test.py

from transformers import AutoModel
import librosa
import wget
from modeling_diva import DiVAModel

filename = wget.download(
    "https://github.com/ffaisal93/SD-QA/raw/refs/heads/master/dev/eng/irl/wav_eng/-1008642825401516622.wav"
)

speech_data, _ = librosa.load(filename, sr=16_000)

model = DiVAModel.from_pretrained("./")

print(model.generate([speech_data]))
print(model.generate([speech_data], ["Repeat verbatim what is said to you."]))

filename = wget.download(
    "https://github.com/ffaisal93/SD-QA/raw/refs/heads/master/dev/eng/irl/wav_eng/-2426554427049983479.wav"
)

speech_data2, _ = librosa.load(filename, sr=16_000)

print(
    model.generate(
        [speech_data, speech_data2],
        ["Reply Briefly Like A Pirate", "Reply Briefly Like A New Yorker"],
    )
)