A docker which includes deep-speech, the English model & DS-server, ready for use out of the box
2.6K
docker run -p 9090:8080 amitbet/deepspeech curl -X POST --data-binary @.wav http://localhost:9090/stt
Audio has to be 16Khz, 16bit PCM wav, (DeepSpeech is kinda picky about that) You can find my testing audio here: https://github.com/amitbet/speech/tree/master/testing-audio
Content type
Image
Digest
Size
1.8 GB
Last updated
over 8 years ago
docker pull amitbet/deepspeech