Error when initializing context from Java

[muety]

When attempting to to run the following piece of Java code, I'm getting a rather non-descriptive error message. Any ideas how to debug this?

I compiled the libwhisper.so from the latest source code. Running ./server or ./stream works just fine.

My code (an excerpt):

// [...]
final WhisperCpp whisper = new WhisperCpp();

try {
    whisper.initContext("base.en");
} catch (FileNotFoundException e) {
    System.err.println("failed to load model file");
    return;
}
// [...]

Error:

whisper_init_from_file_with_params_no_state: loading model from '/home/ferdinand/.cache/whisper/ggml-base.en.bin'
whisper_init_with_params_no_state: use gpu    = 7
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw        = 192
whisper_model_load: loading model
whisper_model_load: n_vocab       = 51864
whisper_model_load: n_audio_ctx   = 1500
whisper_model_load: n_audio_state = 512
whisper_model_load: n_audio_head  = 8
whisper_model_load: n_audio_layer = 6
whisper_model_load: n_text_ctx    = 448
whisper_model_load: n_text_state  = 512
whisper_model_load: n_text_head   = 8
whisper_model_load: n_text_layer  = 6
whisper_model_load: n_mels        = 80
whisper_model_load: ftype         = 1
whisper_model_load: qntvr         = 0
whisper_model_load: type          = 2 (base)
whisper_model_load: adding 1607 extra tokens
whisper_model_load: n_langs       = 99
whisper_backend_init: using CUDA backend
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:   no
ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 3050 Laptop GPU, compute capability 8.6, VMM: yes
whisper_model_load:    CUDA0 total size =   147.37 MB
whisper_model_load: model size    =  147.37 MB
whisper_backend_init: using CUDA backend
whisper_mel_init: n_len = 3001, n_len_org = 1, n_mel = 80
whisper_init_state: kv self size  =   18.87 MB
whisper_init_state: kv cross size =   18.87 MB
whisper_init_state: kv pad  size  =    3.15 MB
terminate called after throwing an instance of 'std::out_of_range'
  what():  map::at