I am currently doing some testing with audio streaming over websockets and the integration of STT, so I found your repo, cloned, installed deepspeech and I noticed that the code of the server is not compatible with deepspeech version 0.7 and above. This is because they changed to a new model system, separated the language model in a scorer and did some changed to the Python API.
I managed to fix this for myself to be able to use it with the current deepspeech version. So to potentially prevent others from fixing it for themselves I created this pull request to make the required changes easily accessible.
Thank you for sharing this repo, this saved me some time to get started :smile:
I am currently doing some testing with audio streaming over websockets and the integration of STT, so I found your repo, cloned, installed deepspeech and I noticed that the code of the server is not compatible with deepspeech version 0.7 and above. This is because they changed to a new model system, separated the language model in a scorer and did some changed to the Python API.
I managed to fix this for myself to be able to use it with the current deepspeech version. So to potentially prevent others from fixing it for themselves I created this pull request to make the required changes easily accessible.
Thank you for sharing this repo, this saved me some time to get started :smile: