(简体中文|English)
FunASR Offline File Transcription Software Package provides a powerful speech-to-text offline file transcription service. With a complete speech recognition pipeline, it combines models for speech endpoint detection, speech recognition, punctuation, etc., allowing for the transcription of long audio and video files, spanning several hours, into punctuated text. It supports simultaneous transcription of hundreds of concurrent requests. The output is text with punctuation, including word-level timestamps, and it supports ITN (Initial Time Normalization) and user-defined hotwords. The server-side integration includes ffmpeg, enabling support for various audio and video formats as input. The software package provides client libraries in multiple programming languages such as HTML, Python, C++, Java, and C#, allowing users to use and further develop the software.
This document serves as a development guide for the FunASR offline file transcription service. If you wish to quickly experience the offline file transcription service, please refer to the one-click deployment example for the FunASR offline file transcription service (docs).
| TIME | INFO | IMAGE VERSION | IMAGE ID |
|---|---|---|---|
| 2024.09.26 | Fix memory leak, Support the SensevoiceSmall onnx model | funasr-runtime-sdk-cpu-0.4.6 | 8651c6b8a1ae |
| 2024.05.15 | Adapting to FunASR 1.0 model structure | funasr-runtime-sdk-cpu-0.4.5 | 058b9882ae67 |
| 2024.03.05 | docker image supports ARM64 platform, update modelscope | funasr-runtime-sdk-cpu-0.4.4 | 2dc87b86dc49 |
| 2024.01.25 | Optimized the VAD (Voice Activity Detection) data processing method, significantly reducing peak memory usage; memory leak optimization | funasr-runtime-sdk-cpu-0.4.2 | befdc7b179ed |
| 2024.01.08 | optimized format sentence-level timestamps | funasr-runtime-sdk-cpu-0.4.1 | 0250f8ef981b |
| 2024.01.03 | Added support for 8k models, optimized timestamp mismatch issues and added sentence-level timestamps, improved the effectiveness of English word FST hotwords, supported automated configuration of thread parameters, and fixed known crash issues as well as memory leak problems. | funasr-runtime-sdk-cpu-0.4.0 | c4483ee08f04 |
| 2023.11.08 | supporting punc-large model, Ngram model, fst hotwords, server-side loading of hotwords, adaptation to runtime structure changes | funasr-runtime-sdk-cpu-0.3.0 | caa64bddbb43 |
| 2023.09.19 | supporting ITN model | funasr-runtime-sdk-cpu-0.2.2 | 2c5286be13e9 |
| 2023.08.22 | integrated ffmpeg to support various audio and video inputs, supporting nn-hotword model and timestamp model | funasr-runtime-sdk-cpu-0.2.0 | 1ad3d19e0707 |
| 2023.07.03 | 1.0 released | funasr-runtime-sdk-cpu-0.1.0 | 1ad3d19e0707 |
If you have already installed Docker, ignore this step!
curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/install_docker.sh;
sudo bash install_docker.shIf you do not have Docker installed, please refer to Docker Installation
Use the following command to pull and launch the Docker image for the FunASR runtime-SDK:
sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.4.6
sudo docker run -p 10095:10095 -it --privileged=true -v /root:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.4.6Introduction to command parameters:
-p <host port>:<mapped docker port>: In the example, host machine (ECS) port 10095 is mapped to port 10095 in the Docker container. Make sure that port 10095 is open in the ECS security rules.
-v <host path>:<mounted Docker path>: In the example, the host machine path /root is mounted to the Docker path /workspace/models.
Use the flollowing script to start the server ：
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.txt 2>&1 &
# If you want to close ssl，please add：--certfile 0
# If you want to deploy the 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（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: /workspace/models/hotwords.txt):
# One hotword per line, format (hotword weight): 阿里巴巴 20"The funasr-wss-server supports downloading models from Modelscope. You can set the model download address (--download-model-dir, default is /workspace/models) and the model ID (--model-dir, --vad-dir, --punc-dir). Here is an example:
cd /workspace/FunASR/runtime
nohup bash run_server.sh \
--download-model-dir /workspace/models \
--model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx \
--vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
--punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx \
--itn-dir thuduj12/fst_itn_zh \
--lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst \
--certfile ../../../ssl_key/server.crt \
--keyfile ../../../ssl_key/server.key \
--hotword ../../hotwords.txt > log.txt 2>&1 &Introduction to run_server.sh parameters:
--download-model-dir: Model download address, download models from Modelscope by setting the model ID.
--model-dir: modelscope model ID or local model path.
--vad-dir: modelscope model ID or local model path.
--punc-dir: modelscope model ID or local model path.
--itn-dir modelscope model ID or local model path.
--port: Port number that the server listens on. Default is 10095.
--decoder-thread-num: The number of thread pools on the server side that can handle concurrent requests.
The script will automatically configure parameters decoder-thread-num and io-thread-num based on the server's thread count.
--io-thread-num: Number of IO threads that the server starts.
--model-thread-num: The number of internal threads for each recognition route to control the parallelism of the ONNX model.
The default value is 1. It is recommended that decoder-thread-num * model-thread-num equals the total number of threads.
