Quick Start

You can use FunASR in the following ways:

Service Deployment SDK
Industrial model egs
Academic model egs

Service Deployment SDK

Python version Example

Supports real-time streaming speech recognition, uses non-streaming models for error correction, and outputs text with punctuation. Currently, only single client is supported. For multi-concurrency, please refer to the C++ version service deployment SDK below.

Server Deployment

cd runtime/python/websocket
python funasr_wss_server.py --port 10095

Client Testing

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.

Service Deployment Software

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.

Docker Installation (optional)

If you have already installed Docker, skip this step.

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（Get the latest image version）：

sudo docker pull \
  registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.5
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-0.1.5

Server Start

After Docker is started, start the funasr-wss-server-2pass service program:

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

python3 funasr_wss_client.py --host "127.0.0.1" --port 10096 --mode 2pass

For more examples, please refer to docs

File Transcription Service, Mandarin (CPU)

Docker Image Download and Launch

Use the following command to pull and launch the FunASR software package Docker image（Get the latest image version）：

sudo docker pull \
  registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.3.0
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-0.3.0

Server Start

After Docker is started, start the funasr-wss-server service program:

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

Testing samples

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

Industrial Model Egs

If you want to use the pre-trained industrial models in ModelScope for inference or fine-tuning training, you can refer to the following command:

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

inference_pipeline = pipeline(
    task=Tasks.auto_speech_recognition,
    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')
print(rec_result)
# {'text': '欢迎大家来体验达摩院推出的语音识别模型'}

More examples could be found in docs

Academic model egs

If you want to train from scratch, usually for academic models, you can start training and inference with the following command:

cd egs/aishell/paraformer
. ./run.sh --CUDA_VISIBLE_DEVICES="0,1" --gpu_num=2

More examples could be found in docs