itn_zh \
+ --hotword /workspace/models/hotwords.txt > log.out 2>&1 &
+
+# If you want to disable SSL, add the parameter: --certfile 0
+# If you want to deploy with a timestamp or nn hotword model, please set --model-dir to the corresponding model:
+# damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx (timestamp)
+# damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404-onnx (nn hotword)
+# If you want to load hotwords on the server side, please configure the hotwords in the host file ./funasr-runtime-resources/models/hotwords.txt (docker mapping address is /workspace/models/hotwords.txt):
+# One hotword per line, format (hotword weight): Alibaba 20
+```
###### Client Testing
Testing [samples](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/sample/funasr_samples.tar.gz)
```shell
-python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode 2pass
+python3 funasr_wss_client.py --host "127.0.0.1" --port 10096 --mode 2pass
```
-For more examples, please refer to [docs](runtime/docs/SDK_tutorial_online_zh.md)
+For more examples, please refer to [docs](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/SDK_advanced_guide_online.md)
#### File Transcription Service, Mandarin (CPU)
-##### Server Deployment
-
-You can use the following command to complete the deployment:
+###### Docker Image Download and Launch
+Use the following command to pull and launch the FunASR software package Docker image锛圼Get the latest image version](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/SDK_advanced_guide_offline.md)锛夛細
```shell
-curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/funasr-runtime-deploy-offline-cpu-zh.sh
-sudo bash funasr-runtime-deploy-offline-cpu-zh.sh install --workspace ./funasr-runtime-resources
+sudo docker pull \
+ registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.4.1
+mkdir -p ./funasr-runtime-resources/models
+sudo docker run -p 10095:10095 -it --privileged=true \
+ -v $PWD/funasr-runtime-resources/models:/workspace/models \
+ registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.4.1
+```
+
+###### Server Start
+
+After Docker is started, start the funasr-wss-server service program:
+
+```shell
+cd FunASR/runtime
+nohup bash run_server.sh \
+ --download-model-dir /workspace/models \
+ --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
+ --model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
+ --punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx \
+ --lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst \
+ --itn-dir thuduj12/fst_itn_zh \
+ --hotword /workspace/models/hotwords.txt > log.out 2>&1 &
+
+# If you want to disable SSL, add the parameter: --certfile 0
+# If you want to use timestamp or nn hotword models for deployment, please set --model-dir to the corresponding model:
+# damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx (timestamp)
+# damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404-onnx (nn hotword)
+# If you want to load hotwords on the server side, please configure the hotwords in the host machine file ./funasr-runtime-resources/models/hotwords.txt (docker mapping address is /workspace/models/hotwords.txt):
+# One hotword per line, format (hotword weight): Alibaba 20
```
##### Client Testing
@@ -68,7 +130,7 @@
python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav"
```
-For more examples, please refer to [docs](runtime/docs/SDK_tutorial_zh.md)
+For more examples, please refer to [docs](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/SDK_advanced_guide_offline.md)
## Industrial Model Egs
@@ -81,7 +143,7 @@
inference_pipeline = pipeline(
task=Tasks.auto_speech_recognition,
- model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
+ model='damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
)
rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
@@ -99,4 +161,4 @@
cd egs/aishell/paraformer
. ./run.sh --CUDA_VISIBLE_DEVICES="0,1" --gpu_num=2
```
-More examples could be found in [docs](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html)
\ No newline at end of file
+More examples could be found in [docs](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html)
--
Gitblit v1.9.1