Ramanibharathi

Hi @nshmyrev I have trained my own model and the performance of the model is great in terms of both accuracy and speech. I found that increasing the beam provides...

Hi! @nshmyrev I'm using vosk-model-en-us-0.22-lgraph it takes around 2 secs to run test_simple.py with a wav input consisting of around 5-8 words. I'm using macbook air with dual-core Intel Core...

Ah! I didn't think about loading the model in memory! Apologies for that. I tested it now Initialisation takes around 1-2 seconds the transcript is generated in a span of...