Viewing profile — trowngon

Vosk https://github.com/alphacep/vosk-api

You don't even need to compare accuracy, you can just check the technology. Facebook model is trained on 256 GPU cards and you can fine-tune it to your domain in a day or two. The …

I believe most people already moved to offline engines. No need to send the data to some random guys like this Assembly. Nemo Conformer from Nvidia, Robust Wav2Vec from Facebook, V…

Movies are no longer just an imagination. Chances are they are shaping the world for real superhero superhuman arrival ;)

Deepspeech project is closed by Mozilla. Developers fired. Now they are Coqui.

Looks like after nvidia 1.5m grant devs returned back ;)

Looks like a fork of Mozilla DeepSpeech by former DeepSpeech developers. What is the relation to the original project?

Irrespective of the subject Deepspeech is very old archtecture with suboptimal results. You'd better try any recent conformer implementations (flashlight, nemo, wenet, etc) or wav2…

Assembly AI is at $0.5 per hour, not extremely reasonable these days. With open source models like Facebook RASR or Vosk you can get self-hosted solution with even better accuracy …

Are there open source projects like this?

Vosk supports both Italian and French. French model is trained by Linto project, pretty good one.