Skip to content

Simple Python HTTP-Server performing STT via HTTP-POST with DeepSpeech as backend.

License

Notifications You must be signed in to change notification settings

xdraylin/DeepSpeechHTTP

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 

Repository files navigation

DeepSpeechHTTP

Simple Python HTTP-Server performing STT via HTTP-POST with DeepSpeech as backend.

Setup

  • Install DeepSpeech via pip
  • Execute dshttp.py with the required parameters, eg.
    dshttp.py models/output_graph.pb models/alphabet.txt 8080 models/lm.binary models/trie
    

Usage

  • Encode the source WAV-formatted audio file (16kHz sampling rate) with base32
  • Post the encoded file to the server, eg. with curl -X POST -d @base_encoded_file.b32 server:8080
  • Server will return the result of STT as response

About

Simple Python HTTP-Server performing STT via HTTP-POST with DeepSpeech as backend.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages