David Zurow
David Zurow
If you just mean the startup time when first starting the server, I believe the latest version of DeepSpeech may have a faster startup time, but I haven't had a...
The server and the `recognize` URL are for websocket connections only, not normal HTTP GET requests. The included client uses that for low-latency streaming; are you using it? It wouldn't...
Hmm, I don't use Anaconda, and I'm no websocket expert (thankfully haven't needed to debug it much). Actually, I just realized that I haven't tested the server running directly in...
I just tried it with your configuration except vanilla python and it worked. Maybe an anaconda issue?
I used python 3.6.3 from python.org, installed the requirements and the latest deepspeech from pip, and the 0.5.1 pretrained model.
Windows 10; normal non-powershell command prompt; no IDE.
Sure; good idea, and a PR would be great! Actually, I have some cleanup to commit for the client that might help, which I'll try to complete in a day...
@TMiguelT Cleanup complete. Also refactored some to ease external usage.
Ah, sorry about that. Thanks, @LexiconCode! I still need to integrate building those packages in my Continuous Integration. Reopening this as a reminder to myself.
That would be a good feature to add, but I haven't gotten around to it yet. There are many text to speech programs and libraries available nowadays, but the problem...