Speech to text open-source project set up on our server( Python, Ai )
Budget: $10 – $30 USD
Task:
Install WeNet ( An open source speech to text project ) and run the demo on our server.
Specific requirements:
1) Remotely build on our server (SSH access), the docker has been installed on the server.
WeNet has docker too, you can use docker to save building time.
2) Use the default configuration of WeNet, use pre-trained model, and only need English speech recognize. We will provide a .wav file in English for testing.
https://github.com/wenet-e2e/wenet
3) Demo needs to demonstrate the effect of real-time speech recognition and display the recognized text. The working directory is ~/speech-to-text/wenet
4) This Demo is only used to observe the operation effect of Wenet, so the configuration parameters are all default. Please do it as soon as possible.
In the future, we will propose revisions based on this demonstration effect, and will consider continuing to customize development based on WeNet if necessary.
Install WeNet ( An open source speech to text project ) and run the demo on our server.
Specific requirements:
1) Remotely build on our server (SSH access), the docker has been installed on the server.
WeNet has docker too, you can use docker to save building time.
2) Use the default configuration of WeNet, use pre-trained model, and only need English speech recognize. We will provide a .wav file in English for testing.
https://github.com/wenet-e2e/wenet
3) Demo needs to demonstrate the effect of real-time speech recognition and display the recognized text. The working directory is ~/speech-to-text/wenet
4) This Demo is only used to observe the operation effect of Wenet, so the configuration parameters are all default. Please do it as soon as possible.
In the future, we will propose revisions based on this demonstration effect, and will consider continuing to customize development based on WeNet if necessary.