Failing to load vosk model

I have already downloaded vosk-model-en-us-0.22 on Ubuntu22.04, but the output is stuck at the log file message
```ruby
LOG (VoskAPI:ReadDataFiles():model.cc:213) Decoding params beam=13 max-active=7000 lattice-beam=6
LOG (VoskAPI:ReadDataFiles():model.cc:216) Silence phones 1:2:3:4:5:11:12:13:14:15
LOG (VoskAPI:RemoveOrphanNodes():nnet-nnet.cc:948) Removed 0 orphan nodes.
LOG (VoskAPI:RemoveOrphanComponents():nnet-nnet.cc:847) Removing 0 orphan components.
LOG (VoskAPI:ReadDataFiles():model.cc:248) Loading i-vector extractor from vosk-model-en-us-0.22_planb/ivector/final.ie
LOG (VoskAPI:ComputeDerivedVars():ivector-extractor.cc:183) Computing derived variables for iVector extractor
LOG (VoskAPI:ComputeDerivedVars():ivector-extractor.cc:204) Done.
LOG (VoskAPI:ReadDataFiles():model.cc:279) Loading HCLG from vosk-model-en-us-0.22_planb/graph/HCLG.fst
LOG (VoskAPI:ReadDataFiles():model.cc:297) Loading words from vosk-model-en-us-0.22_planb/graph/words.txt
LOG (VoskAPI:ReadDataFiles():model.cc:308) Loading winfo vosk-model-en-us-0.22_planb/graph/phones/word_boundary.int
LOG (VoskAPI:ReadDataFiles():model.cc:315) Loading subtract G.fst model from vosk-model-en-us-0.22_planb/rescore/G.fst
LOG (VoskAPI:ReadDataFiles():model.cc:317) Loading CARPA model from vosk-model-en-us-0.22_planb/rescore/G.carpa
LOG (VoskAPI:ReadDataFiles():model.cc:323) Loading RNNLM model from /home/dictmanage/.cache/vosk/vosk-model-en-us-0.22/rnnlm/final.raw
```
and my jupyter kernel sometimes dies after the log message was output:

> Kernel Restarting
The kernel for Wav输出.ipynb appears to have died. It will restart automatically.

I have checked and ensured that the memory is enough to load the model of 16gb
and my code is basically the same as the example code provided.
```ruby
import wave
import sys
from vosk import Model, KaldiRecognizer, SetLogLevel
SetLogLevel(0)
wf = wave.open('text.wav', "rb")
if wf.getnchannels() != 1 or wf.getsampwidth() != 2 or wf.getcomptype() != "NONE":
print("Audio file must be WAV format mono PCM.")
sys.exit(1)
model = Model("vosk-model-en-us-0.22")
rec = KaldiRecognizer(model, wf.getframerate())
rec.SetWords(True)
rec.SetPartialWords(True)
result=[]
while True:
data = wf.readframes(4000)
if len(data) == 0:
break
if rec.AcceptWaveform(data):
print(rec.Result())
with open("output.json", "w", encoding="utf-8") as f:
json.dump(rec.Result()['result'], f, ensure_ascii=False, indent=4)
```

It is confusing that when I downloaded the model, the code above ran perfectly fine and had proper output, but when I ran the same code later on, it always got stuck around the log message above.
And rarely, when I run this block of code 20 times, there may be 1 time when something different would be output:
```ruby
ERROR (VoskAPI:ReadSparseWordFeatures():rnnlm-utils.cc:53) No value for feature-index 6837
Traceback (most recent call last):
File "/home/dictmanage/miniconda3/envs/MinerU6/lib/python3.10/site-packages/IPython/core/interactiveshell.py", line 3579, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "/tmp/ipykernel_565537/4006666277.py", line 19, in
model = Model(model_name="vosk-model-en-us-0.22")
File "/home/dictmanage/miniconda3/envs/MinerU6/lib/python3.10/site-packages/vosk/__init__.py", line 57, in __init__
raise Exception("Failed to create a model")
Exception: Failed to create a model
```
I really have no idea what's wrong.

P.S. If I use default model

> model = Model(lang="en-us")

Everything works fine.