spear-large-speech

from transformers import AutoModel
import torch

model = AutoModel.from_pretrained(
    "marcoyang/spear-large-speech", 
    trust_remote_code=True,
    force_download=False,
)
if torch.cuda.is_available():
    model = model.to("cuda")
model.eval()

device = next(model.parameters()).device
audio = torch.randn(1, 160000).to(device) # dummy audio input of 10 seconds
audio_len = torch.tensor([160000]).to(device)

with torch.no_grad():
    outputs = model(audio, audio_len)

encoder_out = outputs["encoder_out"] # (N,T,C)
encoder_out_lens = outputs["encoder_out_lens"] # (N)
middle_out = outputs["hidden_states"] # list of (N,T,C)

print(encoder_out)
print(encoder_out_lens)
print(len(middle_out)) # 11 layers
print(middle_out[-1].shape)
print(middle_out[-1])