1.words.txt and phones.txt in vosk-model-en-us-0.22-lgraph are different from my own model, and vosk-model-small-en-us-0.15 don't include these 2 files. In my practice, I delete the Gr.fst in vosk-model-small-en-us-0.15 and copy words.txt from vosk-model-en-us-0.22-lgraph to vosk-model-small-en-us-0.15, I got bad result in ASR with grammar, so I think vosk-model-en-us-0.22-lgraph and vosk-model-small-en-us-0.15 use different words.txt (because I delete Gr.fst in vosk-model-en-us-0.22-lgraph and use words.txt also get correct result), right?
2.no tree in vosk-model-small-en-us-0.15. actually, I need tree and L.fst to calculate goodness of pronunciation(gop), and I also need ASR with grammar
I dont know the resaons, can you please explain how to get tree, phones.txt words.txt and L.fst in vosk-model-small-en-us-0.15?
Hi dear author,
I have trained my own model with this doc https://github.com/alphacep/vosk-api/tree/master/training, but it's totally different from vosk-model-small-en-us-0.15 and vosk-model-en-us-0.22-lgraph.
1.words.txt and phones.txt in vosk-model-en-us-0.22-lgraph are different from my own model, and vosk-model-small-en-us-0.15 don't include these 2 files. In my practice, I delete the Gr.fst in vosk-model-small-en-us-0.15 and copy words.txt from vosk-model-en-us-0.22-lgraph to vosk-model-small-en-us-0.15, I got bad result in ASR with grammar, so I think vosk-model-en-us-0.22-lgraph and vosk-model-small-en-us-0.15 use different words.txt (because I delete Gr.fst in vosk-model-en-us-0.22-lgraph and use words.txt also get correct result), right?
2.no tree in vosk-model-small-en-us-0.15. actually, I need tree and L.fst to calculate goodness of pronunciation(gop), and I also need ASR with grammar
I dont know the resaons, can you please explain how to get tree, phones.txt words.txt and L.fst in vosk-model-small-en-us-0.15?
Thanks very much !!!