--certfile <string>: SSL certificate file. Default is ../../../ssl_key/server.crt. If you want to close ssl，set 0
--keyfile <string>: SSL key file. Default is ../../../ssl_key/server.key.
--hotword: Hotword file path, one line for each hotword(e.g.:阿里巴巴 20), if the client provides hot words, then combined with the hot words provided by the client.
# Check the PID of the funasr-wss-server process
ps -x | grep funasr-wss-server
kill -9 PID
To replace the currently used model or other parameters, you need to first shut down the FunASR service, make the necessary modifications to the parameters you want to replace, and then restart the FunASR service. The model should be either an ASR/VAD/PUNC model from ModelScope or a fine-tuned model obtained from ModelScope.
# For example, to replace the ASR model with damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx, use the following parameter setting --model-dir
--model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx
# Set the port number using --port
--port <port number>
# Set the number of inference threads the server will start using --decoder-thread-num
--decoder-thread-num <decoder thread num>
# Set the number of IO threads the server will start using --io-thread-num
--io-thread-num <io thread num>
# Disable SSL certificate
--certfile 0
After executing the above command, the real-time speech transcription service will be started. If the model is specified as a ModelScope model id, the following models will be automatically downloaded from ModelScope: FSMN-VAD, Paraformer-lagre, CT-Transformer, FST-ITN, Ngram lm
If you wish to deploy your fine-tuned model (e.g., 10epoch.pb), you need to manually rename the model to model.pb and replace the original model.pb in ModelScope. Then, specify the path as model_dir.
After completing the deployment of FunASR offline file transcription service on the server, you can test and use the service by following these steps. Currently, FunASR-bin supports multiple ways to start the client. The following are command-line examples based on python-client, c++-client, and custom client Websocket communication protocol:
python funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "./data/wav.scp" --send_without_sleep --output_dir "./results"Introduction to command parameters:
--host: the IP address of the server. It can be set to 127.0.0.1 for local testing.
--port: the port number of the server listener.
--audio_in: the audio input. Input can be a path to a wav file or a wav.scp file (a Kaldi-formatted wav list in which each line includes a wav_id followed by a tab and a wav_path).
--output_dir: the path to the recognition result output.
--ssl: whether to use SSL encryption. The default is to use SSL.
--mode: offline mode.
--hotword: Hotword file path, one line for each hotword(e.g.:阿里巴巴 20)
--use_itn: whether to use itn, the default value is 1 for enabling and 0 for disabling.
. /funasr-wss-client --server-ip 127.0.0.1 --port 10095 --wav-path test.wav --thread-num 1 --is-ssl 1Introduction to command parameters:
--server-ip: the IP address of the server. It can be set to 127.0.0.1 for local testing.
--port: the port number of the server listener.
--wav-path: the audio input. Input can be a path to a wav file or a wav.scp file (a Kaldi-formatted wav list in which each line includes a wav_id followed by a tab and a wav_path).
--is-ssl: whether to use SSL encryption. The default is to use SSL.
--hotword: Hotword file path, one line for each hotword(e.g.:阿里巴巴 20)
--use-itn: whether to use itn, the default value is 1 for enabling and 0 for disabling.
If you want to define your own client, see the Websocket communication protocol
The code for FunASR-runtime is open source. If the server and client cannot fully meet your needs, you can further develop them based on your own requirements:
https://github.com/alibaba-damo-academy/FunASR/tree/main/runtime/websocket
https://github.com/alibaba-damo-academy/FunASR/tree/main/runtime/python/websocket
// The use of the VAD model consists of two steps: FsmnVadInit and FsmnVadInfer:
FUNASR_HANDLE vad_hanlde=FsmnVadInit(model_path, thread_num);
// Where: model_path contains "model-dir" and "quantize", thread_num is the ONNX thread count;
FUNASR_RESULT result=FsmnVadInfer(vad_hanlde, wav_file.c_str(), NULL, 16000);
// Where: vad_hanlde is the return value of FunOfflineInit, wav_file is the path to the audio file, and sampling_rate is the sampling rate (default 16k).See the usage example for details docs
// The use of the ASR model consists of two steps: FunOfflineInit and FunOfflineInfer:
FUNASR_HANDLE asr_hanlde=FunOfflineInit(model_path, thread_num);
// Where: model_path contains "model-dir" and "quantize", thread_num is the ONNX thread count;
FUNASR_RESULT result=FunOfflineInfer(asr_hanlde, wav_file.c_str(), RASR_NONE, NULL, 16000);
// Where: asr_hanlde is the return value of FunOfflineInit, wav_file is the path to the audio file, and sampling_rate is the sampling rate (default 16k).
See the usage example for details, docs
// The use of the PUNC model consists of two steps: CTTransformerInit and CTTransformerInfer:
FUNASR_HANDLE punc_hanlde=CTTransformerInit(model_path, thread_num);
// Where: model_path contains "model-dir" and "quantize", thread_num is the ONNX thread count;
FUNASR_RESULT result=CTTransformerInfer(punc_hanlde, txt_str.c_str(), RASR_NONE, NULL);
// Where: punc_hanlde is the return value of CTTransformerInit, txt_str is the text
See the usage example for details, docs